M.Sc.

, ARTIFICIAL
INTELLIGENCE
Syllabus

UNIVERSITY DEPARTMENT

Program Code:

2024 – 2025 onwards

BHARATHIAR UNIVERSITY
(A State University, Accredited with “A++” Grade by NAAC,
Ranked 21st among Indian Universities by MHRD-NIRF)
Coimbatore - 641 046, Tamil Nadu, India
1
 BHARATHIAR UNIVERSITY :: COIMBATORE - 641046

DEPARTMENT OF COMPUTER SCIENCE

(Effective from the academic Year 2024-2025)

MISSION

 Creating and disseminating world-class knowledge in the global context

 Equip students with knowledge of up-to-date technological developments to take part in
the global software industry
 Promote state of art interdisciplinary research in computer science
 Imbibe entrepreneurial culture through curriculum, pedagogy, research, and mentoring

1. Eligibility for Admission to the Programme

Candidates for admission to the first-year programme leading to the Degree of Master of
Science in Artificial Intelligence (M.Sc., AI) will be required to possess:
A pass in B.Sc. Computer Science/ Information Technology/ Computer Applications or
its equivalents.

2. Duration of the Programme

The programme shall be offered on a full-time basis. The programme will consist of three
semesters of coursework and laboratory work and the fourth semester consists of project work.

3. Regulations
The general Regulations of the Bharathiar University Choice-Based Credit System
Programme apply to this programme.

4. The Medium of Instruction and Examinations

The medium of instruction and Examinations shall be in English.

5. Submission of Record Notebooks for Practical Examinations & Project Viva-Voce

Candidates taking the Practical Examinations should submit bonafide Record Note Books
prescribed for the Examinations. Otherwise, the candidates will not be permitted to take the
Practical Examinations.
Candidates taking the Project Viva Examination should submit the Project Report prescribed for
the Examinations. Otherwise, the candidates will not be permitted to take the Project Viva-voce
Examination.
PROGRAMME EDUCATIONAL OBJECTIVES (PEOs)
2
The M.Sc. Artificial Intelligence programme describes accomplishments that graduates
are expected to attain within five to seven years after graduation
PEO1 Graduates will have developed advanced technical expertise in artificial
intelligence, machine learning, and data science.
PEO2 Graduates will demonstrate leadership and innovation in their professional roles,
driving advancements in AI technologies and applications.
PEO3 Graduates will engage in continuous professional development and lifelong
learning, staying current with the latest trends, technologies, and research in
artificial intelligence.
PEO4 Graduates will exhibit ethical and social responsibility in their professional
practices, understanding the societal impacts of AI technologies.
PEO5 Graduates will effectively collaborate and communicate with professionals from
diverse disciplines, leveraging their AI expertise to solve complex problems.

PROGRAMME SPECIFIC OUTCOMES (PSOs)

After the successful completion of M.Sc. Artificial Intelligence programme, the students
are expected to
PSO1 Students will be able to apply fundamental and advanced AI techniques to develop
innovative solutions for real-world problems across various domains.
PSO2 Students will demonstrate proficiency in using state-of-the-art AI tools,
frameworks, and programming languages to design, implement, and optimize AI
models and systems.
PSO3 Students will be equipped to conduct independent research, contributing to the
advancement of the AI field by developing novel algorithms and methodologies.
PSO4 Students will understand and incorporate ethical considerations in the
development and deployment of AI systems
PSO5 Students will be adept at collaborating with professionals from various disciplines
to address complex challenges and provide inventive solutions

3
PROGRAMME OUTCOMES (POs)
On successful completion of the M.Sc. Artificial Intelligence programme
PO1 Demonstrate comprehensive knowledge of artificial intelligence theories,
principles, and techniques, and their applications in solving complex problems.
PO2 Exhibit technical proficiency in using AI tools, frameworks, and programming
languages to develop and implement AI solutions.
PO3 Apply critical thinking and problem-solving skills to analyze, design, and optimize
AI models and systems for various applications..
PO4 Conduct independent research in AI, contributing to the body of knowledge with
innovative findings.
PO5 Understand and apply ethical principles in the development and deployment of AI
technologies.
PO6 Collaborate effectively with professionals from diverse fields to integrate AI
solutions in multidisciplinary projects and initiatives.
PO7 Demonstrate strong communication skills, both written and verbal, to convey
complex AI concepts and findings to technical and non-technical audiences.
PO8 Engage in lifelong learning and professional development to stay current with
advancements in AI and related fields.
PO9 Manage AI projects effectively, utilizing project management principles to ensure
successful project planning, execution, and delivery.
PO10 Exhibit innovation and entrepreneurial skills to identify opportunities for AI
applications and create new AI-based products or services.

