Syllabus for ME Artificial Intelligence University of Mumbai_1 Syllabus Mumbai University

Page 1

Page 2

Page 3

Page 4

Page 5

Page 6

UNIVERSITY OF MUMBAI


Syllabus
for
Master of Engineering
Program: M.E. ( Artificial Intelligence)
Under
FACULTY OF TECHNOLOGY
Computer Engineering Discipline


(As per Choice Based Credit and Grading System )

with effect from
Academic Year 2019 -20

Page 7

University of Mumbai, M.E. (Artificial Intelligence), 2019. 2 From the Dean ’s Desk:
The era of digitalization has changed and is changing the way we produce, communicate and even
the way cities work. Artificial Intelligence (AI) is considered to be the next remarkable technological
development, alike the past industrial revolutions and th e current digital revolution. The scope of the
AI market seems promising with opportunities in diverse sectors such as the healthcare, security,
retail, agriculture, automotive, manufacturing, and finance. In fact, it is estimated that AI will
transform th e labour market by creating more a million new job opportunities related to this field.
Also, the increasing amount of digital data and the growing consumer preference for smart devices is
resulting into multi fold rise in the demand for engineers with pr oficiency in AI. This Masters
programme in Artificial Intelligence will open the doors to gain skills for developing of a wide range
of applications with efficiency, accuracy and reduced risk.
To meet the challenge of ensuring excellence in engineering edu cation, the issue of quality needs to
be addressed, debated and taken forward in a systematic manner. Accreditation is the principal means
of quality assurance in higher education. The major emphasis of accreditation process is to measure
the outcomes of t he program that is being accredited. In line with this, Faculty of Technology of
University of Mumbai has taken a lead in incorporating philosophy of outcome based education in
the process of curriculum development.
Faculty of Technology, University of Mum bai, in one of its meeting unanimously resolved that, each
Board of Studies shall prepare some Program Educational Objectives (PEO’s) and give freedom to
affiliated Institutes to add few (PEO’s) and course objectives and course outcomes to be clearly
defin ed for each course, so that all faculty members in affiliated institutes understand the depth and
approach of course to be taught, which will enhance learner’s learning process. It was also resolved
that, maximum senior faculty from colleges and experts fr om industry to be involved while revising
the curriculum. I am happy to state that, each Board of studies has adhered to the resolutions passed
by Faculty of Technology, and developed curriculum accordingly. In addition to outcome based
education, Choice B ased Credit and Grading System is also introduced to ensure quality of
engineering education.
Choice Based Credit and Grading System enables a much -required shift in focus from teacher -centric
to learner -centric education since the workload estimated is ba sed on the investment of time in
learning not in teaching. It also focuses on continuous evaluation which will enhance the quality of
education. University of Mumbai has taken a lead in implementing the system through its affiliated
Institutes, Faculty of Technology has devised a transparent credit assignment policy adopted ten
points scale to grade learner’s performance. Choice Based Credit and Grading System was
implemented for First Year Master of Engineering from the academic year 2016 -2017and
subsequen tly the system has been carried forward for Second Year Master of Engineering in the
academic year 2017 -2018.

Dr. Suresh K. Ukarande
Dean (I/ c),
Faculty of Science & Technology,
Member - Board of Dean s, Academic Council and Senate
University of Mumbai, Mumbai

Page 8

University of Mumbai, M.E. (Artificial Intelligence), 2019. 3 Preamble:
University of Mumbai feels that it is desirable to provide specialized Masters programme in Artificial
Intelligence to address the needs of the industry, which today requires more specialized resource in
each field.
The objective of the programme is to give students a deeper understanding of technology and how to
apply logic to create Artificial Intelligence and teach them to create and programme unique projects
for the Artificial Intelligence field. Many skills may be developed during this master’s program that
could lead to high -paying jobs and career advancements in the future. Students may develop critical -
thinking and technology skills that help them excel in their career field, and they may also learn
crucial pr oblem -solving abilities.
The M. E. in Artificial Intelligence programme is offered to students who are interested in advanced
learning and research in any area of Artificial Intelligence, Machine Learning and Business
Intelligence. Applicants to this progr amme are expected to have a background in Computer Science
and Engineering / Information Technology / Electronics Engineering / Electronics and
Telecommunication Engineering / Electrical Engineering / Instrumentation Engineering / Power
Electronics.
The pr ogramme is a 72 -credit post -graduate degree programme, which is usually spread over 4
semesters for a full -time student. About two -thirds of the credits involve coursework, and the
remaining consists of project work. The emphasis is on conducting original research and writing a
thesis individually. The programme is flexible enough to allow a student to specialize in any topic of
interest by taking elective (optional) courses and working on a research project in that area.
Faculty of Technology, University of Mumbai has taken a lead in incorporating philosophy of Choice
Based Education in the process of curriculum development.

Dr. Subhash K. Shinde
Chairman,
Adhoc Board of Studies in Computer Engineering,
University of Mumbai, Mumbai.

Page 9

University of Mumbai, M.E. (Artificial Intelligence), 2019. 4 PROGRAM STRUCTURE FOR M.E. (ARTIFICIAL INTELLIGENCE)
(With Effect from 2019 -20)
University of Mumbai
Semester - I
Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC101 Building Blocks of Artificial
Intelligence 04 - - 04 - - 04
MEAIC102 Machine Learning and
Pattern Recognition 04 - - 04 - - 04
MEAIC103 Mathematical Foundations of
Data Science 04 - - 04 - - 04
MEAIDLO -I Department Level Optional
Course – I 04 - - 04 - - 04
ILO-I Institute Level Optional
Course – I* 03 - - 03 - - 03
MEAIL101 AI Programming Lab - 02 - - 01 - 01
MEAIL102 Data Science Lab - 02 - - 01 - 01
Total 19 04 - 19 02 - 21

Course Code Course Name Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
MEAIC101 Building Blocks of
Artificial Intelligence 20 20 20 80 03 - - 100
MEAIC102 Machine Learning
and Pattern
Recognition 20 20 20 80 03 - - 100
MEAIC103 Mathematical
Foundations of Data
Science 20 20 20 80 03 - - 100
MEAIDLO -I Department Level
Optional Course – I 20 20 20 80 03 - - 100
ILO-I Institute Level
Optional Course – I 20 20 20 80 03 - - 100
MEAIL101 AI Programming Lab - - - - - 25 25 50
MEAIL102 Data Science Lab - - - - - 25 25 50
Total 100 100 100 400 - 50 50 600

Page 10

University of Mumbai, M.E. (Artificial Intelligence), 2019. 5 PROGRAM STRUCTURE FOR M.E. (ARTIFICIAL INTELLIGENCE)
(With Effect from 2019 -20)
University of Mumbai
Semester - I

Department Level Optional Course – I#
Course Code Course Name
MEAIDLO1011 Computer Vision
MEAIDLO1012 Natural Language Processing
MEAIDLO1013 Design and Analysis of Algorithms
MEAIDLO1014 Information Retrieval
MEAIDLO1015 Blockchain

Institute Level Optional Course – I*
Course Code Course Name
ILO1011 Product Lifecycle Management
ILO1012 Reliability Engineering
ILO1013 Management Information System
ILO1014 Design of Experiments
ILO1015 Operation Research
ILO1016 Cyber Security and Laws
ILO1017 Disaster Management & Mitigation Measures
ILO1018 Energy Audit and Management

# Department Level Optional Course (DLO): Every student is required to take one Department
Elective Course for Semester I and Semester II. Different sets of courses will run in both the
semesters. Students can take these courses from the list of department e lectives, which are closely
allied to their disciplines.
* Institute Level Optional Course (ILO): Every student is required to take one Institute Elective
Course for Semester I and Semester II, which is not closely allied to their disciplines. Different se ts
of courses will run in the both the semesters.

Page 11

University of Mumbai, M.E. (Artificial Intelligence), 2019. 6 PROGRAM STRUCTURE FOR M.E. (ARTIFICIAL INTELLIGENCE)
(With Effect from 2019 -20)
University of Mumbai
Semester - II
Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC201 Deep and Reinforcement
Learning 04 - - 04 - - 04
MEAIC202 Big Data Analytics 04 - - 04 - - 04
MEAIC203 Bio-inspired Artificial
Intelligence 04 - - 04 - - 04
MEAIDLO -II Department Level Optional
Course – II 04 - - 04 - - 04
ILO-II Institute Level Optional
Course – II 03 - - 03 - - 03
MEAIL201 Machine Learning Lab - 02 - 01 - 01
MEAIL202 Big Data Lab - 02 - 01 - 01
Total 19 04 - 19 02 - 21

Course Code Course Name Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
MEAIC201 Deep and
Reinforcement
Learning 20 20 20 80 03 - - 100
MEAIC202 Big Data Analytics 20 20 20 80 03 - - 100
MEAIC203 Bio-inspired
Artificial Intelligence 20 20 20 80 03 - - 100
MEAIDLO -II Department Level
Optional Course – II 20 20 20 80 03 - - 100
ILO-II Institute Level
Optional Course – II 20 20 20 80 03 - - 100
MEAIL201 Machine Learning
Lab - - - - - 25 25 50
MEAIL202 Big Data Lab - - - - - 25 25 50
Total 100 100 100 400 - 50 50 600

Page 12

University of Mumbai, M.E. (Artificial Intelligence), 2019. 7 PROGRAM STRUCTURE FOR M.E. (ARTIFICIAL INTELLIGENCE)
(With Effect from 2019 -20)
University of Mumbai
Semester - II
Department Level Optional Course – II
Course Code Course Name
MEAIDLO2021 Artificial Intelligence in Bioinformatics
MEAIDLO2022 IoT Data Analytics
MEAIDLO2023 Speech Recognition
MEAIDLO202 4 Autonomous Robotics
MEAIDLO2025 Mixed Reality
MEAIDLO2026 Robotics Process Automation

Institute Level Optional Course – II
Course Code Course Name
ILO2021 Project Management
ILO2022 Finance Management
ILO2023 Entrepreneurship Development and Management
ILO2024 Human Resource Management
ILO2025 Professional Ethics and CSR
ILO2026 Research Methodology
ILO2027 IPR and Patenting
ILO2028 Digital Business Management
ILO2029 Environmental Management

Page 13

University of Mumbai, M.E. (Artificial Intelligence), 2019. 8 Semester – III
Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIS301 Seminar: State -of-the-art
research topics - 06 - - 03 - 03
MEAID301 Dissertation – I - 24 - - 12 - 12
Total - 30 - - 15 - 15

Course Code Course Name Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
MEAIS301 Seminar: State -of-
the-art research
topics - - - - - 50 50 100
MEAID301 Dissertation – I - - - - - 100 - 100
Total - - - - - 150 50 200
Semester – IV
Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAID401 Dissertation – II - 30 - - 15 - 15
Total - 30 - - 15 - 15

Course Code Course Name Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
MEAID401 Dissertation - II - - - - - 100 100 200
Total - - - - - 100 100 200

Page 14

University of Mumbai, M.E. (Artificial Intelligence), 2019. 9 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC101 Building Blocks of
Artificial
Intelligence 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To introduce the concepts and techniques of building blocks of Artificial Intelligence and S oft
Computing techniques and their difference from conventional techniques.
2. To generate an ability to design, analyze and perform experiments on real life problems using
various Neural Network algorithms.
3. To conceptualize Fuzzy L ogic and its implementation for various real-world applications.
4. To provide the understanding of Genetic Algorithms and its application s in developing solutions
to real -world problems.
5. To introduce the need and concept of hybrid soft computing algorithms .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand AI concepts used to develop solutions that mimic human like thought process on
deterministic machines for real-world problems.
2. Analyze and e valuate whether a problem can be solved using AI techniques and analyze the same
using basic concepts of AI .
3. Understand the fundamental concepts of Neural Networks , different neural network architectures,
algorithms, applications and their limitations.
4. Apply Fuzzy Logic, the concept of fuzziness and fuzzy set theor y in various systems .
5. Apply Genetic Algorithms in problems with self -learning situations that seek global optimum .
6. Create solutions to real -world problems using Neural Network, Genetic Algorithms, Fuzzy Logic
or their Hybrid systems.
Prerequisite s: Data Structures & Algorithms, Fundamentals of Mathematics.
Sr.
No. Module Detailed Content Hours
1 Foundations of
Artificial
Intelligence Introduction to artificial intelligence; Application areas of
artificial intelligence; State space search: Depth first search,
Breadth first search; Heuristic search: Best first search , Hill
Climbing, Beam Search, Tabu Search ; Introduction to
randomized search: Simulated annealing, Genetic algorithms,
Ant colony opti mization; Introduction to expert systems ;
Introduction to AI -related fields like game playing, speech
recognition, language detection machine, computer vision,
robotics. 8
2 Introduction to
Soft Computing Importance of soft computing; Soft computing versus hard
computing; Supervised and unsupervised learning ; Introduction 6

Page 15

University of Mumbai, M.E. (Artificial Intelligence), 2019. 10 to main components of soft computing: Fuzzy logic, Neural
networks, Genetic algorithms.
3 Neural Networks Basic concepts of neural network; Overview of learning rules
and paramete rs; Activation functions; Single layer perceptron
and multilayer perceptron ; Multilayer feed forward network;
Backpropagation networks: Architecture, Algorithm, Variation
of standard backpropagation neural network; Radial basis
function network; Recurrent neural network; Introduction to
Associative Memory; Recent applications. 10
4 Genetic
Algorithms Difference between traditional algorithms and Genetic
Algorithm (GA); Basic concepts of GA; Working principle;
Encoding methods; Fitness function; GA Operators:
Reproduction, Crossover, Mutation; Convergence of GA;
Detailed algorithmic steps; Adjustment of parameters; Multi -
criteria optimization; Solution of typical problems using
genetic algorithm; Recent applications. 8
5 Fuzzy Logic Concepts of unce rtainty and imprecision; Concepts, properties
and operations on classical sets and fuzzy sets; Classical &
fuzzy relations; Membership functions and its types;
Fuzzification; Fuzzy rule -based systems; Defuzzification;
Fuzzy propositions; Fuzzy extension pr inciple; Fuzzy inference
system; Recent applications. 8
6 Hybrid Systems Introduction to hybrid systems: Fuzzy -neural systems, Genetic -
fuzzy systems, Neuro -genetic systems; Details of any one
method for each hybrid system. 8
Text Books:
1. S. Rajasekaran and G. A. Vijayalakshmi Pai, Neural Networks, Fuzzy Logic and Genetic
Algorithm: Synthesis and Applications, PHI .
2. S. N. Sivanandam and S. N. Deepa, Principles of Soft Computing, 2nd ed., Wiley India.
Reference Books:
1. J. Zurada , Introduction to Artificial Neural Systems, Jaico Publishing House.
2. D. Goldberg , Genetic Algorithms in Search, Optimization and Machine Learning , Addison -
Wesley
3. G. Klir , B. Yuan, Fuzzy Sets and Fuzzy Logic: Theory and A: Theory and Applications, Pearson.
Internal Assessment:
Assessment con sists of two tests out of which one should be compulsor ily class test (on minimum 02
modules) and the other can be either a class test or assignment on real-world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All question s carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 16

University of Mumbai, M.E. (Artificial Intelligence), 2019. 11 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC 102 Machine Learning
and Pattern
Recognition 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand the concept of a pattern and the basic approach to the development of pattern
recognition and machine intelligence algorithms.
2. To u nderstand and apply the basic methods of feature extraction, feature evaluation, and data
mining.
3. To u nderstand a nd apply both supervised and unsupervised machine learning algorithms to detect
and characterize patterns in real -world data.
4. To d evelop prototype pattern recognition algorithms that can be used to study algorithm behavior
and performance against real -world multivariate data.
5. To understand complexity of machine learning algorithms, their limitations and open -issues.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the fundamentals of pattern recognition and machine learning.
2. Understand the issue of dimensionality and apply suitable feature extraction methods considering
the characteristics of a given problem.
3. Apply parametric and non -parametric methods for pattern recognition in real -world problems.
4. Create solutions to real -world problems using pattern recognition and machine intelligence
algorithms.
5. Understand and apply ensemble methods for performance enhancement of machine learning
algorithms.
6. Analyze the performance of machine learning algorithms , effect of parameters and tuning of
parameters.

Prerequisite s: Fundamentals of Data Mining, Fundamentals of Mathematics.

Sr.
No. Module Detailed Content Hours
1 Introduction Basic definitions; Hypothesis space and inductive bias;
Data cleaning; Data transformation; Evaluation; Model
visualization; Cross -validation; Linear Regression . 6
2 Feature Extraction Curse of dimensionality; Principal component
analysis; Fisher linear discriminant, Feature extraction
from multivariate data, image data ; Feature evaluation. 8
3 Non-parametric
Methods for Pattern Non-numeric data or nominal data; Linear regression;
Decision tree algorithms: ID3, C4.5, Classification and 10

Page 17

University of Mumbai, M.E. (Artificial Intelligence), 2019. 12 Recognition Regression Trees (CART); Overfitting and
underfitting.
4 Bayes Learning and
Parametric Estimation
Methods Maximum -Likelihood estimation; Maximum a
posteriori estimation; Naïve Bayes and Bayesian
classifiers; K-nearest neighbour method; Support
Vector Machines; Algorithms for clustering: K -means,
Hierarchical and other methods. 10
5 Ensemble Classifiers Need and usefulness of ensemble classifiers; Bagging;
Boosting, Random forests; Decorate; Vote; Stacking. 8
6 Algorithmic
Performance
Evaluation Analysis of classification, clustering, prediction,
association al gorithms; Approaches of parameter
tuning . 6
Text Books:
1. T. Mitchell, Machine Learning, McGraw Hill.
2. M. Gopal, Applied Machine Learning, McGraw Hill.
Reference Books:
1. A. Ethem, Introduction to Machine Learning, PHI Learning Pvt. Ltd.
2. M. Evangelia, Supervised and Unsupervised Pattern Recognition, CRC Press.
3. C. Bishop , Neural Networks for Pattern Recognition , Oxford University Press .
4. G. James, D. Witten, T. Hastie, R. Tibshirani, Introduction to Statistical Learning, Springer.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In que stion paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 18

University of Mumbai, M.E. (Artificial Intelligence), 2019. 13 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC103 Mathematical
Foundations of
Data Science 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
This course will introduce students to the fundamental mathematical concepts required for applying
data science .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the importance of linear algebra, statistics and probability from data science
perspective.
2. Understand the elements of structured data and data distribution for binary a s well as categorical
data.
3. Apply the knowledge of sampling and distribution algorithms to evaluate the real distribution of
sampling data.
4. Apply the knowledge of significance testing, use of null value hypothesis to outline the
conditions for a particular test.
5. Evaluate and analyze the results of confusion matrix .
6. Apply optimization techniques for improvising performance .
Prerequisite s: Fundamentals of Probability and Statistics.
Sr.
No. Module Detailed Content Hours
1 Basics of Data
Science Introduction; Importance of linear algebra, statistics
and optimization from a data science perspective;
Structured thinking for solving data science problems;
Probability, Statistics and Random Processes:
Probability theory and axioms; Random variables. 8
2 Linear Algebra Matrices and their properties (determinants, traces,
rank, nullity, etc.); Eigenvalues and eigenvectors;
Matrix factorizations; Inner products; Distance
measures. 8
3 Exploratory Data
Analysis Elements of structured data; Estimates of location;
Estimates of variability; Expectations and moments;
Exploring the data distribution; Exploring binary and
categorical data ; Covariance and correlation;
Exploring two or more variables. 8
4 Data and Sampling
Distributions Random sampling and sample bias; Selection bias;
Central limit theorem; Standard error; Bootstrap; 8

Page 19

University of Mumbai, M.E. (Artificial Intelligence), 2019. 14 Confidence intervals; Normal distribution; Long -tailed
distributions; Student’s t -distribution; Binomial
distribution; Poisson distributions; Exponential
distribution; Weibull distribution; Fitting a model.
5 Statistics and
Significance Testing Hypothesis tests ; A/B testing ; Chi-square test ;
confidence interv als; p-values ; ANOVA ; t-test;
Confidence (statistical) intervals; Degrees of freedom ;
White -noise process. 8
6 Evaluation and
Optimization Mathematics in algorithmic performance evaluation:
Confusion matrix; Precision; Recall; Specificity; ROC
Curve; AUC; Lift; Optimization: Global and local
optima; Unconstrained and constrained optimization;
Introduction to least squares optimization. 8
Text Books:
1. P. Bruce and A. Bruce, Practical Statistics for Data Scientists: 50 Essential Concepts , O’Reilly .
2. C. O’Neil and R. Schutt, Doing Data Science, O’Reilly.
Reference Books:
1. G. Strang, Introduction to Linear Algebra, 5th edition, Wellesley -Cambridge Press, USA.
2. W. Hines, D. Montgomery, D. Goldman, C. Borror, Probability and Statistics in Engineering,
Wiley India Pvt. Ltd.
3. A. Agresti, C. Franklin, B. Klingenberg, Statistics: The Art and Science of Learning from Data,
Global Edition, Pearson.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours a s mentioned in the syllabus.

Page 20

University of Mumbai, M.E. (Artificial Intelligence), 2019. 15 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO1011 Computer
Vision 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To review image processing techniques for computer vision.
2. To understand shape and region analysis.
3. To understand Hough Transform and its applications to detect lines, circles, ellipses.
4. To understand three -dimensional image analysis techniques.
5. To understand motion analysis.
6. To implement computer vision algorithms for real -world problems.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand and apply fundamental image processing techniques required for computer vision.
2. Analyze shapes and regions .
3. Apply Hough Transform for line, circle, and ellipse detections.
4. Understand and analyze 3D vision techniques.
5. Understand motion analysis.
6. Develop applications using computer vision techniques .
Prerequisite s: Fundamentals of Image Processing.
Sr.
No. Module Detailed Content Hours
1 Image Processing
Foundations Review of image processing techniques; classical
filtering operations; thresholding techniques; edge
detection techniques; corner and interest point
detection; mathematical morphology; texture. 9
2 Shapes And Regions Binary shape analysis; connectedness; object
labelling and counting; size filtering; di stance
functions; skeletons and thinning; deformable shape
analysis; boundary tracking procedures; active
contours; shape models and shape recognition;
centroidal profiles; handling occlusion; boundary
length measures; boundary descriptors; chain codes;
Fourier descriptors; region descriptors; moments. 9
3 Hough Transform Line detection; Hough Transform (HT) for line
detecti on; foot-of-normal method; line localization;
line fitting; RANSAC for straight line detection; HT
based circular object detection; accurate centre
location; speed problem; ellipse detection; Case 9

Page 21

University of Mumbai, M.E. (Artificial Intelligence), 2019. 16 study: Human Iris location; hole detection;
generalized Hough Transform (GHT); spatial
matched filtering; GHT for ellipse detection; object
location; GHT for feature collation.
4 3D Visio n Methods for 3D vision; projection schemes; shape
from shading; photometric stereo; shape from
texture; shape from focus; active range finding;
surface representations; point -based representation;
volumetric representations; 3D object recognition;
3D reco nstruction. 9
5 Introduction To
Motion Triangulation; bundle adjustment; translational
alignment; parametric motion; spline -based motion;
optical flow; layered motion 6
6 Applications and Case
Studies Implementation of a pplication like face detection,
face recognition, eigen faces, surv eillance ,
foreground -background separation , particle filters ,
Chamfer matching , tracking , and occlusion;
combining views from multip le cameras; human gait
analysis; locating roadway; road markings;
identifying r oad signs; locating pedestrians, etc. ;
Case Studies and recent researches in Computer
Vision. 6
Text Books:
1. D. Forsyth, J. Ponce, Computer Vision: A Modern Approach, Pearson Education.
2. J. Solem, Programming Computer Vision with Python: Tools and Algorithms for Analyzing
Images, O’Reilly.
Reference Books:
1. M. Nixon and A. Aquado, Feature Extraction & Image Processing for Computer Vision, 3rd
Edition, Academic Press .
2. R. Jain, R. Kasturi, B. Schunck, Machine Vision, Indo American Books .
3. R. Szeliski, Computer Vision: Algorithms and Applications, Springer.
4. S. Prince, Computer Vision: Models, Learning, and Inference, Cambridge University Press
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours a s mentioned in the syllabus.

Page 22

University of Mumbai, M.E. (Artificial Intelligence), 2019. 17 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO1012 Natural
Language
Processing 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To explain the leading trends and systems in natural language processing.
2. To understand the concepts of morphology, syntax, semantics and pragmatics of the language.
3. To recognize the significance of pragmatics for natural language understanding.
4. To enable students to describe the application based on natural language processing and to show
the points of syntactic, semantic and pragmatic processing.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand fundamentals of Natural Language Processing.
2. Model linguistic phenomena with formal grammars.
3. Design, implement and analyze Natural Language Processing algorithms.
4. Understand approaches to syntax, semantics and discourse generation in natural language
processing.
5. Apply NLP techniques to design real world NLP applications, such as machine translation, text
categorization, text s ummarization, information extraction, etc.
6. Implement proper experimental methodology for training and evaluating empirical NLP systems.
Prerequisite s: Fundamentals of Mathematics and Computer Programming skills.
Sr.
No. Module Detailed Content Hours
1 Introduction History of NLP; Generic NLP system; Levels of NLP;
Knowledge in language processing problem; Ambiguity
in natural language; Stages in NLP; Challenges of NLP;
Role of machine learning; Brief history of the field;
Applications of NLP: Machine tr anslation, Question
answering system, Information retrieval, Text
categorization, text summarization & Sentiment
analysis. 8
2 Words & Word Forms Morphology analysis survey of English morphology,
inflectional morphology & derivational morphology;
Regular expressions; Finite automata; Finite state
transducers (FST); Morphological parsing with FST;
Lexicon free FST, Porter stemmer, N -Grams, N -gram
language model, N -gram for spelling correction. 10
3 Syntax Passing Part-of-Speech tagging (POS); Lexical synta x tag set for
English (Penn Treebank); Rule based POS tagging;
Stochastic POS tagging; Issues: Multiple tags & words, 8

Page 23

University of Mumbai, M.E. (Artificial Intelligence), 2019. 18 unknown words, class -based n -grams, HM Model ME,
SVM, CRF; Context Free Grammar; Constituency;
Context free rules & trees; Sentence level construction;
Noun Phrase; Coordination; Agreement; Verb phrase &
sub categorization.
4 Semantic Analysis Attachment for fragment of English sentences, noun
phrases, verb phrases, prepositional phrases;
Relations among lexemes & their senses; Homonymy,
Polysemy based disambiguation & limitations, Robust
WSD; Machine learning approach and dictionary -based
approach. 8
5 Discourse Discourse reference resolution; Reference phenomenon;
Syntactic & semantic constraints on co reference;
Preferences in pronoun interpretation; Algorithm for
pronoun resolution; Text coherence; Discourse
structure. 8
6 Applications and Case
Studies Implementation of applications like Machine translation ,
Information retrieval, Question answers system ,
Categorization, Summarizatio n; Sentiment analysis ;
Case Studies and recent researches in Natural Language
Processing 6
Text Books:
1. A. Géron, Hands -On Machine Learning with Scikit -Learn and TensorFlow: Concepts, Tools, and
Techniques to Build Intelligent Systems, O'Reilly.
2. T. Siddiqui , Natural Language Processing and Information Retrieval , Oxford University Press .
3. S. Bird, Natural Language Processing with Python, 1st edition, O'Reilly.
Reference Books:
1. D. Rao and B. McMahan, Natural Language Processing with PyTorch: Build Intelligent
Language Applications Using Deep Learning, O'Reilly.
2. D. Jurafsky and J. Martin, Speech and Language Processing, 2nd edition, Prentice Hall .
3. A. Kao, Natural Language Processing and Text Mining , Elsevier .
4. A. James, Natural Language Understanding, 2nd edition, Pearson
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 24

University of Mumbai, M.E. (Artificial Intelligence), 2019. 19 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO1013 Design and
Analysis of
Algorithms 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand the usage of algorithms in computing.
2. To learn and use hierarchical data structures and its operations.
3. To learn the usage of parallel algorithms and its applications.
4. To select and design data structures and algorithms that is appropriate for problems.
5. To study about NP Completeness of problems.
6. To analyze the running time and space complexity of algorithms.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand fundamentals of designing and analyzing algorithms.
2. Design advanced data structures and algorithms to solve computing problems.
3. Analyze the running time and space complexity of algorithms.
4. Design algorithms using greedy, dynamic and string -matching algorithms to solve real-life
problems .
5. Implement parallel algorithms for suitable applications.
6. Understand concepts of NP -completeness and evaluate algorithms accordingly.
Prerequisite s: Data Structures, Programming skills .
Sr.
No. Module Detailed Content Hours
1 Introduction to
Analysis of
Algorithms Design and analysis fundamentals; Performance
analysis: space and time complexity; Growth of a
function: Asymptotic notation; Mathematical
background for algorithm analysis, Recurrences:
Substitution method, Recursion -tree method, Master
method; Randomized algorithms. 8
2 Advanced Data
Structures B trees; B+ trees; 2 -3 tree operations; Tries; Heap
operations; AVL tree; Huffman code; Heap
operations; Topological sort ; Analysis of all
problems. 8
3 Greedy and Dynamic
Algorithms Characteristics of greedy algorithms; Problem
solving using greedy algorithms: Job scheduling
problem, Graph travelling and colouring problem,
Knapsack problem, Matrix Chain Multiplication
problem; The principle of optimality for dynamic
progra mming; Problem solving using dynamic 10

Page 25

University of Mumbai, M.E. (Artificial Intelligence), 2019. 20 algorithms: Making change problem, Assembly line
scheduling, Knapsack problem, Matrix chain
multiplication problem ; Analysis of all problems.
4 Parallel Algorithms Sequential vs. Parallel Algorithms; Models: Data
parallel model, Task graph model, Work pool model,
Master slave model, Producer consumer or pipeline
model; Hybrid model; Speedup and efficiency;
Examples of parallel algorithms: Parallel sorting,
Parallel matrix chain multiplication ; Analysis of all
problems. 8
5 Applied Algorithms String matching algorithms: The naive string -
matching algorithm, The Rabin -Karp algorithm,
String Matching with finite automata, The Knuth -
Morris -Pratt algorithm, Longest Common
Subsequence; Randomized Algorithms: Monte Carlo
and Las Vegas algorithms; Analysis of artificial
intelligence algorithms: Decision tree classifier,
Neural networks . 8
6 NP-Completeness and
Approximation
Algorithms Introduction to NP -Completeness: The clas s P and
NP, NP -Complete, NP -Hard, NP -Completeness and
reducibility; Approximation algorithms: Vertex -
cover problem, Traveling -salesman problem. 6
Text Books:
1. T. Cormen, C. Leiserson, R Rivest and C. Stein, Introduction to Algorithms, 3rd edition, Prentice
Hall.
2. G. Brassard, P. Bratley, Fundamental of Algorithms, PHI.
Reference Books:
1. A. Levitin, Introduction to Design and Analysis of Algorithms, Pearson .
2. S. Basu, Design Methods and Analysis of Algorithm, PHI .
3. A. Bhargava, Grokking Algorit hms: An illustrated guide for programmers and other curious
people, Manning Publications.
4. A. Basheer, M. Zaghlool, FPGA -Based High Performance Parallel Computing, Scholars' Press.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry eq ual marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 26

University of Mumbai, M.E. (Artificial Intelligence), 2019. 21 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO1014 Information
Retrieval 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand the basics of information retrieval with pertinence to modeling, query operations
and indexing .
2. To get an understanding of machine learning techniques for text classification and clustering.
3. To understand the various applications of information retrieval giving emphasis to multimedia,
and web search.
4. To understand the concepts of digital libraries and image retrieval .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the need and importance of information retrieval.
2. Understand the standard methods for information indexing and retrieval and implement different
information retrieval models.
3. Apply Artificial Intelligence techniques to text classification and clustering for efficient
information retrieval .
4. Design an efficient search engine and analyze the web content structure.
5. Apply image retrieval techniques while developing solutions to real -world problems.
6. Create an information retrieval system using the available tools.
Prerequisites: Database Management Systems
Sr.
No. Module Detailed Content Hours
1 Introduction Basic concepts; Practical issues; Retrieval process;
Architecture; Boolean retrieval; Retrieval evaluation;
Open source retrieval systems; History of web search;
Web characteristics; Impact of the web on information
retrieval; Information retrieval versus web search;
Components of a search engine. 6
2 Retrieval Models Taxonomy and characterization of information retrieval
models: Boolean model, Vector model; Term weighting;
Scoring and ranking; Language models; Set theoretic
models; Probabilistic models; Algebraic models;
Structured text retrieval models; Models for browsing. 8
3 Indexing Static and dynamic inverted indices; Index construction
and index compression; Searching; Sequential searching
and pattern matching; Query operations; Query 10

Page 27

University of Mumbai, M.E. (Artificial Intelligence), 2019. 22 languages; Q uery processing; Relevance feedback and
query expansion; Automatic local and global analysis;
Measuring effectiveness and efficiency.
4 Classification and
Clustering Text classification and Naïve Bayes; Vector space
classification; Support vector machines and Machine
learning on documents; Flat clustering; Hierarchical
clustering; Matrix decompositions and latent semantic
indexing; Fusion and meta learning. 8
5 Searching the Web Searching the web; Structure of the web; IR and web
search; Static an d dynamic Ranking; Web crawling and
indexing; Link analysis; XML retrieval; Multimedia IR:
Models and languages; Indexing and searching; Parallel
and distributed IR; Digital libraries. 8
6 Image Retrieval Introduction to content -based image retrieval;
Challenges in image retrieval; Image representation;
Indexing and retrieving images; Relevance feedback. 8
Text Books:
1. C. Manning, P. Raghavan, H. Schutze, Introduction to Information Retrieval, First South Asian
Edition, Cambridge University Press.
2. R. B. Yates, B. R. Neto, Modern Information Retrieval: The concepts and Technology behind
Search, 2nd edition, ACM Press Books.
Reference Books:
1. S. Büttcher, C. Clarke and G. Cormack, Information Retrieval - Implementing and Evaluating
Search Engines, MIT Press
2. R. Korfhage, Information Storage and Retrieval , Wiley .
3. P. Paliwal, S. Balakrishnan , Principles of Information Retrieval , Anmol Publications Pvt. Ltd .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respe ctive
lecture hours as mentioned in the syllabus.