4
 BHARATHIAR UNIVERSITY :: COIMBATORE 641 046
M.Sc. Artificial Intelligence Curriculum (University Department)
(For the students admitted during the academic year 2024 – 2025 onwards)
Course Hours Maximum Marks
Title of the Course Credits
Code Theory Practical CIA ESE Total
First Semester
Advanced Data Structures
24AI1C1 4 2 4 25 75 100
and Algorithms
Foundations in Statistics &
24AI1C2 4 2 4 25 75 100
Mathematics for AI
24AI1C3 Foundations of AI 4 4 - 25 75 100
Machine Learning and its
24AI1C4 4 2 4 25 75 100
Applications
24AI1C5 Foundations of Data Science 4 4 - 25 75 100
24AI1EX Elective I 4 4 - 25 75 100
1GS Supportive 2 2 - 12 38 50
PDC Industry Literacy 1 - - 25 - 25
24AI1JOC1 Job Oriented course 2 - - - - 50
Total 29 725
Second Semester
24AI2C1 Computational Intelligence 4 4 - 25 75 100
24AI2C2 Deep Learning Techniques 4 2 4 25 75 100
24AI2C3 Data Engineering 4 2 4 25 75 100
24AI2C4 Probabilistic Graphical Model 4 4 - 25 75 100
24AI2C5 Cloud and Big Data Analytics 4 2 4 25 75 100
24AI2EX Elective II 4 4 - 25 75 100
24AI2MP Mini Project - I 2 - - 50 - 50
2GS Supportive 2 2 - 12 38 50
24AI2VAC1 Value Added Course 2 - - - - 50
Total 30 750
Third Semester
Introduction to Speech
24AI3C1 4 2 4 25 75 100
Processing
24AI3C2 Natural Language Processing 4 2 4 25 75 100
24AI3C3 Reinforcement Learning 4 2 4 25 75 100
24AI3C4 Multi Agent Systems 4 2 4 25 75 100
24AI3EX Elective III 4 4 - 25 75 100
24AI3MP Mini Project - II 4 - - 25 75 100
3GS Supportive 2 2 - 12 38 50
Literature Survey & Gap
PDC 1 - - 25 - 25
Analysis
24AI3JOC2 Job Oriented course 2 - - - - 50
Total 29 725
Fourth Semester
24AI4PW Project work 12 - - 180 120 300
24AI4VAC2 Value Added Course 2 - - - - 50
Total 14 350
Grand Total 102 2550
5
 Online Course

SWAYAM – MOOC 2
Course*

*Swayam – Mooc online course shall be for at least 4 weeks with at least 2 credits.
The course shall be mandatory and shall be completed within the third semester (i.e., before the
beginning of the fourth semester)

Elective Papers

Se Group1 with Group2 with Suggested Group3 with

Elective
m Suggested Code Code Suggested Code

24AI1E1 24AI1E2 24AI1E3

I Elective - I
Representation Learning Data Visualization AI in IoT

24AI2E3
24AI2E1 24AI2E2
II Elective - II Machine Learning
AI for Robotics AI in Healthcare
for Big Data
24AI3E3
24AI3E1 24AI3E2
III Elective - III Applied Prediction
Computer Vision Quantum AI
Analytics

List of Job Oriented/Value Added Course

1. Data Analysis using Excel

2. Power BI for Data Analytics
3. Software Testing Tools
4. Cyber Security and Digital Forensics
5. Mobile Application Development
6. Smart Applications with the Internet of Things
7. Remote Sensing and GIS

6
SEMESTER - I

7
 Course Code ADVANCED DATA STRUCTURES AND L T P C
24AI1C1
ALGORITHMS
Core/Elective/Supportive CORE 2 0 4 4

Pre-requisite BASIC DATA STRUCTURES AND Syllabus 2024-2025

FUNDAMENTALS ALGORITHMS Version
Course Objectives:
 This course builds upon the fundamental data structures and algorithms.
 Its goal is to empower students to design data structures and algorithms to solve intricate problems,
especially within the AI domain
 The primary focus will be on concrete implementations of diverse data structures and their
application in sophisticated algorithms with thorough analysis.