Page 28

University of Mumbai, M.E. (Artificial Intelligence), 2019. 23 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO1015 Blockchain 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
This course explores the fundamentals of blockchain, the workings and applications of this
technology and its potential impact on Supply Chain, Manufacturing, Real Estate, Customer Loyalty,
Agriculture, Financial Services, Government, Banking, Contracting and Identity Management.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the concept of blockchain and its need .
2. Analyze methods of cryptography for application with blockchain.
3. Evaluate the working of blockchain.
4. Understand the underlying technology of transactions, blocks, proof -of-work, and consensus
building .
5. Identify real world problems that blockchain can solve and analyze a use case.
6. Develop applications on blockchain using platforms such as Ethereum , Hyperl edger or Azure .
Prerequisites: Cryptography.
Sr.
No. Module Detailed Content Hours
1 Basics Identifying the problems with current infrastructure;
Understanding Centralised Practises, Policies & Business;
Businesses with Decentralised Infra structure ; Overview of
blockchain technology ; Advantage over conventional
distributed database; History of blockchain: how and when
blockchain/bitcoin started, milestones on the development of
bitcoin, criticism, ridicule and promise of bitcoin, sharing
economy, inte rnet of value; how economics benefits from
blockchain . 6
2 Cryptography Block Ciphers; Encryptions; Secret Keys; Elliptic Curve
Cryptography; Hash cryptography; Encryption vs hashing;
Digital Signature; Memory Hard Algorithm, Zero
Knowledge Proof. 6
3 Blockchain
Concepts Introduction: Transactions, blocks, hashes, consensus, verify
and confirm blocks, peer to peer networks, blocks of data in
a chain, decentralisation of networks, processes &
workflows, cryptocurrencies, nodes, assets, consensus,
dapps ; types of blockchain ; chain policy ; working of
blockchain ; life of blockchain application ; privacy, 10

Page 29

University of Mumbai, M.E. (Artificial Intelligence), 2019. 24 anonymity and security of blockchain.
4 Blockchain
Implementation Hyperledger: Introduction, where can Hyperledger be used,
Hyperledger architecture, Hyperledger Fabric, features of
Hyperledger ; Open source blockchain platform technology ;
Tools & services ; Cloud options in blockchains AWS ; Azure
workbench ; Hyperledger console; Consensus: Proof of work,
proof of stake, delegated proof of stake, proof of burn,
BlocBox Protocol . 10
5 Smart Contracts History ; Distributed ledger ; Smart contracts ;
Cryptocurrency ; Bitcoin protocols ; Mining strategy and
rewards ; Ethereum – construction ; DAO ; GHOST ;
Vulnerability ; Attacks ; Sidechain; N amecoin . 8
6 Use Cases Trade finance ; Supply chain ; Manufacturing; Security ; Real
Estate, Customer Loyalty, Agriculture, Financial Services,
Government, Banking, Contracting and Identity
Management ; Internet of Things ; Medical record
management system; D omain name service, etc.; future of
blockchain . 8
Text Books:
1. D. Tapscott, A. Tapscott , Blockchain Revolution: How the Technology Behind Bitcoin Is
Changing Money, Business, and the World , Portfolio Publishers.
2. A. Antonopoulos, Mastering Bitcoin: Programming the Open Blockchain, O'Reilly.
3. P. Champagne, The Book of Satoshi: The Collected Writings of Bitcoin Creator Satoshi
Nakamoto, e53 Publishing, LLC.
Reference Books:
1. M. Swan , Blockchain: Blueprint for a New Economy , O’Reilly.
2. R. Wattenhofer, The Science of the Blockchain , Inverted Forest Publishing.
3. R. Modi, Solidity Programming Essentials: A beginner's guide to build smart contracts for
Ethereum and blockchain, Packt Publishing.
4. Narayanan, J. Bonneau, E. Felten, A. Miller, S. Goldfeder, Bitcoin and Cryptocurrency
Technolog ies: A Comprehensive Introduction, Princeton University Press.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 30

University of Mumbai, M.E. (Artificial Intelligence), 2019. 25 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1011 Product Life
Cycle
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To familiarize the students with the need, benefits and components of PLM.
2. To acquaint students with Product Data Management & PLM strategies.
3. To give insights into new product development program and guidelines for designing and
developing a product.
4. To familiarize the students with Virtual Product Development.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Gain knowledge about phases of PLM, PLM strategies and methodology for PLM feasibility
study and PDM implementation.
2. Illustrate various approaches and techniques for designing and developing products.
3. Apply product engineering guidelines / thumb rules in designing products for molding ,
machining, sheet metal working etc.
4. Acquire knowledge in applying virtual product development tools for components, machining
and manufacturing plant .

Sr.
No. Detailed Content Hours
1 Introduction to Product Lifecycle Management (PLM): Product Lifecycle
Management (PLM), Need for PLM, Product Lifecycle Phases, Opportunities of
Globalization, Pre -PLM Environment, PLM Paradigm, Importance & Benefits of
PLM, Widespread Impact of PLM, Focus and Application, A PLM Project,
Starting the PLM Initiative, PLM Applications
PLM Strategies: Industrial strategies, Strategy elements, its identification,
selection and implementation, Developing PLM Vision and PLM Strategy ,
Change management for PLM. 10
2 Product Design: Product Design and Development Process, Engineering Design,
Organization and Decomposition in Product Design, Typologies of Design Process
Models, Reference Model, Product Design in the Context of the Product
Development Process, Relat ion with the Development Process Planning Phase,
Relation with the Post design Planning Phase, Methodological Evolution in
Product Design, Concurrent Engineering, Characteristic Features of Concurrent
Engineering, Concurrent Engineering and Life Cycle Appr oach, New Product
Development (NPD) and Strategies, Product Configuration and Variant
Management, The Design for X System, Objective Properties and Design for X
Tools, Choice of Design for X Tools and their use in the Design Process. 9

Page 31

University of Mumbai, M.E. (Artificial Intelligence), 2019. 26 3 Product Data Mana gement (PDM): Product and Product Data, PDM systems
and importance, Components of PDM, Reason for implementing a PDM. system,
financial justification of PDM, barriers to PDM implementation . 5
4 Virtual Product Development Tools: For components, machines, and
manufacturing plants, 3D CAD systems and realistic rendering techniques, Digital
mock -up, Model building, Model analysis, Modelling and simulations in Product
Design, Examples/Case studies. 5
5 Integration of Environmental Aspects in Product Design: Sustainable
Development, Design for Environment, Need for Life Cycle Environmental
Strategies, Useful Life Extension Strategies, End -of-Life Strategies, Introduction
of Environmental Strategies into the Design Process, Life Cycle Environmental
Strategies a nd Considerations for Product Design 5
6 Life Cycle Assessment and Life Cycle Cost Analysis: Properties, and
Framework of Life Cycle Assessment, Phases of LCA in ISO Standards, Fields of
Application and Limitations of Life Cycle Assessment, Cost Analysis and the Life
Cycle Approach, General Framework for LCCA, Evolution of Models for Product
Life Cycle Cost Analysis 5
Reference s:
1. J. Stark, Product Lifecycle Management: Paradigm for 21st Century Product Realisation,
Springer -Verlag, 2004. ISBN: 1852338105.
2. F. Giudice, G. Rosa, Antonino Risitano, Product Design for the environment - A life cycle
approach, Taylor & Francis 2006, ISBN: 0849327229.
3. S. Antti, I. Anselmie, Product Life Cycle Management, Springer, Dreamtech, ISBN: 3540257314.
4. M. Grieve, Product L ifecycle Management: Driving the next generation of lean thinking, Tata
McGraw Hill, 2006, ISBN: 0070636265 .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has p art (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 32

University of Mumbai, M.E. (Artificial Intelligence), 2019. 27 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1012 Reliability
Engineering 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To familiarize the students with various aspects of probability theory
2. To acquaint the students with reliability and its concepts
3. To introduce the students to methods of estimating the system reliability of simple and complex
systems
4. To understand the various aspects of Maintainability, Availability and FMEA procedure.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand and apply the concept of Probability to engineering problems
2. Apply various reliability concepts to calculate different reliability parameters
3. Estimate the system reliability of simple and complex systems
4. Carry out a Failure Mode Effect and Criticality Analysis .

Sr.
No. Detailed Content Hours
1 Probability theory: Probability: Standard definitions and concepts; Conditional
Probability, Bayes Theorem.
Probability Distributions: Central tendency and Dispersion; Binomial, Normal,
Poisson, Weibull, Exponential, relations between them and their significance.
Measures of Dispersion: Mean, Median, Mode, Range, Mean Deviation,
Standard Deviation, Variance, Skewness and Kurtosis. 8
2 Reliability Concepts: Reliability definitions, Importance of Reliability, Quality
Assurance and Reliability, Bath Tub Curve.
Failure Data Analysis: Hazard rate, failure density, Failure Rate, Mean Time to
Failure (MTTF), MTBF, Reliability Functions.
Reliability Hazard Models: Constant Failure Rate, Linearly increasing, Time
Dependent Failure Rate, Weibull Model. Distribution functions and reliability
analysis. 8
3 System Reliability: System Configurations: Series, parallel, mixed configuration,
k out of n structure, Complex systems. 5
4 Reliability Improvement: Redundancy Techniques: Element redundancy, Unit
redundancy, Standby redundancies. Markov analysis. System Reliability Analysis
– Enumeration method, Cut -set method, Success Path method, Decomposition
method. 8
5 Maintainability and Availability: System downtime, Design for Maintainability:
Maintenance requirements, Design methods: Fault Isolation and self -diagnostics, 5

Page 33

University of Mumbai, M.E. (Artificial Intelligence), 2019. 28 Parts standardization and Interchangeability, Modularization and Acces sibility,
Repair Vs Replacement.
Availability – qualitative aspects.
6 Failure Mode, Effects and Criticality Analysis: Failure mode effects analysis,
severity/criticality analysis, FMECA examples. Fault tree construction, basic
symbols, development of functional reliability block diagram, Fau1t tree analysis
and Event tree Analysis 5
References:
1. L. Srinath, Reliability Engineering, Affiliated East -West Press (P) Ltd., 1985.
2. C. Ebeling, Reliability and Maintainability Engineering, Tata McGraw Hill.
3. B. D hillion, C. Singh, Engineering Reliability, John Wiley & Sons, 1980.
4. P.D.T. Conor, Practical Reliability Engineering , John Wiley & Sons, 1985.
5. K. Kapur, L.R. Lamberson, Reliability in Engineering Design, John Wiley & Sons.
6. M. Spiegel, Probability and Stati stics, Tata McGraw -Hill Publishing Co. Ltd .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 34

University of Mumbai, M.E. (Artificial Intelligence), 2019. 29 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1013 Management
Information
System 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. The course is blend of Management and Technical field.
2. Discuss the roles played by information technology in today’s business and define various
technology architectures on which information systems are built.
3. Define and analyze typical functional information systems and identify how they meet the needs
of the firm to deliver efficiency and competitive advantage.
4. Identify the basic steps in systems development .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Explain how information systems Transform Business .
2. Identify the impact information systems have on an organization .
3. Describe IT infrastructure and its components and its current trends .
4. Understand the principal tools and technologies for accessing information from databases to
improve business performance and decision making .
5. Identify the types of systems used for enterprise -wide knowledge management and how they
provide value for busines ses.
Sr.
No. Detailed Content Hours
1 Introduction to Information Systems (IS): Computer Based Information Systems,
Impact of IT on organizations, Importance of IS to Society. Organizational
Strategy, Competitive Advantages and IS. 4
2 Data and Knowledge Management: Database Approach, Big Data, Data warehouse
and Data Marts, Knowledge Management.
Business intelligence (BI): Managers and Decision Making, BI for Data analysis
and Presenting Results 7
3 Ethical issues and Privacy: Information Secu rity. Threat to IS, and Security
Controls 7
4 Social Computing (SC): Web 2.0 and 3.0, SC in business -shopping, Marketing,
Operational and Analytic CRM, E -business and E -commerce – B2B B2C. Mobile
commerce. 7
5 Computer Networks Wired and Wireless technology, Pervasive computing, Cloud
computing model. 6
6 Information System within Organization: Transaction Processing Systems,
Functional Area Information System, ERP and ERP support of Business Process.
Acquiring Information Systems and Applications : Various System development
life cycle models. 8

Page 35

University of Mumbai, M.E. (Artificial Intelligence), 2019. 30 References:
1. K. Rainer, Brad Prince, Management Information Systems, Wiley
2. K.C. Laudon and J. Laudon, Management Information Systems: Managing the Digital Firm, 10th
Ed., Prentice Hall, 2007.
3. D. Boddy, A. Boonstra, Managing Information Systems: Strategy and Organization, Prentice
Hall, 2008 .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 36

University of Mumbai, M.E. (Artificial Intelligence), 2019. 31 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1014 Design of
Experiments 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand the issues and principles of Design of Experiments (DOE).
2. To list the guidelines for designing experiments.
3. To become familiar with methodologies that can be used in conjunction with experimental
designs for robustness and optimization .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Plan data collection, to turn data into information and to make decisions that lead to appropriate
action.
2. Apply the methods taught to real life situations.
3. Plan, analyze, and interpret the results of experiments .

Sr.
No. Detailed Content Hours
1 Introduction: Strategy of Experimentation, Typical Applications of Experimental
Design, Guidelines for Designing Experiments, Response Surface Methodology. 6
2 Fitting Regression Models: Linear Regression Models, Estimation of the
Parameters in Linear Regression Models, Hypothesis Testing in Multiple
Regression, Confidence Intervals in Multiple Regression, Predicti on of new
response observation, Regression model diagnostics, Testing for lack of fit. 8
3 Two -Level Factorial Designs: The 22Design, The 23 Design, The General 2k
Design, A Single Replicate of the 2kDesign, The Addition of Center Points to the
2kDesign, Blocking in the 2kFactorial Design, Split -Plot Designs. 7
4 Two -Level Fractional Factorial Designs: The One -Half Fraction of the 2k
Design, The One -Quarter Fraction of the 2k Design, The General 2k-p Fractional
Factorial Design, Resolution III D esigns, Resolution IV and V Designs, Fractional
Factorial Split -Plot Designs. 7
5 Conducting Tests: Testing Logistics, Statistical aspects of conducting tests,
Characteristics of good and bad data sets, Example experiments, Attribute Vs
Variable data sets . 7
6 Taguchi Approach: Crossed Array Designs and Signal -to-Noise Ratios, Analysis
Methods, Robust design examples. 4

Page 37

University of Mumbai, M.E. (Artificial Intelligence), 2019. 32 References:
1. R. Mayers, D. Montgomery, Christine M. Anderson -Cook, Response Surface Methodology:
Process and Product Optimization using Designed Experiment, 3rd edition, John Wiley & Sons,
New York, 2001
2. D. Montgomery, Design and Analysis of Experiments, 5th edition, John Wiley & Sons, New
York, 2001
3. G. Box, J. Hunter, W. Hunter, Statics for Experimenters: Design, Innovation and Discover y, 2nd
Ed. Wiley
4. W. Diamond, Practical Experiment Designs for Engineers and Scientists, John Wiley and Sons
Inc. ISBN: 0 -471-39054 -2
5. A. Dean, and D. Voss, Design and Analysis of Experiments (Springer text in Statistics), Springer
6. P. Ross, Taguchi Technique for Quality Engineering, McGraw Hill.
7. M. Phadake, Quality Engineering using Robust Design, Prentice Hall .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllab us.

Page 38

University of Mumbai, M.E. (Artificial Intelligence), 2019. 33 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1015 Operations
Research 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. Formulate a real -world problem as a mathematical programming model.
2. Understand the mathematical tools that are needed to solve optimization problems.
3. Use mathematical software to solve the proposed models .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the theoretical workings of the simplex method, the relationship between a linear
program and its dual, including strong duality and complementary slackness.
2. Perform sensitivity analysis to determine the direction and magnitude of change of a model’s
optimal solution as the data change.
3. Solve specialized linear programming problems like the transportation and assignm ent problems,
solve network models like the shortest path, minimum spanning tree, and maximum flow
problems.
4. Understand the applications of integer programming and a queuing model and compute important
performance measures.

Sr.
No. Detailed Content Hours
1 Introduction to Operations Research : Introduction, Structure of the
Mathematical Model, Limitations of Operations Research.
Linear Programming : Introduction, Linear Programming Problem, Requirements
of LPP, Mathematical Formulation of LPP, Graphical met hod, Simplex Method
Penalty Cost Method or Big M -method, Two Phase Method, Revised simplex
method, Duality , Primal – Dual construction, Symmetric and Asymmetric Dual,
Weak Duality Theorem, Complimentary Slackness Theorem, Main Duality
Theorem, Dual Simplex Method, Sensitivity Analysis.
Transportation Problem : Formulation, solution, unbalanced Transportation
problem. Finding basic feasible solutions – Northwest corner rule, least cost
method and Vogel’s approximation method. Optimality test: the stepping stone
method and MODI method.
Assignment Problem : Introduction, Mathematical Formulation of the Problem,
Hungarian Method Algorithm, Processing of n Jobs Through Two Machines and
m Machines, Graphical Method of Two Jobs m Machines Problem Routing
Problem, Travelling Salesman Problem.
Integer Programming Problem : Introduction, Types of Integer Programming
Problems, Gomory’s cutting plane Algorithm, Branch and Bound Technique . 14

Page 39

University of Mumbai, M.E. (Artificial Intelligence), 2019. 34 Introduction to Decomposition algorithms.
2 Queuing models : queuing systems and structures, single server and multi -server
models, Poisson input, exponential service, constant rate service, finite and infinite
population 5
3 Simulation : Introduction, Methodology of Simulation, Basic Concepts,
Simulation Procedure, Application of Simulation Monte -Carlo Method:
Introduction, Monte -Carlo Simulation, Applications of Simulation, Advantages of
Simulation, Limitations of Simulation 5
4 Dynamic programming . Characteristics of dynamic programming. Dynamic
programming approach for Priority Management employment smoothening,
capital budgeting, Stage Coach/Shortest Path, cargo loading and Reliability
problems. 5
5 Game Theory . Competitive games, rectangular game, saddle point, minimax
(maximin) method of optimal strategies, value of the game. Solution of games
with saddle points, dominance principle. Rectangular games without saddle point –
mixed strategy for 2 X 2 games. 5
6 Inventory Models : Classical EOQ Models, EOQ Model with Price Breaks, EOQ
with Shortage, Probabilistic EOQ Model. 5
References:
1. H. Taha, Operations Research - An Introduction, Prentice Hall, 7th Edition , 2002.
2. A. Ravindran , D. Phillips a nd J. Solberg , Operations Research: Principles and Practice, John
Willey and Sons, 2nd Edition, 2009.
3. F. Hiller and G. Liebermann, Introduction to Operations Research, Tata McGraw Hill, 2002.
4. S. Sharma, Operations Research, Kedar Nath.
5. K. Swarup, P. Gupta and M. Mohan, Operations Research, Sultan Chand & Sons .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry eq ual marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proport ional to the number of respective
lecture hours as mentioned in the syllabus.

Page 40

University of Mumbai, M.E. (Artificial Intelligence), 2019. 35 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1016 Cyber
Security and
Laws 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand and identify different types cybercrime and cyber law .
2. To recognized Indian IT Act 2008 and its latest amendments .
3. To learn various types of security standards compliances .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the concept of cybercrime and its effect on outside world
2. Interpret and apply IT law in various legal issues
3. Distinguish different aspects of cyber law
4. Apply Information Security Standards compliance during software design and development.

Sr.
No. Detailed Content Hours
1 Introduction to Cybercrime: Cybercrime definition and origins of the world,
Cybercrime and information security, Classifications of cybercrime, Cybercrime
and the Indian ITA 2000, A global Perspective on cybercrimes. 4
2 Cyber offenses & Cybercrime: How criminal plan the attacks, Social
Engine ering, Cyber stalking, Cyber café and Cybercrimes, Botnets, Attack vector,
Cloud computing, Proliferation of Mobile and Wireless Devices, Trends in
Mobility, Credit Card Frauds in Mobile and Wireless Computing Era, Security
Challenges Posed by Mobile Devic es, Registry Settings for Mobile Devices,
Authentication Service Security, Attacks on Mobile/Cell Phones, Mobile Devices:
Security Implications for Organizations, Organizational Measures for Handling
Mobile, Devices -Related Security Issues, Organizational Security Policies and
Measures in Mobile Computing Era, Laptops. 9
3 Tools and Methods Used in Cyberline: Phishing, Password Cracking, Key
loggers and Spywares, Virus and Worms, Steganography, DoS and DDoS Attacks,
SQL Injection, Buffer Over Flow, Attacks on Wireless Networks, Phishing,
Identity Theft (ID Theft). 6
4 The Concept of Cyberspace: E-Commerce , The Contract Aspects in Cyber Law
,The Security Aspect of Cyber Law ,The Intellectual Property Aspect in Cyber
Law, The Evidence Aspect in Cyber Law, T he Criminal Aspect in Cyber Law,
Global Trends in Cyber Law , Legal Framework for Electronic Data Interchange
Law Relating to Electronic Banking , The Need for an Indian Cyber Law. 8
5 Indian IT Act: Cyber Crime and Criminal Justice: Penalties, Adjudication and 6

Page 41

University of Mumbai, M.E. (Artificial Intelligence), 2019. 36 Appeals Under the IT Act, 2000, IT Act. 2008 and its Amendments.
6 Information Security Standard compliances: SOX, GLBA, HIPAA, ISO,
FISMA, NERC, PCI. 6
References:
1. N. Godbole, S. Belapure , Cyber Security , Wiley India, New Delhi.
2. S. Vishwanathan, The Indian Cyber Law; Bharat Law House New Delhi.
3. The Information Technology Act, 2000; Bare Act - Professional Book Publishers, New Delhi.
4. P. Mali, Cyber Law & Cyber Crimes; Snow White Publications , Mumbai.
5. K. Knapp, Cyber Security & Global Information Assurance, Information Science Publishing.
6. W. Stallings , Cryptography and Network Security, Pearson Publication
7. Websites for more information: The Information Technology ACT, 2008 - TIFR:
https://www.tifrh.res.in
8. Website for more information : A Compliance Primer for IT professional:
https://www.sans.org/reading -room/whitepapers/compliance/compliance -primer -professionals -
33538
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All question s carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 42

University of Mumbai, M.E. (Artificial Intelligence), 2019. 37 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1017 Disaster
Management
and
Mitigation
Measures 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand physics and various types of disaster occurring around the world.
2. To identify extent and damaging capacity of a disaster.
3. To study and understand the means of losses and methods to overcome /minimize it.
4. To understand role of individual and various organization during and after disaster.
5. To understand a pplication of GIS in the field of disaster management.
6. To understand the emergency government response structures before, during and after disaster .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Get to know natural as well as manmade disaster and their extent and possible effects on the
economy.
2. Plan of national importance structures based upon the previous history.
3. Get acquainted with government policies, acts and various organizational structu re associated
with an emergency.
4. Get to know the simple do’s and don’ts in such extreme events and act accordingly .

Sr.
No. Detailed Content Hours
1 Introduction:
Definition of Disaster, hazard, global and Indian scenario, general perspective,
importance of study in human life, Direct and indirect effects of disasters, long
term effects of disasters. Introduction to global warming and climate change. 3
2 Natural D isaster and Manmade disasters:
3.1 Natural Disaster: Meaning and nature of natural disaster, Flood, Flash flood,
drought, cloud burst, Earthquake, Landslides, Avalanches, Volcanic eruptions,
Mudflow, Cyclone, Storm, Storm Surge, climate change, global warming, sea
level rise, ozone depletion
3.2 Manmade Disasters: Chemical, Industrial, Nuclear and Fire Hazards. Role of
growing population and subsequent industrialization, urbanization and
changing lifestyle of human beings in frequent occurrences of manmade
disasters. 9
3 Disaster Management, Pol icy and Administration :
3.1 Disaster management: meaning, concept, importance, objective of disaster
management policy, disaster risks in India, Paradigm shift in disaster
management. 6

Page 43

University of Mumbai, M.E. (Artificial Intelligence), 2019. 38 3.2 Policy and administration: Importance and principles of disaster management
policies, command and co -ordination of in disaster management, rescue
operations -how to start with and how to proceed in due course of time, study of
flowchart showing the entire process.
4 Institutional Framework for Disaster Management in I ndia:
4.1 Importance of public awareness, Preparation and execution of emergency
management programme. Scope and responsibilities of National Institute of
Disaster Management (NIDM) and National disaster management authority
(NDMA) in India. Methods and m easures to avoid disasters, Management of
casualties, set up of emergency facilities, importance of effective
communication amongst different agencies in such situations.
4.2 Use of Internet and software for effective disaster management. Applications
of GIS, Remote sensing and GPS in this regard. 6
5 Financing Relief Measures:
5.1 Ways to raise finance for relief expenditure, role of government agencies and
NGO’s in this process, Legal aspects related to finance raising as well as
overall management of disasters. Various NGO’s and the works they have
carried out in the past on the occurrence of various disasters, Ways to approach
these teams.
5.2 International relief aid agencies and their role in extreme events. 9
6 Preventive and Mitigation Measures:
6.1 Pre -disaster, during disaster and post -disaster measures in some events in
general
6.2 Structural mapping: Risk mapping, assessment and analysis, sea walls and
embankments, Bio shield, shelters, early warning and communication
6.3 Non Structural Mitig ation: Community based disaster preparedness, risk
transfer and risk financing, capacity development and training, awareness and
education, contingency plans.
6.4 Do’s and don’ts in case of disasters and effective implementation of relief aids. 6
References:
1. H. Gupta Disaster Management, Universities Press Publications.
2. O. Dagur, Disaster Management: An Appraisal of Institutional Mechanisms in India, Centre for
land warfare studies, New Delhi, 2011.
3. D. Copolla, B. Heinemann, Introduction to Interna tional Disaster Management, Elsevier
Publications.
4. J. Pinkowski, Disaster Management Handbook, CRC Press, Taylor and Francis group.
5. R. Dasgupta, Disaster management & rehabilitation, Mittal Publications, New Delhi.
6. R. Singh, Natural Hazards and Disaster Ma nagement, Vulnerability and Mitigation, Rawat
Publications.
7. C. Albert, K. Yonng, Concepts and Techniques of GIS, Prentice Hall (India) Publications.
(Learners are expected to refer reports published at national and International level and updated
informati on available on authentic web sites)
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.

Page 44

University of Mumbai, M.E. (Artificial Intelligence), 2019. 39 Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 45

University of Mumbai, M.E. (Artificial Intelligence), 2019. 40 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO1018 Energy
Audit and
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand the importance energy security for sustainable development and the fundamentals
of energy conservation.
2. To introduce performance evaluation criteria of various electrical and thermal installations to
facilitate the energy management
3. To relate the data collected during performance evaluation of systems for identification of energy
saving opportunities .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. To identify and describe present state of energy security and its importance.
2. To identify and describe the basic principles and methodologies adopted in energy audit of a
utilit y.
3. To describe the energy performance evaluation of some common electrical installations and
identify the energy saving opportunities.
4. To describe the energy performance evaluation of some common thermal installations and
identify the energy saving opport unities
5. To analyze the data collected during performance evaluation and recommend energy saving
measures .

Sr.
No. Detailed Content Hours
1 Energy Scenario:
Present Energy Scenario, Energy Pricing, Energy Sector Reforms, Energy
Security, Energy Conservation and its Importance, Energy Conservation Act -2001
and its Features. Basics of Energy and its various forms, Material and Energy
balance. 4
2 Energy Audit Principles:
Definition, Energy audit - need, Types of energy audit, Energy management (au dit)
approach -understanding energy costs, Bench marking, Energy performance,
Matching energy use to requirement, Maximizing system efficiencies, Optimizing
the input energy requirements, Fuel and energy substitution. Elements of
monitoring& targeting; Ener gy audit Instruments; Data and information -analysis.
Financial analysis techniques: Simple payback period, NPV, Return on investment
(ROI), Internal rate of return (IRR). 8

Page 46

University of Mumbai, M.E. (Artificial Intelligence), 2019. 41 3 Energy Management and Energy Conservation in Electrical System:
Electricity billing, Electrical load management and maximum demand Control;
Power factor improvement, Energy efficient equipment and appliances, star
ratings.
Energy efficiency measures in lighting system, Lighting control: Occupancy
sensors, daylight integration, a nd use of intelligent controllers.
Energy conservation opportunities in: water pumps, industrial drives, induction
motors, motor retrofitting, soft starters, variable speed drives. 10
4 Energy Management and Energy Conservation in Thermal Systems:
Review of different thermal loads; Energy conservation opportunities in: Steam
distribution system, Assessment of steam distribution losses, Steam leakages,
Steam trapping, Condensate and flash steam recovery system.
General fuel economy measures in Boile rs and furnaces, Waste heat recovery, use
of insulation - types and application. HVAC system: Coefficient of performance,
Capacity, factors affecting Refrigeration and Air Conditioning system performance
and savings opportunities. 10
5 Energy Performance Assessment:
On site Performance evaluation techniques, Case studies based on: Motors and
variable speed drive, pumps, HVAC system calculations; Lighting System:
Installed Load Efficacy Ratio (ILER) method, Financial Analysis. 4
6 Energy conservation in Buildings:
Energy Conservation Building Codes (ECBC): Green Building, LEED rating,
Application of Non -Conventional and Renewable Energy Sources 3
References:
1. G. Stokes, Handbook of Electrical Installation Practice, Blackwell Science .
2. A. Valia, Designing with light: Lighting Handbook, Lighting System.
3. W. Turner, Energy Management Handbook, John Wiley and Sons .
4. A. K. Tyagi, Handbook on Energy Audits and Management , Tata Energy Research Institute
(TERI).
5. C. Smith, E nergy Management Princ iples, Pergamon Press .
6. D. Patrick, S. Ray and E. Richardson, Energy Conservation Guidebook, Fairmont Press
7. A. Thumann, W. Younger, T. Niehus, Handbook of Energy Audits, CRC Press.
8. Website: www.energymanagertraining.com ; www.bee -india.nic.in .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 47

University of Mumbai, M.E. (Artificial Intelligence), 2019. 42 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIL101 AI
Programming
Lab - 02 - - 01 - 01
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
- - - - - 25 25 50
Practical sessions based on the course s MEAIC101 and MEAIC102 will be conducted in this
laboratory. Implementation of AI and Soft Computing techniques to understand, analyse, compare
and visualize the performance of the induced models will be done using Python with Pytorch ,
Numpy, NL TK, Scikit -learn, etc. packages and MATLAB.
Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIL10 2 Data Science
Lab - 02 - - 01 - 01
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
- - - - - 25 25 50
Practical sessions based on the course s MEAIC102 and MEAIC103 will be conducted in this
laboratory. Implementation of Exploratory data analysis, Statistical techniques, Evaluation methods,
Machine Learning and Data Science techniques will be done using R, MATLAB , Python , Weka .
End Semester Examination:
Practical/Oral examination for both laboratories is to be conducted by a pair of internal and external
examiners appointed by the University of Mumbai.