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 1. Provide an insight into Data structures and algorithms in real-life domain K2/K3
scenarios.
2 Solve complex problems by applying appropriate Data structures and K1/K3
algorithms
3 Critically analyse the complexity of various algorithms and provide an K2/K5
understanding of efficiency and performance characteristics
4 To select suitable design strategies to solve real-world problems within the K6
AI domain
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 - Create
Unit 1 Algorithm Analysis and Number Theory Fundamentals 9 hours
Algorithm Analysis - Methodologies for Analysing Algorithms, Asymptotic growth rates, Amortized
Analysis. Number Theory: Preliminaries, FLT, Euclid’s algorithm (extended), Totient function, Sieve
for primes, Modular exponentiation
Unit 2 Advanced Algorithms and Problem-Solving Techniques 12 hours
Graph terminology and representation Applications of graph algorithms: Topological sort, connected
components, Bi-connected Components, Bridges, Articulation points, All Pairs Shortest Paths, Single
Source Shortest Paths. Applications of Divide-and-Conquer

Unit 3 Advanced Algorithmic Techniques 11 hours

Greedy and Dynamic programming techniques - Knapsack, Median finding, Scheduling algorithms,
Party planning, bitonic TSP. String matching algorithms: the Boyer- Moore, KMP algorithm, Hash-
based lexicon matching

Unit 4 Advanced-Data Structures & Network Flow Algorithms 12 hours

Universal hashing, consistent hashing, load balancing, power of two choices, B-trees, Suffix trees,
Segment trees, Flow Networks: Ford-Fulkerson algorithm, Edmonds Karp algorithm
Unit 5 NP-Completeness and Approximation Algorithms 14 hours

8
Applications of maximum flows - Maximum bipartite matching, minimum cost matching, NP-
Completeness: Important NP-Complete Problems, Polynomial-time reductions, Approximation
algorithms.
Total Lecture hours 58 hours
Text Book(s)
1 Cormen T H, Leiserson CE, Rivest R L, and Stein C,” Introduction to Algorithms”,
Prentice-Hall of India Private Limited. Third Edition 2009.
2 Michael T Goodrich and Roberto Tamassia,” Algorithm Design and Applications”, Wiley, -
first edition 2014

Reference Books
1 Rajeev Motwani and Prabhakar Raghavan, ”Randomized Algorithms”, Cambridge
University Press- First edition, 1995.
2 Vijay V. Vazirani,” Approximation Algorithm”, Springer Science and Business Media –
Second edition 2003

Course Designed by: Dr. D. RAMYACHITRA

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M L L L M M M L M
CO2 L S S L M L L L M M
CO3 L L S M M L L M M L
CO4 S M M M L M L M M S

*S-Strong; M-Medium; L-Low

Advanced Data Structures and Algorithms – LAB

List of Programs

1. Generation of Graph
2. Topological Sorting
3. All Pairs Shortest Path
4. Single Source Shortest Path
5. Implementation of Knapsack problem
6. Travelling Salesman Problem
7. B Tree
8. Ford Fulkerson Algorithm
9. KMP algorithm for pattern matching

9
 FOUNDATIONS IN STATISTICS AND
Course Code 24AI1C2 L T P C
MATHEMATICS FOR AI
Core/Elective/Supportive CORE 3 1 0 4
Syllabus 2024-
Pre-Requisite Mathematics and Statistics
Version 2025
Course Objective:
The main objectives of this course are:
 To express various matrix techniques and illustrate the matrix's nature.
 To gather the techniques in matrix algebra and the concepts of basis and dimension in vector
spaces.
 To discuss general inner product spaces with associated norms and matrix decompositions.
 To provide knowledge of different distributions
 To explore the parameter estimation