Page 48

University of Mumbai, M.E. (Artificial Intelligence), 2019. 43 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC201 Deep and
Reinforcement
Learning 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
To understand the foundations of deep learning, reinforcement learning, and deep reinforcement
learning including the ability to successfully implement, apply and test relevant learning algorithms
in TensorFlow.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the basics of deep learning and reinforcement learning paradigms.
2. Understand the importance of neural networks for deep learning.
3. Apply optimization and regularization techniques to t rain deep neural networks.
4. Construct and train convolutional, recurrent and recursive neural networks.
5. Implement and apply reinforcement learning algorithms.
6. Analyze real-world problems for solutions using deep and reinforcement learning .
Prerequisites: Fundamentals of Neural Networks and Mathematics.
Sr.
No. Module Detailed Content Hours
1 Foundations of Deep
learning Introduction to Neural Networks; Shallow Neural
Networks; Deep Neural Networks; Recurrent
Neural Networks; Reinforcement Learning;
Successful application examples ; Fundamental
principles and techniques to Deep Learning and
Reinforcement Learning . 6
2 Neural Networks in
Deep learning Deep Feedforward Networks: Example of Learning
XOR, Gradient -Based Learning, Hidden Units,
Architecture Design, Back -Propagation and Other
Differentiation Algorithms; Regularization
techniques for deep learning; Optimization for
Training Deep Models . 8
3 Convolutional neural
networks, Recurrent
and recursive neural
networks Convolutional neural networks (CNN) :
Fundamentals, Properties of CNN representations,
Need , Architecture , Building CNN; Sequence
Modelling : Recurrent and Recursive Nets ,
Unfolding Computational Graphs, Deep Recurrent
Networks, Recurrent Neural Networks ,
Bidirectional RNNs , Encod er-Decoder Sequence -10

Page 49

University of Mumbai, M.E. (Artificial Intelligence), 2019. 44 to-Sequence Architectures , Recursive Neural
Networks , Echo State Networks .
4 Reinforcement
Learning Fundamentals of Reinforcement L earning; Agent
environment framework; Successes of
reinforcement learning; Bandit problems and online
learning; Markov decision processes ; Returns and
value functions 8
5 Algorithms for
Reinforcement
Learning Dynamic programming algorithms for
reinforcement learning ; Monte Carlo methods for
reinfo rcement learning; Temporal -Difference Learning 8

6 Deep Reinforcement
Learning and Case
Studies Fundamentals and applications of Deep
Reinforcement Learning; Case studies of deep
learning applications; Case studies of reinforcement
learning applications; Active research topics in deep
and reinforcement learning 8
Text Books:
1. I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press.
2. R. Sutton and A. Barto Reinforcement Learning: An Introduction, MIT Press.
Reference Books:
1. S. Ravichandiran, Hands -on Reinforcement Learning with Python, Packt Publishing.
2. N. Buduma, N. Locascio , Fundamentals of Deep Learning: Designing Next -Generation Machine
Intelligence Alg orithms , O'Reilly .
3. G. Ciaburro, Keras Reinforcement Learning Projects, Packt Publishing.
4. C. Aggarwal, Neural Networks and Deep Learning: A Textbook, Springer.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number o f respective
lecture hours as mentioned in the syllabus.

Page 50

University of Mumbai, M.E. (Artificial Intelligence), 2019. 45 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC202 Big Data Analytics 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To implement methods for big data analytics.
2. To introduce the tools required to manage and analyze big data like Hadoop, NoSql, MapReduce,
etc.
3. To teach the fundamental techniques and principles in achieving big data analytics with
scalability and streaming capability.
4. To enable students to have skills that will help them to solve complex real -world problems in for
decision support.
5. To understand the issues in privacy -preservation and handling data streams.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Analyze the key issues in data science and its associated applications in intelligent business and
scientific computing.
2. Understand and apply the methods of big data analytics.
3. Investigate perspectives of big data analytics in various applications like recommender systems,
social media applications, etc.
4. Implement big data analytics using Hadoop, Map Reduce, NOSQL , etc.
5. Understand the fundamentals of privacy -preservation in data analytics.
6. Implement the concepts of data stream mining using MOA.
Prerequisites: Datab ase Management Systems, Fundamentals of Data Mining.
Sr.
No. Module Detailed Content Hours
1 Introduction Business Intelligence vs Data Science vs Big Data
Analytics ; Data warehouse; Data mining: Introduction,
Knowledge discovery from data, Data pre-processing,
Classification, Clustering, Prediction, Association,
Recent applications of data mining methods; Decision
support system (DSS) and its components; Business
intelligence. 6
2 Big Data Analytics Introduction; Distributed file system; Big dat a and its
importance; Four Vs; Drivers for Big data; Hadoop; Big
data analytics; Big data applications like recommender
systems, social media applications, etc. ; Recent research
in big data analytics. 8
3 Hadoop for Data Apache Hadoop & Hadoop e cosystem; Hadoop 10

Page 51

University of Mumbai, M.E. (Artificial Intelligence), 2019. 46 Analytics distributed file system (HDFS); Architecture of HDFS;
Architectural assumptions and goals; Moving data in
and out of Hadoop .
4 Big Data Processing Use of MapReduce; Architecture of the MapReduce
framework; Phases of a MapReduce job; MapReduce
design patterns; YARN architecture; Algorithms using
map reduce; Exploration of Pig, Hive and Oozie ,
NOSQL. 8
5 Privacy and Data
Science Significance of Privac y and Ethics in Application of
Data Science ; Reidentification of Anonymous People
with Big Data , Privacy -preserving data mining
algorithms, Data Partitioning and Privacy; Recent
research in privacy -preserving data mining . 8
6 Data Streams Static data, incremental data and data streams ; Storage
and Processing of Data Streams ; Algorithms for Data
Stream Mining: Hoeffding tree, Windowing, MOA for
data stream mining; Recent research in data stream
mining . 8
Text Books:
1. A. Maheshwari, Big Data, McGraw Hill.
2. T. White, Hadoop: The Definitive Guide, 3rd edition, O’reily Media.
Reference Books:
1. A. Bifet, R. Gavaldà, G. Holmes, B. Pfahringer, F. Bach, Machine Learning for Data Streams –
with Practical Examples in MOA, MIT Press.
2. S. Acharya and S. Chellappan, Big Data Analytics, Wiley .
3. C. Aggarwal and P. Yu, Privacy -Preserving Data Mining - Models and Algorithms, Springer.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 52

University of Mumbai, M.E. (Artificial Intelligence), 2019. 47 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIC203 Bio-inspired
Artificial
Intelligence 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
To course will provide a motivation to learn bio -inspired algorithms and will impart knowledge of
various bio -inspired AI algorithms .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the principles of bio -inspired algorithms .
2. Apply evolutionary algorithms to optimize solutions for real -world problems.
3. Develop o ptimiz ed solutions using algorithms like ACO.
4. Understand the applications of immune systems and apply it in suitable situations.
5. Apply swarm intelligence to develop solutions for real -world problems.
6. Investigate about cutting edge research that uses bio -inspired a lgorithms.

Prerequisites: Fundamentals of Artificial Intelligence

Sr.
No. Module Detailed Content Hours
1 Introduction From nature to nature -inspired computing; Bio -inspired
computing; Multi -objective optimization; Artificial life;
Constraint handling; Artificial neural networks. 6
2 Evolutionary
Computing Foundation of evolutionary theory; Evolutionary strategies;
Evolutionary algorithms: Genetic algorithm and Genetic
programming; Representations; Initial population; Fitness
function; Selectio n and reproduction; Genetic operators
(Selection, Crossover, Mutation); Elitism; Parallel
implementations; Adaptive genetic algorithm. 8
3 Collective
Systems Ant colony optimization: Ant foraging behaviour;
Theoretical considerations; Convergence proofs; ACO
algorithm; ACO and model -based search; Variations of
ACO; Artificial bee colony (ABC) Optimization: Behaviour
of real bees, ABC algorithm, Variations of ABC. 10
4 Immune Systems Introduction; Artificial immune systems: Biological
motivation, Design principles; Main types of algorithms:
Bone marrow, Negative selection, Clonal selection;
Continuous immune network models; Discrete immune
network models; Scope of artificial immune systems. 8
5 Swarm Particle swarm optim ization: Principles of bird flocking and 8

Page 53

University of Mumbai, M.E. (Artificial Intelligence), 2019. 48 Intelligence and
Other Algorithms fish schooling; Evolution of PSO; Operating principles, PSO
algorithm, Neighbourhood topologies, Convergence criteria,
Variations of PSO; Overview of other bio -inspired
algorithms: Harmony Search, Honey -Bee Optimiza tion,
Memetic Algorithms, Co -evolution .
6 Case Studies Case Studies and recent research in bio -inspired artificial
intelligence. 8
Text Books:
1. D. Floreano and C . Mattiussi , Bio-inspired Artificial Intelligence, MIT Press.
2. S. Olariu and A. Zomaya, Handbook of Bioinspired Algorithms and Applications, Chapman and
Hall/CRC.
Reference Books:
1. K. Deb, Multi -Objective Optimization using Evolutionary Algorithms, Wiley.
2. D. Marco, S. Thomas , Ant Colony Optimization , Prentice Hall India Learning Pvt. Ltd .
3. R. Chiong, Nature -Inspired Algorithms for Optimization, Springer.
4. N. Arana -Daniel, C. Lopez -Franco A. Alanis, Bio -inspired Algorithms for Engineering, Elsevier.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number o f respective
lecture hours as mentioned in the syllabus.

Page 54

University of Mumbai, M.E. (Artificial Intelligence), 2019. 49 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO2021 Artificial
Intelligence in
Bioinformatics 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
This course introduces the concepts and state -of-the-art research in bioinformatics, data mining and
AI especially for medical application.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the concepts of molecular biology, DNA analysis with respect to data processing.
2. Analyze biological sequences and score matrices with respect to data processing.
3. Implement data mining algorithms on microarray, gene expression, feature selection for
proteomic and genomic data.
4. Understand ethics in using bioinformatics.
5. Apply AI in medic al field for development of contributive solutions.
6. Investigate state-of-the-art research and developments in bioinformatics.

Prerequisites: Fundamentals of Artificial Intelligence

Sr.
No. Module Detailed Content Hours
1 Introduction Introduction to Bioinformatics and Data Mining;
Molecular Biology background: Analysing DNA;
Bioinformatics perspective of how individuals of a
species differ and how different species differ;
Bioinformatics challenges and opportunities. 6
2 Biological Sequence
Analysis DNA sequence analysis; DNA databases; Protein
structure and function; Protein sequence databases;
Sequence alignment; Sequence comparison, Sequence
similarity search; Longest common subsequence
problem; Scoring matrices for similarity search PAM,
BLOSUM, e tc. 8
3 Mining Biological
Data Protein structural classification; Protein structural
prediction; Modeling text retrieval in biomedicine;
Mining from microarray and gene expressions; Feature
selection for proteomic and genomic data mining. 10
4 Ethics in
Bioinformatics Ethical and social challenges of electronic health
information; Public access to anatomic images; Evidence -
based medicine; Outcome measures and practice
guidelines for using data mining in medicine; Computer
assisted medical and patient education. 8

Page 55

University of Mumbai, M.E. (Artificial Intelligence), 2019. 50 5 AI in Medical
Informatics Infectious disease informatics and outbreak detection;
Identification of biological Relationships from text
documents; Medical expert systems; Telemedicine and
tele surgery ; Internet grateful med (IGM). 8
6 Case S tudies Case Studies and recent research in application of
artificial intelligence in bioinformatics. 8
Text Books:
1. S. Rastogi, N. Mendiratta and P. Rastogi, Bioinformatics: Methods and Applications: Genomics,
Proteomics and Drug Discovery, PHI.
2. Z. Ghosh, B. Mallick, Bioinformatics: Principles and Applications, Oxford University Press.
Reference Books:
1. J. Chen and S. Lonardi, Biological Data Mining, Chapman and Hall/CRC.
2. V. Buffalo , Bioinformatics Data Skills , O′Reilly Publishing .
3. H. Zengyou, Data Mining for Bioinformatics Applications, Woodhead Publishing.
4. L. Low, Bioinformatics: A Practical Handbook of Next Generation Sequencing and its
Applications, World Scientific Publishing.
5. M. Model, Bioinformatics Programming Using Python, O′Reilly Publishing.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 56

University of Mumbai, M.E. (Artificial Intelligence), 2019. 51 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO2022 IoT Data
Analytics 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand the significance of the Internet of Things Data Analytics.
2. To discuss the architecture, operation, and business benefits of an IoT solution.
3. To explore the relationship between IoT, cloud computing, and big data.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the fundamentals of IoT and IoT Data Analytics.
2. Apply the design protocols of IoT in addition to protecting the privacy and trust of a network.
3. Analyze and evaluate the use of IoT Ana lytics in several dominating application areas.
4. Create solutions for Smart Homes, Smart Environmental Care and Smart Travelling using
IoT Data Analytics.
5. Develop solutions for Smart Agriculture using IoT Data Analytics.
6. Design solutions for Smart Healthcar e using IoT Data Analytics.

Prerequisites: Fundamentals of Internet of Things and Data Analytics.

Sr.
No. Module Detailed Content Hours
1 Data Science and IoT Fundamentals of data analytics, Android programming,
Web programming, Internet of Things (IoT);
Characteristics of IoT, IoT vision, Application areas of
IoT; IoT Technology: Architectural overview, Components
of IoT, Devices and Gateways, Local and wide area
networking, IoT data collection, storage, processing and
analytics, data management in IoT, IoT analytics ; AI and
IoT ecosystem; Cloud -based IoT analytics; IoT and big
data; Challenges in IoT data analytics applications. 10
2 Design Principles of
IoT Design principles for connected devices; IoT system layers
and design standardization; net working technology in IoT;
protocols in IoT; security, privacy and Trust in IoT. 6
3 IoT Data Analytics in
Smart Homes Introduction; IoT Data Analytics techniques for: Security
and Surveillance , Energy Conservation; Recent research in
IoT data analytics for smart homes. 6
4 IoT Data Analytics in
Smart Agriculture Introduction; IoT Data Analytics techniques for: Weather
prediction , Demand pricing , Disease prediction , Crop yield
prediction; Recent research in IoT data analytics for smart
travelling. 8

Page 57

University of Mumbai, M.E. (Artificial Intelligence), 2019. 52 5 IoT Data Analytics in
Smart Healthcare Introduction; IoT Data Analytics techniques for: Remote
health monitoring , Remote medical assistance , Data
assortment, transfer and analysis , Tracking and alerts;
Recent research in IoT data analytics for smart healthcare. 8
6 IoT Data Analytics in
Smart Environmental
Care and Smart
Travelling Introduction and need of environmental care , IoT Data
Analytics techniques for: Fire detection , Air pollution
prediction , Earthquake early detection ; Recent research in
IoT data analytics for smart environmental care.
Introduction and need of smart travelling : IoT Data
Analytics techniques for: Self-driving cars , Travel route
optimization , Smart traffic management ; Recent research in
IoT data analytics for smart travelling . 10
Text Books:
1. H. David , S. Gonzalo , G. Patrick, B . Rob, H . Jerome, IoT Fundamentals: Networking
Technologies, Protocols and Use Cases for the Internet of Things , Pearson.
2. A. Minteer, Analytics for the Internet of Things (IoT) - Intelligent analytics for your intelligent
devices, Packt Publishing Ltd.
Reference Books:
1. N. Wilkins, Internet of Things: What You Need to Know about Iot, Big Data, Predictive
Analytics, Artificial Intelligence, Machine Learning, Cybersecurity, Business Intelligence,
Augmented Reality and our Future, IP.
2. J. Soldatos, Building Blocks for IoT Analytics, River Publishers.
3. H. Geng, Internet of Things and Data Analytics Handbook, Wiley.
Interna l Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be so lved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 58

University of Mumbai, M.E. (Artificial Intelligence), 2019. 53 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO2023 Speech
Recognition 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To introduce speech production and related parameters of speech.
2. To show the computation and use of techniques such as short time Fourier transform, linear
predictive coefficients and other coefficients in the analysis of speech.
3. To understand different speech modeling proced ures such as Markov and their implementation
issues.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the basic concepts of speech and fundamental signal processing approaches to speech
spectral analysis.
2. Analyze va rious features of speech and understand the techniques of extracting the features and
pattern comparison techniques.
3. Apply statistical modeling techniques.
4. Understand the architecture and various models of continuous speech recognition system.
5. Apply method s of text to speech synthesis for different applications.
6. Investigate recent developments in speech recognition.