Expected Course Outcomes:

On the successful completion of the course, students will able to:
1 Demonstrate the matrix techniques in solving problems. K1/K2
2 Apply the concepts of basis and dimension in vector spaces. K2/K4
3 Interpret the inner product spaces. K2/K4
4 Perform different kinds of statistical distributions K2/K4
5 Understand the concepts of parameter estimation and the relevant problems K2/K3/K6
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit: 1 MATRICES AND QUADRATIC FORMS 12 Hours

Matrices: Types - Symmetric and Skew – symmetric matrices, Hermitian matrix, Unitary matrix and
Orthogonal matrices – Rank, Inverse, and Trace of a matrix - Eigenvalues and eigenvectors-
Diagonalization of matrices using orthogonal transformation - Quadratic forms - Reduction to canonical
form using orthogonal transformation

Unit: 2 VECTOR SPACES 12 Hours

Vector spaces – Subspaces – Linear combinations and system of Linear equations – Linear
independence and Linear dependence – Bases and Dimensions – Linear Transformation – Matrix
representation of Linear Transformation - Null space, Range space, and dimension theorem (without
proof).

Unit: 3 INNER PRODUCT SPACES 12 Hours

Inner product and norms - Gram Schmidt orthonormalization process - QR Factorization-Singular value
decomposition -Principal component analysis.

Unit: 4 PROBABILITY AND STATISTICS FOR COMPUTER SCIENCE 11 Hours

Introduction to Statistics and Probability – Probability and Conditioning – Conditional Probability –
Bayes rule – Random variables – Expectation and Variance – Covariance – Discrete and Continuous
Distributions- Uniform, Gaussian and Rayleigh distributions; Binomial, and Poisson distributions;
Multivariate Gaussian distribution – Central Limit Theorem

10
Unit: 5 STATISTICS AND PARAMETER ESTIMATION 11 Hours
Confidence intervals and Hypothesis testing. Elements of estimation theory: linear minimum mean-
square error and orthogonality principle in estimation; Moment-generating and characteristic functions
and their Applications-Bounds and approximations: Chebysev inequality and Chernoff Bound

Unit: 6 CONTEMPORARY ISSUES 2 Hours

Discussion on case study - Expert lectures - Online seminars – Webinars – Workshops
Total Lectures 60 Hours
Text Books
T Veerarajan , Linear Algebra, and Partial Differential Equations, Mc Graw Hill
1
Education,2019.
2 T Veerarajan, Engineering Mathematics –I , Mc Graw Hill Education, 2018
David Forsyth, “Probability and Statistics for Computer Science”, Springer international
3
publishing, 2018
Ernest Davis, “Linear Algebra and Probability for Computer Science Applications”, CRC
4
Press, 2012
Grewal B.S., “Higher Engineering Mathematics”, Khanna Publishers, New Delhi, 43rd
5
Edition, 2014.
Reference Books
Ramana. B.V., " Higher Engineering Mathematics ", McGraw Hill Education Pvt.Ltd, New
1
Delhi, 2016.
Friedberg, A.H., Insel, A.J. and Spence, L., ―Linear Algebra‖, Prentice - Hall of India, New
2
Delhi, 2004.
Erwin Kreyszig ," Advanced Engineering Mathematics ", John Wiley and Sons, 10th Edition,
3
New Delhi, 2016.
Douglas C. Montgomery and George C. Runger, “Applied Statistics and Probability for
4
Engineers”, Third Edition, John Wiley & Sons Inc., 2003.
Ronald E. Walpole, Raymond H Myres, Sharon.L. Myres and Kying Ye, “Probability and
5
Statistics for Engineers and Scientists”, Seventh Edition, Pearson Education, 2002.
A. Papoulis and UnnikrishnaPillai, “Probability, Random Variables and Stochastic
6
Processes”, Fourth Edition, McGraw Hill, 2002.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.udemy.com/course/mathematical-foundation-for-machine-learning-and-ai/
2 https://www.coursera.org/learn/machine-learning-probability-and-statistics
3 https://www.coursera.org/learn/math-for-ai-beginner-part-1-linear-algebra
Course Designed by:

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S M M L S L M M M
CO2 M S S M L M L S S S
CO3 S S S S M M L S S S
CO4 S S S S M M L M S M
CO5 S M M S M M L M S S

*S-Strong; M-Medium; L-Low

11
 Course
24AI1C3 FOUNDATION OF AI L T P C
Code
Core/Elective/Supportive CORE 4 0 0 4
Syllabus 2024-
Pre-requisite
Version 2025
Course Objectives:
The main objectives of this course are:
 To understand the basic principles of Artificial Intelligence.
 To learn and design intelligent agents.
 To understand the basic areas of artificial intelligence including problem-solving, knowledge
representation, reasoning, and expert systems.

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 Apply basic principles of AI for inference, perception, problem-solving, and K2
knowledge representation.
2 Design and develop systems that process data automatically using AI K2/K4
framework and patterns.
3 Apply real-life problems in a state space representation to solve using state K4/K5
space representation.
4 Formulate valid solutions for the problems involved. K4
5 Understand the fundamental principles of expert systems, and their K1 /K2
applications and understand the other methods of programming.

K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 – Create

Unit:1 10 hours
AI problems, the foundation of AI and history of AI intelligent agents: Agents and Environments, the
concept of rationality, the nature of environments, structure of agents, problem solving agents, problem
formulation.
Unit:2 12 hours
Searching- Searching for solutions, uniformed search strategies – Breadth-first search, depth-first
Search. Search with partial information (Heuristic search) Hill climbing, A*, AO* Algorithms, Problem
reduction, Game Playing - Adversial search, Games, mini-max algorithm, optimal decisions in
multiplayer games, Problem in Game playing, Alpha-Beta pruning, Evaluation functions.
Unit:3 15 hours
Knowledge representation issues, predicate logic- logic programming, semantic nets- frames and
inheritance, constraint propagation, representing knowledge using rules, rules based deduction systems.
Reasoning under uncertainty, review of probability, Baye’s probabilistic interferences and
dempstershafer theory.
Unit:4 11 hours
First order logic. Inference in first order logic, propositional vs. first order inference, unification & lifts
forward chaining, Backward chaining, Resolution, Learning from observation Inductive learning,
Decision trees, Explanation based learning, Statistical Learning methods, Reinforcement Learning.
12
Unit:5 10 hours
Expert Systems: Introduction – Advantages – General concepts – Characteristics – Development of
experts system technology – Expert system application and domains – Elements of expert systems –
Production Systems – Procedural paradigms – Non procedural paradigms.
Unit:6 2 hours
Discussion on case study - Expert lectures - Online seminars – Webinars - Workshops
Total Lecture hours 60 hours
Text Books
1 S. Russel and P. Norvig, “Artificial Intelligence – A Modern Approach”, Prentice Hall, 2022.
Reference Books
1 J. Nilsson, “Artificial Intelligence: A new Synthesis”, Elsevier Publishers,1998.
2 David Poole, Alan Mackworth, Randy Goebel, ”Computational Intelligence: a logical approach”,
Oxford University Press, 1998.
3 G. Luger, “Artificial Intelligence: Structures and Strategies for Complex Problem Solving”, Sixth
Edition, Pearson Education.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.sci.brooklyn.cuny.edu/~dzhu/cis718/preview01.pdf
2 https://onlinecourses.nptel.ac.in/noc21_ge20/
Course Designed by: Dr. P. B. Pankajavalli

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S M M L S L M M M
CO2 M S S M L M L S S S
CO3 S S S S M M L S S S
CO4 S S S S M M L M S M
CO5 S M M S M M L M S S