Prerequisites: Fundamentals of Artificial Intelligence and Signal Processing.

Sr.
No. Module Detailed Content Hours
1 Basic Concepts Speech Fundamentals: Articulatory Phonetics –
Production and Classification of Sp eech Sounds;
Acoustic Phonetics, Acoustics of speech production;
Review of Digital Signal Processing concepts; Short -
Time Fourier Transform, Filter -Bank and LPC Methods. 10
2 Speech Analysis Features ; Feature Extraction and Pattern Comparison
Techniques ; Speech distortion measur es– mathematical
and perceptual, Log, Spectral Distance, Cepstral
Distances, Weighted Cepstral Distances and Filtering ;
Likelihood Distortions ; Spectral Distortion using a
Warped Frequency Scale, LPC, PLP and MFCC
Coefficients ; Time Alignment and Normalization;
Dyna mic Time Warping, Multiple Time, Alignment
Paths. 6
3 Speech Modelling Hidden Markov Models: Markov Processes, HMMs,
Evaluation, Opt imal State Seq uence, Viterbi Search, 6

Page 59

University of Mumbai, M.E. (Artificial Intelligence), 2019. 54 Baum -Welch Parameter Re -estimation ; Implementation
issues.
4 Speech Recognition Large Vocabulary Continuous Speech Recognition:
Architecture of a large vocabulary conti nuous speech
recognition system, acoustics and language mode ls, n-
grams, context dependent sub -word units; Applications
and present status. 8
5 Speech Synthesis Text-to-Speech Synthesis: Concatenative and waveform
synthesis methods, sub -word units for TTS, intelligibility
and naturalnes s; role of prosody ; applications and curre nt
status. 8
6 Case Studies Case Studies and recent research in speech processing 10
Text Books:
1. L. Rabiner and B. Juang, Fundamentals of Speech Recognition, Pearson Education.
2. D. Jurafsky and J. Martin, Speech and Language Processing – An Introduction to Natural
Language Processing, Computational Linguistics, and Speech Recognition, Pearson Education.
Reference Books:
1. S. Smith, The Scientist and Engineer’s Guide to Digital Signal Processin g, California Technical
Publishing.
2. T. Quatieri, Discrete -Time Speech Signal Processing – Principles and Practice, Pearson
Education.
3. C. Becchetti and L. Ricotti, Speech Recognition, John Wiley and Sons.
4. B. Gold and N. Morgan, Speech and Audio Signal Processing, Processing and Perception of
Speech and Music, Wiley - India Edition.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 60

University of Mumbai, M.E. (Artificial Intelligence), 2019. 55 Course Code Course Nam e Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO202 4 Autonomous
Robotics 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
To introduce the concepts of autonomous robotics and familiarize learners with methods of
modelling /analysis/control that have been proven efficient through research.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the fundamentals of robotics .
2. Understand and apply spatial descriptions, transformations and kinematics .
3. Construct trajectory and check collision .
4. Analyze and p lan motion and path of motion.
5. Apply manipulation algorithms.
6. Develop applications using sensors and actuators.

Prerequisites: Fundamentals of Mathematics and Physics.

Sr.
No. Module Detailed Content Hours
1 Introduction to Robots Mobile robots ; Robotic arms (manipulators) ; Mobile
manipulators ; Humanoid robots, drones, UGV, AGV, etc. ;
Basic terminologies to characterize robot: Degrees of
Freedom, Joint Space, Cartesian Space, Cartesian -Time
space . 4
2 Spatial Descriptions,
Transformations,
Kinematics and
Inverse Kinematics Positions, orientations, frames, Transformation between
frames, Transformation arithmetic ; Link description of
robot arm, Link connection description, convention for
affixing frames to links ; Using DH parameters to compute
forward kinematics ; Using arithme tic or geometric
approach for inverse kinematics ; Tool Frame ; Using toolkit
like python KDL Orocos to find forward kinematics and
inverse kinematics . 8
3 Trajectory Generation
and Collision
Checking Joint space schemes, Cartesian space schemes,
Singularities, Repeatability, Accuracy ; Overview of
Industrial robots like ABB or FANUC programming
language ; Collision checking using AABB, OBB, mesh -
mesh intersection, Separation axis theorem ; Collision
checking in unknown environments using occupancy gr id, 10

Page 61

University of Mumbai, M.E. (Artificial Intelligence), 2019. 56 OCT -tree, etc.
4 Path Planning and
Motion Planning
Algorithms Standard planning algorithms like visibility graph, C -
Obstacles, PRM, etc. used for static environments ; For
dynamic environments, RRT and some of its variants,
Real-time Adaptive Motion Planning (RAMP), etc. ;
Information spaces and information mappings, sensing
uncertainty, POMDPs, Kalman filtering, particle filtering . 10
5 Manipulation
Algorithms Grasping: Analytical and Data Driven Models ; Data
Drive n Models Configuration Spaces, etc. 6
6 Sensors and Actuators Discrete and continuous sensors, reading from point cloud
data using stereo -vision sensor or laser range finder, using
sensor data for further collision checking ; Obstacle
detection using any computer vision algorithm,
Understanding different type of actuators (joints), such as,
DC Motors, Stepper motors, Servo motors, linear
actuators, spherical joints, etc. 10
Text Books:
1. J. Craig , Introduction to Robotics: Mech anics and Control , Pearson .
2. S. LaValle, Planning Algorithms, Packt Publishing.
Reference Books:
1. G. Blokdyk , Robotics and Autonomous Vehicles , 3rd Edition, 5starcooks .
2. F. Lewis, S. Ge, Autonomous Mobile Robots: Sensing, Control, Decision Making and
Applications, CRC Press.
3. M. Gilbert, Artificial Intelligence for Autonomous Networks , Chapman and Hall/CRC .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has pa rt (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 62

University of Mumbai, M.E. (Artificial Intelligence), 2019. 57 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO2025 Mixed Reality 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
To introduce the concepts of virtual reality, augmented reality & mixed reality and familiarize
learners with the architecture and techniques for mixed reality.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the fundamentals of virtual, augmented and mixed reality .
2. Understand the architecture of mixed reality systems .
3. Analyze the vital techniques required to turn a vision into reality .
4. Apply mixed reality development tools for implementing various techniques of mixed reality.
5. Design MR interfaces.
6. Develop mixed reality system s for real -world applications .

Prerequisites: Computer Graphics, Fundamentals of Virtual Reality a nd Augmented Reality.

Sr.
No. Module Detailed Content Hours
1 Introduction The Reality –Virtuality continuum; Virtual, augmented
and mixed reality, an historical perspective; Industrial
applicability of virtual, augmented and mixed reality;
How do we perceive reality? ; Fundamental concept and
components of virtual augmented and mixed reality. 8
2 Arch itecture and
Designing of MR
systems VR-AR-MR system architecture: Tracking system,
Visual, aural, and haptic display; Design principles:
From traditional UI design to mixed reality UI design ;
Usability guidelines: Space, scale and ergonomics of
immersive environments, comfort and distress, gaze
direction and comfort range test, motion sickness,
simulator sickness, cyber sickness. 10
3 Techniques for Mixed
Reality environments Common interaction techniques for mixed reality
environments: selection, manipul ation, isomorphic vs.
non- isomorphic, exocentric vs egocentric interaction ;
Common navigation techniques : physical locomotion
techniques, target based techniques, steering . 8
4 MR Development
Tools and
Frameworks Development Tools like X3D Standard / Vega /
MultiGen / Virtools / WebVR / React360 / Vuforia /
PTC / others. 6

Page 63

University of Mumbai, M.E. (Artificial Intelligence), 2019. 58 5 MR Interface
Designing Common interface for MR: Menu design directions,
haptic control panel, the interaction design process:
advanced user interaction and manipulation, distant vs
direct interaction, physical controls vs virtual controls;
Performance of an interaction techniques: speed,
accuracy and more. 10
6 Case Studies Case studies, researches on application of MR for
Medical, Education, Art and Entertainment, Military,
Manufacturing, etc. fields. 6

Text Books:
1. S. Benford , Performing Mixed Reality , The MIT Press .
2. Y. Ohta, H. Tamura , Mixed Reality: Merging Real and Virtual Worlds , Springer .
Reference Books:
1. K. Varnum , Beyond Reality: Augmented, Virtual, and Mixed Reality in the Library , Amer
Library Assn Editions .
2. J. Gwinner, Getting Started with React VR, Packt Publishing.
3. E. Pangilinan, S. Lukas, V. Mohan , Creating Augmented and Virtual Realities: Theory and
Practice for Next -Generation Spatial Computing , O'Reilly Media .
4. R. Virk, The Simulation Hypothesis: An MIT Computer Scientist Shows Why AI, Quantum
Physics and Eastern Mystics All Agree We Are in a Video Game, Bayview Books.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 quest ions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 64

University of Mumbai, M.E. (Artificial Intelligence), 2019. 59 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIDLO202 6 Robotics
Process
Automation 04 - - 04 - - 04
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
This course aims at providing knowledge of basic concepts of Robotic Process Automation to
students. It further builds on these concepts and introduces key RPA Design and Development
strategies and methodologies specifically in context of UiPath products. The student undergoing the
course shall develop the competence to design and develop a robot for a defined process.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand basic programming concepts and its operation from RPA perspective.
2. Understand the basic concepts of Robotic Process Automation and its applications.
3. Develop familiarity and deep understanding of UiPath tool s.
4. Apply automation to image, text, data tables, citrix, pdf, email, etc. , execute exception handling
and apply various functionalities of orchestrator .
5. Analyze opportunities of research in Artificial Intelligence with respect to RPA.
6. Design and create robots for business processes .

Prerequisites: Basic Programming skills

Sr.
No. Module Detailed Content Hours
1 Programming
Fundamentals Understanding the application; Basic Web Concepts;
Protocols; Email Clients; Data Structures; Data Tables;
Algorithms; Software Processes; Software Design; SDLC;
Scripting; Net Framework; .Net Fundamentals; XML;
Control structures and functions; XML; HTML; CSS;
Variables & Arguments . 6
2 RPA Concepts Fundamentals: History of Automation, Introduction to
RPA, RPA vs Automation, Processes & Flowcharts,
Programming Constructs in RPA, Processes and workloads
that can be Automated, Types of Bots ; Advanced concepts:
Standardization of processes, RPA Development
methodologies, Difference from SDLC, Robotic control
flow architecture, RPA business case, RPA Team, Process
Design Document/Solution Design Document, Industries
best suited for RPA, Risks & Challenges with RPA, RPA
and emerging ecosystem . 6
3 UiPath Introduction & Introduction: Installing UiPath Studio community edition, 12

Page 65

University of Mumbai, M.E. (Artificial Intelligence), 2019. 60 Exploration The User Interface, Keyboard Shortcuts
About Updating, About Automation Projects, Introduction
to Automation Debugging, Managing Activation Packages,
Reusing Automations Library, Installing the Chrome
Extension; Variables; Control Flow; Data Manipulation;
Recording and Advanced UI Interaction; Selectors.
4 UiPath Advanced
Automation Image, Text & Advanced Citrix Automation ; Excel Data
Tables & PDF; Email Automation; Debugging and
Exception Handling; Project Organization; Orchestrator:
Tenants, Authentication, Users, Roles, Robots,
Environme nts, Queues & Transactions, Schedules . 10
5 Artificial Intelligence
and RPA Research on application of RPA for Machine Learning,
Agent awareness, Natural Language Processing, Computer
Vision, etc. 4
6 Case Studies and
Projects Case studies and projects on applying RPA for designing
and developing robots for real -world problems. 10

Text Books:
1. A. Tripathi, Learning Robotic Process Automation: Create Software robots and automate
business processes with the leading RPA tool - UiPath : Create Software robots with the leading
RPA tool – UiPath, Packt Publishing.
2. K. Wibbenmeyer, The Simple Implementation Guide to Robotic Process Automation (RPA):
How to Best Implement RPA in an Organization, iUniverse.
Reference Books:
1. S. Merianda, Robot ic Process Automation Tools, Process Automation and Their Benefits:
Understanding RPA and Intelligent Automation, Createspace.
2. M. Lacity, L. Willcocks, Robotic Process and Cognitive Automation: The Next Phase, Steve
Brookes Publishing.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 66

University of Mumbai, M.E. (Artificial Intelligence), 2019. 61 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2021 Project
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To familiarize the students with the use of a structured methodology/approach for each and every
unique project undertaken, including utilizing project management concepts, tools and
techniques.
2. To appraise the students with the project management life cycle and make them knowledgeable
about the various phases from project initiation through closure.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Apply selection criteria and select an appropriate project from different options.
2. Write work break down structure for a project and develop a schedule based on it.
3. Identify opportunities and threats to the project and decide an approach to deal with them
strategically.
4. Use Earned value technique and determine & predict status of the project.
5. Capture lessons learned du ring project phases and document them for future reference .