*S-Strong; M-Medium; L-Low

13
 MACHINE LEARNING AND ITS
Course Code 24AI1C4 L T P C
APPLICATIONS
Core/Elective/Supportive CORE 2 0 4 4
Foundation in Mathematics and Syllabus
Pre-requisite 2024-2025
Programming Skills Version
Course Objectives:
• To provide insight into fundamental concepts of machine learning and its various algorithms
• To understand various plans for generating models from data and evaluating them
• To apply ML algorithms on given data and elucidate the results obtained
• To design suitable ML solutions to solve real-world problems in the AI domain
•
Expected Course Outcomes:
Understand fundamental concepts and principles of machine learning
1 K1/K2/K3
algorithm scenarios.
2 Apply various machine learning to real world datasets K2/K5
Evaluate and find out suitable machine learning models based on dataset
3 K2/K5
characteristics.
Design and execute machine learning experiments to solve complex
4 K6
problems.
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 – Create

Introduction to Machine Learning: Fundamentals and

Unit 1 Discriminative Models 9 hours
Introduction: Machine learning, Terminologies in machine learning, Types of machine learning:
supervised, unsupervised, semi-supervised learning. Design of ML system – Model selection, bias,
variance, learning curves, and error analysis.
Unit 2 Improving Models and Learning Theory 12 hours
Review of probability. Discriminative Models: Least Square Regression, Gradient Descent
Algorithm, Univariate and Multivariate Linear Regression, Prediction Model, probabilistic
interpretation, Regularization, Logistic regression, multi-class classification, Support Vector
Machines- Large margin classifiers, Nonlinear SVM, kernel functions, SMO algorithm.
Unit 3 Gaussian Models and EM Algorithm 11 hours
Computational Learning theory- Sample complexity, ε- exhausted version space, PAC Learning,
agnostic learner, VC dimensions, Sample complexity - Mistake bounds. Gaussian models:
Multivariate Gaussian distributions, Maximum Likelihood Estimate, Inferring parameters, Linear
and Quadratic Discriminant Analysis, Mixture models, EM algorithm for clustering and learning
with latent variables.
Unit 4 Models and Unsupervised Learning Algorithms 12 hours
Generative models: k-Nearest Neighbor Classification, Bayesian concept learning, Likelihood,
Posterior predictive distribution, beta-binomial model, Naive Bayes classifiers, classifying
documents using bag of words. Bayesian Statistics and Frequentist statistics. Directed graphical
models (Bayes nets), Conditional independence, Inference. Dimensionality Reduction, Combining
weak learners- AdaBoost.
Unit 5 Singular Value Decomposition and Clustering 14 hours
Recommendation Systems – Model for Recommendation Systems, Utility Matrix, Content Based
Recommendations, Discovering Features of Documents, Collaborative Filtering. Advertising on
14
the Web: Issues in Online Advertising, Online and offline algorithms, The matching Problem, The
AdWords Problem, The Balance Algorithm, A Lower Bound on Competitive Ratio for Balance.
Total Lecture hours 58 hours
Text Book(s)
Tom Mitchell, “Machine Learning”, McGraw Hill-First edition,1997, Prentice Hall of
1
India Private Limited. Third Edition 2009.
2 E. Alpaydin, “Introduction to Machine Learning”, PHI- First edition,2005-2014.
Andrew Ng, Machine learning yearning, https://www.deeplearning.ai/machine-learning-
3
yearning/
AnandRajaRaman, Jure Leskovec and J.D. Ullman, “Mining of Massive Data sets”, e-
4
book, Publisher, Second edition-2014.
Kevin P. Murphey, “Machine Learning, a Probabilistic Perspective”, The MIT Press,
5
Cambridge, Massachusetts, First edition-2012.
Reference Books
AurolienGeron, ”Hands-On Machine Learning with Scikit-Learn and Tensor Flow,
1
Shroff/O’Reilly”-Second edition, 2017
Andreas Muller and Sarah Guido, ”Introduction to Machine Learning with Python: A
2
Guide for Data Scientists”, Shroff/O’Reilly,-First edition,2016
Alejandro Barredo Arrieta, Natalia D´ıaz-Rodr´ıguez, Javier Del Ser, et.al.,” Explainable
Artificial Intelligence (XAI): Concepts, taxonomies, opportunities, and challenges toward
3
responsible AI, Information Fusion”, Volume 58, 2020, Pages 82-115, ISSN 1566-2535,
https://doi.org/10.1016/j.inffus.2019.12.012.- Volume 58,2019.
Course Designed by: Dr. D. RAMYACHITRA

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M L L L M M M L M
CO2 L S S L M M L L M M
CO3 L L S M M L L M M L
CO4 S S M M L M L M M M

*S-Strong; M-Medium; L-Low

15
 MACHINE LEARNING AND ITS APPLICATIONS – LAB

List of Programs

1. K-nearest neighbors’ classification

2. Linear regression
3. Naïve Bayes theorem for classification of English text
4. Support Vector Machine algorithm
5. Calculation of the VC dimension of a set of hypotheses.
6. Multivariate Gaussian distribution.
7. AdaBoost algorithm for binary classification problem.
8. Implementation of Bayesian and frequent approaches for estimating the mean of a
Gaussian distribution.
9. Implementation of matrix factorization for collaborative filtering using Singular Value
Decomposition.

16
 Course Code L T P C
24AI1C5 FOUNDATIONS OF DATA SCIENCE
Core/Elective/Supportive CORE 4 0 0 4
Pre-requisite FOUNDATION IN MATHEMATICS AND Syllabus 2024-2025
PROGRAMMING SKILLS Version
Course Objectives:
• To provide a solid understanding of core principles and techniques in data science.
• To learn how to collect, preprocess, analyze, and visualize data using Python and relevant libraries.
• To gain proficiency in statistical methods and machine learning algorithms.
• To develop skills to extract insights and build predictive models.
• To learn the inference and classification model and also graph based models.
Expected Course Outcomes:
1 Understand and master fundamental data science concepts. K1/K2/K3
2 Proficiency in data sampling, distributions and correlations of features in samples. K2/K3/K5
3 Understand and apply the hypothesis testing and assessing the models. K2/K3/K5
4 Understand and apply the resampling and regression techniques for prediction in data K2/K3/K6
analysis.
5 Understand the classification models and apply these into different domain to making K2/K3/K6
decisions.
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 – Create
Unit 1 Foundations of Data Science: Exploring Causality, Pre-processing, Visualization, 11 hours
and Probability
Introduction to Data Science, Causality and Experiments, Data Pre-processing - Data cleaning – Data reduction - Data
transformation, Visualization and Graphing: Visualizing Categorical Distributions -Visualizing Numerical Distributions -
Overlaid Graphs and plots - Summary statistics of exploratory data analysis, Randomness, Probability

Unit 2 Statistical Fundamentals: Sampling, Distributions, Inference, and Testing 12 hours

Introduction to Statistics, Sampling, Sample Means and Sample Sizes. Probability distributions and density functions
(univariate and multivariate), Error Probabilities, Expectations and moments; Covariance and correlation; Sampling and
Empirical distributions; Permutation Testing, Statistical Inference
Unit 3 Advanced Statistical Analysis: Hypothesis Testing, Model Assessment, and 11 hours
Causality
Hypothesis testing of means, proportions, variances and correlations - Assessing Models - Decisions and Uncertainty,
Comparing Samples - A/B Testing, PValues, Causality.
Unit 4 Estimation and Prediction in Data Analysis: Resampling, Regression and 12 hours
Confidence
Estimation - Resampling and Bootstrap - Confidence Intervals, Properties of Mean - Central Limit Theorem -Variability of
mean -Choosing Sample Size, Prediction - Regression - Method of Least Squares - Visual and Numerical Diagnostics
Unit 5 Advanced Data Analysis Techniques: Inference, Classification, and Bayesian 14 hours
Methods
Inference for true slope - Prediction intervals, Classification - Nearest neighbours - accuracy of a classifier, Updating
Predictions - Making Decisions – Bayes Theorem, Graphical Models
Total Lecture hours 60 hours
Text Book(s)
17
 1 Peter Bruce, Andrew Bruce and Peter Gedeck, ”Practical Statistics for Data Scientists: 50+Essential
Concepts Using R and Python”, 2/e, O’Reilly Media, 2020.
Hall of India Private Limited. Third Edition 2009.
2 Joel Grus, ”Data Science from Scratch: First Principles with Python”, 2/e, O’Reilly Media,2019.
Reference Books
1 Allen B. Downey, Think Stats: Probability and Statistics for Programmers”, 2/e, by O’Reilly Media,
2014.
2 Cathy O’Neil and Rachel Schutt,”Doing Data Science”, O’Reilly Media, 2013.
3 Ani Adhikari and John DeNero, ”Computational and Inferential Thinking: The Foundations of Data
Science”, e-book.2022
Course Designed By: Dr.R.PORKODI