Sr.
No. Detailed Content Hours
1 Project Management Foundation:
Definition of a project, Project Vs Operations, Necessity of project management,
Triple constraints, Project life cycles (typical & atypical) Project phases and stage
gate process. Role of project manager. Negotiations and resolving conflicts.
Project management in various organization structures. PM knowledge areas as per
Project Management Institute (PMI). 5
2 Initiating Projects:
How to get a project started, Selecting project strategically, Project selection
models (Numeric /Scoring Models and Non -numeric models), Project portfolio
process, Project sponsor and creating charter; Project proposal. Effective project
team, Stages of team development & growth (forming, storming, norming &
performing), team dynamics. 6
3 Project Planning and Scheduling:
Work Breakdown structure (WBS) and linear responsibility chart, Interface
Co-ordination and concurrent engineering, Project cost esti mation and budgeting,
Top down and bottoms up budgeting, Networking and Scheduling techniques.
PERT, CPM, GANTT chart. Introduction to Project Management Information
System (PMIS). 8

Page 67

University of Mumbai, M.E. (Artificial Intelligence), 2019. 62 4 Planning Projects:
Crashing project time, Resource loading and leveling, Goldratt's critical chain,
Project Stakeholders and Communication plan.
Risk Management in projects: Risk management planning, Risk identification and
risk register. Qualitative and quantitative risk assessment, Probability and impact
matrix. Ris k response strategies for positive and negative risks 6
5 5.1 Executing Projects:
Planning monitoring and controlling cycle. Information needs and reporting,
engaging with all stakeholders of the projects. Team management, communication
and project meetin gs.
5.2 Monitoring and Controlling Projects:
Earned Value Management techniques for measuring value of work completed;
Using milestones for measurement; change requests and scope creep. Project audit.
5.3 Project Contracting
Project procurement management, contracting and outsourcing, 8
6 6.1 Project Leadership and Ethics:
Introduction to project leadership, ethics in projects, Multicultural and virtual
projects.
6.2 Closing the Project:
Customer acceptance; Reasons of project termination, Various types of project
terminations (Extinction, Addition, Integration, Starvation), Process of project
termination, completing a final report; doing a lessons learned analysis;
acknowledging successes and failures; Project management templates and other
resources; Ma naging without authority; Areas of further study. 6
References:
1. Ja. Meredith & S. Mantel, Project Management: A managerial approach, Wiley India, 7thEd.
2. A Guide to the Project Management Body of Knowledge (PMBOK ® Guide), 5th Ed, Project
Management Institute , PA, USA .
3. G. Clements, Project Management, Cengage Learning.
4. M. Gopalan, Project Management, Wiley India .
5. D. Lock, Project Manageme nt, Gower Publishing England, 9th Edition.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions .
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of eac h module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 68

University of Mumbai, M.E. (Artificial Intelligence), 2019. 63 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2022 Finance
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. Overview of Indian financial system, instruments and market
2. Basic concepts of value of money, returns and risks, corporate finance, working capital and its
management
3. Knowledge about sources of finance, capital structure, dividend policy.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand Indian finance system and corporate finance
2. Take investment, finance as well as dividend decisions

Sr.
No. Detailed Content Hours
1 Overview of Indian Financial System: Characteristics, Components and
Functions of Financial System.
Financial Instruments: Meaning, Characteristics and Classification of Basic
Financial Instruments — Equity Shares, Preference Shares, Bonds -Debentures,
Certificates of Deposit, and Treasury Bills.
Financial Markets: Meaning, Characteristics and Classificat ion of Financial
Markets — Capital Market, Money Market and Foreign Currency Market
Financial Institutions: Meaning, Characteristics and Classification of Financial
Institutions — Commercial Banks, Investment -Merchant Banks and Stock
Exchanges 6
2 Concepts of Returns and Risks: Measurement of Historical Returns and
Expected Returns of a Single Security and a Two -security Portfolio; Measurement
of Historical Risk and Expected Risk of a Single Security and a Two -security
Portfolio.
Time Value of Money : Future Value of a Lump Sum, Ordinary Annuity, and
Annuity Due; Present Value of a Lump Sum, Ordinary Annuity, and Annuity Due;
Continuous Compounding and Continuous Discounting. 6
3 Overview of Corporate Finance: Objectives of Corporate Finance; Functio ns of
Corporate Finance —Investment Decision, Financing Decision, and Dividend
Decision.
Financial Ratio Analysis: Overview of Financial Statements —Balance Sheet,
Profit and Loss Account, and Cash Flow Statement; Purpose of Financial Ratio
Analysis; Liquidi ty Ratios; Efficiency or Activity Ratios; Profitability Ratios;
Capital Structure Ratios; Stock Market Ratios; Limitations of Ratio Analysis. 9

Page 69

University of Mumbai, M.E. (Artificial Intelligence), 2019. 64 4 Capital Budgeting: Meaning and Importance of Capital Budgeting; Inputs for
Capital Budgeting Decisions; Inve stment Appraisal Criterion —Accounting Rate
of Return, Payback Period, Discounted Payback Period, Net Present Value(NPV),
Profitability Index, Internal Rate of Return (IRR), and Modified Internal Rate of
Return (MIRR)
Working Capital Management: Concepts of Meaning Working Capital;
Importance of Working Capital Management; Factors Affecting an Entity’s
Working Capital Needs; Estimation of Working Capital Requirements;
Management of Inventories; Management of Receivables; and Management of
Cash and Marketable Securities. 10
5 Sources of Finance: Long Term Sources —Equity, Debt, and Hybrids; Mezzanine
Finance; Sources of Short Term Finance —Trade Credit, Bank Finance,
Commercial Paper; Project Finance.
Capital Structure: Factors Affecting an Entity’s Capital Str ucture; Overview of
Capital Structure Theories and Approaches — Net Income Approach, Net
Operating Income Approach; Traditional Approach, and Modigliani -Miller
Approach. Relation between Capital Structure and Corporate Value; Concept of
Optimal Capital Stru cture 5
6 Dividend Policy: Meaning and Importance of Dividend Policy; Factors Affecting
an Entity’s Dividend Decision; Overview of Dividend Policy Theories and
Approaches —Gordon’s Approach, Walter’s Approach, and Modigliani -Miller
Approach 3
References:
1. E. Brigham and J. Houston, Fundamentals of Financial Management, 13th Edition, Cengage
Publications, New Delhi, 2015.
2. R. Higgins, Analysis for Financial Management, 10th Edition, McGraw Hill Education, New
Delhi, 2013.
3. M. Y. Khan, Indian Financial System, 9th Edition, McGraw Hill Education, New Delhi, 2015.
4. I. Pandey, Financial Management, 11th Edition, S. Chand (G/L) & Company Limited, New Delhi.
2015.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixe d in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 70

University of Mumbai, M.E. (Artificial Intelligence), 2019. 65 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2023 Enterpreneurship
Development and
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To acquaint with entrepreneurship and management of business
2. Understand Indian environment for entrepreneurship
3. Idea of EDP, MSME .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the concept of business plan and ownerships
2. Interpret key regulations and legal aspects of entrepreneurship in India
3. Understand government policies for entrepreneurs .

Sr.
No. Detailed Content Hours
1 Overview of Entrepreneurship: Definitions, Roles and Functions/Values of
Entrepreneurship, History of Entrepreneurship Development, Role of
Entrepreneurship in the National Economy, Functions of an Entrepreneur,
Entrepreneurship and Forms of Business Ownership, Role of Money and Capit al
Markets in Entrepreneurial Development: Contribution of Government Agencies
in Sourcing information for Entrepreneurship. 4
2 Business Plans and Importance of Capital to Entrepreneurship: Preliminary
and Marketing Plans, Management and Personnel, Start -up Costs and Financing as
well as Projected Financial Statements, Legal Section, Insurance, Suppliers and
Risks, Assumptions and Conclusion, Capital and its Importance to the
Entrepreneur
Entrepreneurship And Business Development: Starting a New Business ,
Buying an Existing Business, New Product Development, Business Growth and
the Entrepreneur Law and its Relevance to Business Operations. 9
3 Women’s Entrepreneurship Development, Social entrepreneurship -role and need,
EDP cell, role of sustainability an d sustainable development for SMEs, case
studies, exercises. 5
4 Indian Environment for Entrepreneurship: key regulations and legal aspects ,
MSMED Act 2006 and its implications, schemes and policies of the Ministry of
MSME, role and responsibilities of v arious government organisations,
departments, banks etc., Role of State governments in terms of infrastructure
developments and support etc., Public private partnerships, National Skill
development Mission, Credit Guarantee Fund, PMEGP, discussions, group
exercises, etc. 8

Page 71

University of Mumbai, M.E. (Artificial Intelligence), 2019. 66 5 Effective Management of Business: Issues and problems faced by micro and
small enterprises and effective management of M and S enterprises (risk
management, credit availability, technology innovation, supply chain
management, linkage with large industries), exercises, e -Marketing. 8
6 Achieving Success In The Small Business: Stages of the small business life
cycle, four types of firm -level growth strategies, Options – harvesting or closing
small business Critical Success factors of small business. 5
References:
1. P. Charantimath , Entrepreneurship development - Small Business Enterprise, Pearson Education
2. R. Hisrich, M. Peters and A. Shapherd, Entrepreneurship, latest edition, The McGrawHill
Company
3. T. Chhabra, Entrepreneurship Development, Sun India Publications, New Delhi
4. C. N P rasad, Small and Medium Enterprises in Global Perspective, New century Publications,
New Delhi
5. V. Desai, Entrepreneurial development and management, Himalaya Publishing House
6. M. Lall and S. Sahai, Entrepreneurship, Excel Books
7. R. Bansal, STAY hungry STA Y foolish, CIIE, IIM Ahmedabad
8. Law and Practice relating to Micro, Small and Medium enterprises, Taxmann Publication Ltd.
9. Kurakto, Entrepreneurship - Principles and Practices, Thomson Publication
10. Laghu Udyog Samachar
11. www.msme.gov.in
12. www.dcmesme.gov.in
13. www.msmetraining.gov.in .
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related proje ct.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3) .
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 72

University of Mumbai, M.E. (Artificial Intelligence), 2019. 67 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2024 Human
Resource
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To introduce the students with basic concepts, techniques and practices of the human resource
management.
2. To provide opportunity of learning Human resource management (HRM) processes, related with
the functions, and challenges in the emerging perspective of today’s organizations.
3. To familiarize the students about the latest developments, trends & different aspects of HRM.
4. To acquaint the student with the importance of inter -personal & inter -group behavioral skills in
an organizational setting r equired for future stable engineers, leaders and managers.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the concepts, aspects, techniques and practices of the human resource management.
2. Understand the Human resource management (HRM) processes, functions, changes and
challenges in today’s emerging organizational perspective.
3. Gain knowledge about the latest developments and trends in HRM.
4. Apply the knowledge of behavioral skills learnt and integrate it with in inter personal and
intergroup environment emerging as future stable engineers and managers

Sr.
No. Detailed Content Hours
1 Introduction to HR
 Human Resource Management - Concept, Scope and Importance,
Interdisciplinary Approach Relationship with other Sciences, Competencies of
HR Manager, HRM functions.
 Human resource development (HRD): changing role of HRM – Human
resource Planning, Technological change, Restructuring and rightsizing,
Empowerment, TQM, Managing ethical issues. 5
2 Organizational Beha viour (OB)
 Introduction to OB Origin, Nature and Scope of Organizational Behavior,
Relevance to Organizational Effectiveness and Contemporary issues
 Personality: Meaning and Determinants of Personality, Personality
development, Personality Types, Assessment of Personality Traits for
Increasing Self Awareness
 Perception: Attitude and Value, Effect of perception on Individual Decision -
making, Attitude and Behavior.
 Motivation: Theories of Motivation and their Applications for Behavioral 7

Page 73

University of Mumbai, M.E. (Artificial Intelligence), 2019. 68 Change (Masl ow, Herzberg, McGregor);
 Group Behavior and Group Dynamics: Work groups formal and informal
groups and stages of group development. Team Effectiveness: High
performing teams, Team Roles, cross functional and self -directed team.
 Case study
3 Organizational Structure &Design
 Structure, size, technology, Environment of organization; Organizational Roles
& conflicts: Concept of roles; role dynamics; role conflicts and stress.
 Leadership: Concepts and skills of leadership, Leadership and manageria l
roles, Leadership styles and contemporary issues in leadership.
 Power and Politics: Sources and uses of power; Politics at workplace, Tactics
and strategies. 6
4 Human resource Planning
 Recruitment and Selection process, Job -enrichment, Empowerment - Job-
Satisfaction, employee morale.
 Performance Appraisal Systems: Traditional & modern methods, Performance
Counseling, Career Planning.
 Training & Development: Identification of Training Needs, Training Methods 5
5 Emerging Trends in HR
 Organizational development; Business Process Re -engineering (BPR), BPR as
a tool for organizational development , managing processes & transformation
in HR. Organizational Change, Culture, Environment
 Cross Cultural Leadership and Decision Making : Cross C ultural
Communication and d iversity at work , Causes of diversity, managing diversity
with special reference to handicapped, women and ageing people, intra
company cultural difference in employee motivation. 6
6 HR & MIS
 Need, purpose, objective and role o f information system in HR, Applications
in HRD in various industries (e.g. manufacturing R&D, Public Transport,
Hospitals, Hotels and service industries
Strategic HRM
 Role of Strategic HRM in the modern business world, Concept of Strategy,
Strategic Management Process, Approaches to Strategic Decision Making;
Strategic Intent – Corporate Mission, Vision, Objectives and Goals
Labor Laws & Industrial Relations
 Evolution of IR, IR issues in organizations, Overview of Labor Laws in India;
Industrial Dispu tes Act, Trade Unions Act, Shops and Establishments Act 10
References:
1. S. Robbins, Organizational Behavior, 16th Ed, 2013 .
2. V. Rao, Human Resource Management, 3rd Ed, 2010, Excel publishing .
3. K. Aswathapa, Human resource management: Text & cases, 6th edition, 2011 .
4. C. Mamoria and S . Gankar, Dynamics of Industrial Relations in India, 15th Ed, 2015, Himalaya
Publishing, 15thedition, 2015 .
5. P. Rao, Essentials of Human Resource management and Industrial relations, 5th Ed, 2013,
Himalaya Publishing .
6. L. Mullins, Management & Organizational Behavior, Latest Ed, 2016, Pearson Publications .

Page 74

University of Mumbai, M.E. (Artificial Intelligence), 2019. 69 Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 75

University of Mumbai, M.E. (Artificial Intelligence), 2019. 70 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2025 Professional
Ethics and
Corporat e
Social
Responsibility 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand professional ethics in business.
2. To recognized corporate social responsibility .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand rights and duties of business.
2. Distinguish different aspects of corporate social responsibility.
3. Demonstrate professional ethics.
4. Understand legal aspects of corporate social responsi bility .

Sr.
No. Detailed Content Hours
1 Professional Ethics and Business: The Nature of Business Ethics; Ethical Issues
in Business; Moral Responsibility and Blame; Utilitarianism: Weighing Social
Costs and Benefits; Rights and Duties of Business 4
2 Professional Ethics in the Marketplace: Perfect Competition; Monopoly
Competition; Oligopolistic Competition; Oligopolies and Public Policy
Professional Ethics and the Environment: Dimensions of Pollution and
Resource Depletion; Ethics of Pollution Control ; Ethics of Conserving Depletable
Resources 8
3 Professional Ethics of Consumer Protection: Markets and Consumer Protection;
Contract View of Business Firm’s Duties to Consumers; Due Care Theory;
Advertising Ethics; Consumer Privacy
Professional Ethics of Job Discrimination: Nature of Job Discrimination; Extent
of Discrimination; Reservation of Jobs. 6
4 Introduction to Corporate Social Responsibility: Potential Business Benefits —
Triple bottom line, Human resources, Risk management, Supplier relations;
Criticisms and concerns - Nature of business; Motives; Misdirection.
Trajectory of Corporate Social Responsibility in India 5
5 Corporate Social Responsibility: Articulation of Gandhian Trusteeship,
Corporate Social Responsibility and Small and Medium Enterprises (SMEs) in
India, Corporate Social Responsibility and Public -Private Partnership (PPP) in
India 8
6 Corporate Social Responsibility in Globalizing India : Corporate Social
Responsibility Voluntary Guidelines, 2009 issued by the Ministry of Corporate
Affairs, Government of India, Legal Aspects of Corporate Social Responsibility —
Companies Act, 2013. 8

Page 76

University of Mumbai, M.E. (Artificial Intelligence), 2019. 71 References:
1. A. Gupta, Business Ethics: Texts and Cases from the Indian Perspective, Springer, 2013.
2. A. Crane, D. Matten, L. Spence, Corporate Social Responsibility: Readings and Cases in a Global
Context, Routledge, 2007.
3. M. Velasquez, Business Ethics: Concepts and Cases, 7th Edition, Pearson, New Delhi, 2011.
4. B. Chakrabarty, Corporate Social Responsibility in India, New Delhi, 2015.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 77

University of Mumbai, M.E. (Artificial Intelligence), 2019. 72 Course Code Course
Nam e Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2026 Research
Methodology 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand Research and Research Process
2. To acquaint students with identifying problems for research and develop research strategies
3. To familiarize students with the techniques of data collection, analysis of data and interpretation .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Prepare a preliminary research design for projects in their subject matter areas.
2. Accurately collect, analyze and report data.
3. Present complex data or situations clearly.
4. Review and analyze research findings .

Sr.
No. Detailed Content Hours
1 Introduction and Basic Research Concepts
1.1 Research – Definition; Concept of Construct, Postulate, Proposition, Thesis,
Hypothesis, Law, Principle. Research methods vs Methodology
1.2 Need of Research in Business and Social Sciences
1.3 Objectives of Research
1.4 Issues and Problems in Research
1.5 Characteristics of Research: Systematic, Valid, Verifiable, Empirical and
Critical 9
2 Types of Research
2.1. Basic Research
2.2. Applied Research
2.3. Descriptive Research
2.4. Analytical Research
2.5. Empirical Research
2.6 Qualitative and Quantitative Approaches 7
3 Research Design and Sample Design
3.1 Research Design – Meaning, Type s and Significance
3.2 Sample Design – Meaning and Significance Essentials of a good sampling
Stages in Sample Design Sampling methods/techniques Sampling Errors 7
4 Research Methodology
4.1 Meaning of Research Methodology
4.2. Stages in Scientific Research Process:
a. Identification and Selection of Research Problem 8

Page 78

University of Mumbai, M.E. (Artificial Intelligence), 2019. 73 b. Formulation of Research Problem
c. Review of Literature
d. Formulation of Hypothesis
e. Formulation of research Design
f. Sample Design
g. Data Collection
h. Data Analysis
i. Hypothesis testing and Interpretation of Data
j. Preparation of Research Report
5 Formulating Research Problem
5.1 Considerations: Relevance, Interest, Data Availability, Choice of data,
Analysis of data, Generalization and Interpretation of analysis 4
6 Outcome of Research
6.1 Preparation of the report on conclusion reached
6.2 Validity Testing & Ethical Issues
6.3 Suggestions and Recommendation 4
References:
1. C. Dawson, Practical Research Methods, New Delhi, UBS Publishers Distributors, 2002.
2. C. Kothari, Research Methodology -Methods and Techniques, New Delhi, Wiley Eastern Limited,
1985.
3. R. Kumar, Research Methodology -A Step -by-Step Guide for Beginners, 2nd edition, Singapore,
Pearson Education, 2005.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will com prise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In questi on paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 79

University of Mumbai, M.E. (Artificial Intelligence), 2019. 74 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2027 IPR and
Patenting 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To understand intellectual property rights protection system
2. To promote the knowledge of Intellectual Property Laws of India as well as International treaty
procedures
3. To get acquaintance with Patent search and patent filing procedure and applications .
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand Intellectual Property assets .
2. Assist individuals and organizations in capacity building .
3. Work for development, promotion, protection, compliance, and enforcement of Intellectual
Property and Patenting .

Sr.
No. Detailed Content Hours
1 Introduction to Intellectual Property Rights (IPR) : Meaning of IPR, Different
category of IPR instruments - Patents, Trademarks, Copyrights, Industrial Designs,
Plant variety protection, Geographical indications, Transfer of technology etc.
Importance of IPR in Modern Global Economic Environment: Theori es of
IPR, Philosophical aspects of IPR laws, Need for IPR, IPR as an instrument of
development 5
2 Enforcement of Intellectual Property Rights: Introduction, Magnitude of
problem, Factors that create and sustain counterfeiting/piracy, International
agree ments, International organizations (e.g. WIPO, WTO) active in IPR
enforcement
Indian Scenario of IPR: Introduction, History of IPR in India, Overview of IP
laws in India, Indian IPR, Administrative Machinery, Major international treaties
signed by India, Procedure for submitting patent and Enforcement of IPR at
national level etc. 7
3 Emerging Issues in IPR: Challenges for IP in digital economy, e -commerce,
human genome, biodiversity and traditional knowledge etc. 5
4 Basics of Patents: Definition of Patents, Conditions of patentability, Patentable
and non -patentable inventions, Types of patent applications (e.g. Patent of addition
etc.), Process Patent and Product Patent, Precautions while patenting, Patent
specification Patent claims, Disclosures and non-disclosures, Patent rights and
infringement, Method of getting a patent 7
5 Patent Rules: Indian patent act, European scenario, US scenario, Australia 8

Page 80

University of Mumbai, M.E. (Artificial Intelligence), 2019. 75 scenario, Japan scenario, Chinese scenario, Multilateral treaties where India is a
member (TRIPS agreement, Paris convention etc.)
6 Procedure for Filing a Patent (National and International): Legislation and
Salient Features, Patent Search, Drafting and Filing Patent Applications,
Processing of patent, Patent Litigation, Patent Publication, etc, T ime frame and
cost, Patent Licensing, Patent Infringement
Patent databases: Important websites, Searching international databases 7
References:
1. R. Adukia, A Handbook on Laws Relating to Intellectual Property Rights in India, The Institute
of Chartered Acc ountants of India, 2007.
2. B. Keayla, Patent system and related issues at a glance, Published by National Working Group on
Patent Laws.
3. T. Sengupta, Intellectual Property Law in India, Kluwer Law International, 2011.
4. T. Wong and G. Dutfield, Intellectual Property and Human Development: Current Trends and
Future Scenario, Cambridge University Press, 2010.
5. W. Cornish, and D. Llewelyn, Intellectual Property: Patents, Copyrights, Trade Marks and Allied
Right, 7th Edition, Sweet & Maxwell, 2010.
6. H. Lous, The en forcement of Intellactual Property Rights: A Case Book, 3rd Edition, WIPO,
2012.
7. P. Ganguli, Intellectual Property Rights, 1st Edition, TMH, 2012.
8. R. Radha Krishnan & S. Balasubramanian, Intellectual Property Rights, 1st Edition, Excel Books,
2012.
9. M. Ash ok Kumar and M. Iqbal Ali, Intellectual Property Rights, 2nd Edition, Serial Publications
10. K. Bansal and Pr. Bansal, Fundamentals of IPR for Engineers, 1st Edition, BS Publications, 2012.
11. Entrepreneurship Development and IPR Unit, BITS Pilani, A Manual on I ntellectual Property
Rights, 2007.
12. M. Maa, Fundamentals of Patenting and Licensing for Scientists and Engineers, World Scientific
Publishing Company, 2009.
13. N. Rathore, S. Mathur, P. Mathur, A. Rathi , IPR: Drafting,Interpretation of Patent Specifications
and Claims , New India Publishing Agency.
14. V. Irish, Intellectual Property Rights for Engineers, IET. 2005.
15. H. Rockman, Intellectual Property Law for Engineers and scientists, Wiley -IEEE Press, 2005.
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 81

University of Mumbai, M.E. (Artificial Intelligence), 2019. 76 Course Code Course
Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2028 Digital
Business
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. To familiarize with digital business concept.
2. To acquaint with E -commerce.
3. To give insights into E -business and its strategies.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Identify drivers of digital business
2. Illustrate various approaches and techniques for E-business and management
3. Prepare E -business plan .

Sr.
No. Detailed Content Hours
1 Introduction to Digital Business - Introduction, Background and current status, E -
market places, structures, mechanisms, economics and impacts
Difference between physic al economy and digital economy.
Drivers of digital business - Big Data & Analytics, Mobile, Cloud Computing,
Social media, BYOD, and Internet of Things (digitally intelligent
machines/services) , Opportunities and Challenges in Digital Business. 9
2 Overview o f E-Commerce - Meaning, Retailing in e -commerce -products and
services, consumer behaviour, market research and advertisement
B2B-E-commerce -selling and buying in private e -markets, public B2B exchanges
and support services, e -supply chains, Collaborative Commerce, Intra business EC
and Corporate portals .
Other E -C models and applications, innovative EC System -From E -government
and learning to C2C, mobile commerce and pervasive computing .
EC Strategy and Implementation -EC strategy and global EC, Economics and
Justification of EC, Using Affiliate marketing to promote your e -commerce
business, Launching a successful online business and EC project, Legal, Ethics
and Societal impacts of EC . 6
3 Digital Business Support services : ERP as e –business backbone, kn owledge
Tope Apps, Information and referral system .
Application Development: Building Digital business Applications and
Infrastructure . 6
4 Managing E -Business -Managing Knowledge, Management skills for e -business,
Managing Risks in e –business , Security T hreats to e -business -Security Overview, 6

Page 82

University of Mumbai, M.E. (Artificial Intelligence), 2019. 77 Electronic Commerce Threats, Encryption, Cryptography, Public Key and Private
Key Cryptography, Digital Signatures, Digital Certificates, Security Protocols over
Public Networks: HTTP, SSL, Firewall as Security Cont rol, Public Key
Infrastructure (PKI) for Security, Prominent Cryptographic Applications .
5 E-Business Strategy -E-business Strategic formulation - Analysis of Company’s
Internal and external environment, Selection of strategy, E -business strategy into
Action, challenges and E -Transition (Process of Digital Transformation) . 4
6 Materializing e -business: From Idea to Realization -Business plan preparation
Case Studies and presentations 8
References:
1. A. Mishra, W. Sarwade, A Textbook on E -commerce, Neha Publishers & Distributors, 2011.
2. E. Awad, E -commerce from vision to fulfilment, PHI-Restricted, 2002.
3. D. Chaffey Digital Business and E -Commerce Management, 6th Ed, Pearson, August 2014.
4. C. Combe, Introduction to E -Business -Management and Strategy, Elsevie r, 2006
5. E. Coupey, Digital Business Concepts and Strategy, 2nd Edition, Pearson
6. V. Morabito, Trend and Challenges in Digital Business Innovation, Springer
7. E. Darics, Digital Business Discourse, Palgrave Macmillan, April 2015.
8. E-Governance -Challenges and Op portunities, Proceedings in 2nd International Conference theory
and practice of Electronic Governance Perspectives
9. The Digital Enterprise - A framework for transformation, TCS consulting journal, vol. 5
10. Measuring Digital Economy - A new perspective -DOI: 10.1787/9789264221796 -en, OECD
Publishing
Internal Assessment:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper will comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 83

University of Mumbai, M.E. (Artificial Intelligence), 2019. 78 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
ILO2029 Environmental
Management 03 - - 03 - - 03
Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
(in Hrs) Test 1 Test 2 Avg
20 20 20 80 03 - - 100
Course Objectives:
1. Understand and identify environmental issues relevant to India and global concerns.
2. Learn concepts of ecology.
3. Familiarize environment related legislations.
Course Outcomes:
Upon completion of the course, the learners will be able to:
1. Understand the concept of environmental management.
2. Understand ecosystem and interdependence, food chain etc.
3. Understand and interpret environment related legislations .

Sr.
No. Detailed Content Hours
1 Introduction and Definition of Environment: Significance of Environment
Management for contemporary managers, Career opportunities.
Environmental issues relevant to India, Sustainable Development, The Energy
scenario. 10
2 Global Environmental concerns : Global Warming, Acid Rain, Ozone Depletion,
Hazardous Wastes, Endangered life -species, Loss of Biodiversity, Industrial/Man -
made disasters, Atomic/Biomedical hazards, etc. 6
3 Concep ts of Ecology: Ecosystems and interdependence between living organisms,
habitats, limiting factors, carrying capacity, food chain, etc. 5
4 Scope of Environment Management, Role & functions of Government as a
planning and regulating agency.
Environment Quality Management and Corporate Environmental Responsibility 10
5 Total Quality Environmental Management, ISO -14000, EMS certification. 5
6 General overview of major legislations like Environment Protection Act, Air (P &
CP) Act, Water (P & CP) Act, Wil dlife Protection Act, Forest Act, Factories Act,
etc. 3
References:
1. C. Barrow, Environmental Management: Principles and Practice, Routledge Publishers London,
1999 .
2. J. Lovett and D. Ockwell, A Handb ook of Environmental Management , Edward Elgar Publishing .
3. T. Ramachandra and V. Kulkarni, Environmental Management, TERI Press .

Page 84

University of Mumbai, M.E. (Artificial Intelligence), 2019. 79 4. Indian Standard Environmental Management Systems — Requirements with Guidance For Use,
Bureau Of Indian Standards, February 2005
5. S. Chary and V. Vyasulu, Environmental Management: An Indian Perspective, Macmillan
Publishing, India, 2000 .
6. M. Theodore and L. Theodore, Introduction to Environmental Management, CRC Press
7. M. Hussain, Environment and Ecology, 3rd Edition, Access Publishing , 2015 .
Internal Assessm ent:
Assessment consists of two tests out of which one should be compulsorily class test (on minimum 02
modules) and the other can be either a class test or assignment on real -world problems or course
related project.
Theory Examination:
1. Question paper wi ll comprise of total 6 questions.
2. All questions carry equal marks.
3. Questions will be mixed in nature (for example, suppose Q2 has part (a) from module 3, then Q2
part (b) will be from any module other than module 3).
4. Only 4 questions need to be solved.
5. In question paper, weightage of each module will be proportional to the number of respective
lecture hours as mentioned in the syllabus.

Page 85

University of Mumbai, M.E. (Artificial Intelligence), 2019. 80 Subject Code Subject Name Credits
MEAIL201 Machine Learning Lab 04
Practical sessions based on the course s MEAIC20 1 and MEAIC203 will be conducted in this
laboratory. Implementation of bio-inspired algorithms, deep learning, reinforcement learning, and
deep reinforcement learning will be done in Caffe , Python , TensorFlow and MATLAB .
Subject Code Subject Name Credits
MEAIL202 Big Data Lab 04
Practical sessions based on the course MEAIC202 will be conducted in this laboratory .
Implementation of techniques for big data analytics, data streams and privacy -preserving data mining
will be done using Hadoop , MapReduce , Pig/Hive , NoSQL , MOA , Weka and Python .
End Semester Examination:
Practical/Oral examination for both laboratories is to be conducted by a pair of internal and external
examiners appointed by the University of Mumbai.

Page 86

University of Mumbai, M.E. (Artificial Intelligence), 2019. 81 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAIS301 Seminar: State -of-the-art
research topics - 06 - - 03 - 03
MEAID301 Dissertation – I - 24 - - 12 - 12
Total - 30 - - 15 - 15
Course Code Course Name Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
MEAIS301 Seminar: State -of-
the-art research
topics - - - - - 50 50 100
MEAID301 Dissertation – I - - - - - 100 - 100
Total - - - - - 150 50 200

Guidelines for Seminar:
 Seminar should be based on thrust areas in Artificial Intelligence.
 Students should do literature survey, identify the topic of seminar and finalize it with consultation
of Guide/Supervisor.
 Students should use multiple lit eratures from at least 10 papers from refereed Journals (Scopus
Indexed & with good Thomson Reuters Impact Factor) / renowned Conferences to understand the
topic and research gap.
 Implementation of one paper from refereed journal as a case study is require d.
 The report should be compiled in standard format and present to the panel of examiners. (Pair of
Internal and External examiners appointed by the University of Mumbai).
 It is advisable to students should publish at least one paper based on the work in r eputed
International / National Conference.
Note: At least 4 -5 hours of course on Research Methodology should be conducted which includes
literature survey, identification of problems, analysis and interpretation of results and technical paper
writing in the beginning of 3rd semester.
Guidelines for Diss ertation - I:
Students should do literature survey and identify the problem for Dissertation and finalize in
consultation with Guide/Supervisor. Students should use multiple literatures from refereed Journals
(Scopus Indexed & with good Thomson Reuters Impact Factor) / renowned Conferences to
understand the problem. Students should attempt solution to the problem by
analytical/simulation/experimental methods. The solution to be validated with proper justification
and compile the report in standard format .

Page 87

University of Mumbai, M.E. (Artificial Intelligence), 2019. 82 Guidelines for Assessment of Dissertation - I:
Dissertation - I should be assessed based on following points:
 Quality of Literature Survey and Novelty in the Problem
 Clarity of Problem Definition and Feasibility of Problem Solution
 Relevance to the Sp ecialization
 Clarity of Objective and Scope
Dissertation -I should be assessed through a presentation by a panel of Internal examiners and
External examiner appointed by the Head of the Department/Institute of respective program.

Page 88

University of Mumbai, M.E. (Artificial Intelligence), 2019. 83 Course Code Course Name Teaching Scheme
(Contact Hours) Credits Assigned
Theory Prac Tut Theory Prac Tut Total
MEAID401 Dissertation – II - 30 - - 15 - 15
Total - 30 - - 15 - 15
Course Code Course Name Examination Scheme
Theory
TW Oral/
Prac Total Internal End
Sem.
Exam Exam
Duration
( in Hrs) Test 1 Test 2 Avg
MEAID401 Dissertation - II - - - - - 100 100 200
Total - - - - - 100 100 200

Guidelines for Assessment of Dissertation – II:
Dissertation - II should be assessed based on following points:
 Quality of Literature Survey and Novelty in the Problem
 Clarity of Problem Definition and Feasibility of Problem Solution
 Relevance to the Specialization
 Clarity of Objective and Scope
 Quality of Work Attempted or Learner Contribution
 Validation of Results
 Quality of Written and Oral Presentation
Students should publish at least one paper based on the work in referred National/International
conference/Journal of repute. Dissertation II should be assessed by Internal and External Examiners
appointed by the University of Mumbai.