Mapping with programme outcomes:

COS PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S M S S S M M M M
CO2 S S M S S S M M M M
CO3 S S M S S S M M M M
CO4 S S M S S S M M M M
CO5 S S M M S S M L M M
S- Strong; M-Medium; L-Low

18
SEMESTER - II

19
Course code 24AI2C1 COMPUTATIONAL INTELLIGENCE L T P C
Core/Elective/Supportive CORE 4 0 0 4
Syllabus
Pre-requisite Basic knowledge of handling digital data 2024-2025
Version
Course Objectives:
The main objectives of this course are to:
 To provide a strong foundation on fundamental concepts in Computational Intelligence.
 To enable Problem-solving through various approaches using neural networks, fuzzy and
evolutionary algorithms
 To apply Computational Intelligence techniques using nature-inspired algorithms

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
To understand the fundamentals of Computational Intelligence, models, and its K1/K2
1
applications
2 To know about Generative AI K1/K2
3 To understand Prompt Engineering and its applications K1/K2
To Provide a basic exposition of the goals and methods of Computational K1/K2/
4 K4
Intelligence using different types of neural networks
5 To get familiarity with evolutionary algorithms K2/K3/K4
K1/K2/
6 To apply Intelligent techniques using fuzzy logic
K4/K5
7 To know about optimization using swarm intelligence K2/K3/K4
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 11 hours
Introduction to Computational Intelligence- Definition and Scope of Computational Intelligence-
Applications in Various Field-Basic Concepts: Optimization, Learning, Adaptation - Soft Computing vs.
Hard Computing-Computational Intelligence vs. Classical Techniques vs. Artificial Intelligence - Future
Trends and Directions – Traditional AI vs. Generative AI - Generative AI: overview of generative
models and its applications - Language models LLM architecture -Understanding GPT - Introduction to
Prompt Engineering: Types - application - text and image prompts

Unit:2 11 hours
Neural Networks: Introduction to Artificial Neural Networks (ANN)-Neuron Models and Activation
Functions - Single-Layer Perceptrons (SLP)-Multilayer Perceptrons (MLP) and Feedforward Networks -
Backpropagation Algorithm - Convolutional Neural Networks (CNN) - Recurrent Neural Networks
(RNN) and Long Short-Term Memory (LSTM)-Self-Organizing Maps (SOM)- Unsupervised Learning
with Neural Networks-Applications: Image Recognition, Natural Language Processing

Unit:3 12 hours
Evolutionary Algorithms: Introduction to Evolutionary Algorithms (EA)-Genetic Algorithms (GA):
Basic Concepts and Operators-Evolution Strategies (ES) and Evolutionary Programming (EP)-Genetic
Programming (GP)-Differential Evolution (DE)-Multi-Objective Optimization using Evolutionary
20
Algorithms-Co-evolutionary Algorithms- Parallel and Distributed Evolutionary Algorithms- Real-World
Applications: Engineering Design, Robotics-Comparison with Classical Optimization Techniques

Unit:4 12 hours
Fuzzy Logic: Introduction to Fuzzy Logic- Fuzzy Sets and Membership Functions-Fuzzy Operators:
AND, OR, NOT-Fuzzy Rules and Fuzzy Inference Systems (FIS)-Mamdani and Sugeno Fuzzy Inference
Methods-Fuzzy Control Systems: PID Controllers vs. Fuzzy Controllers-Fuzzy Logic Applications in
Control Engineering-Fuzzy Decision Making and Expert Systems- Fuzzy Clustering and Pattern
Recognition- Fuzzy Logic in Medical Diagnosis and Healthcare

Unit:5 12 hours
Swarm Intelligence: Introduction to Swarm Intelligence- Ant Colony Optimization (ACO)-Particle
Swarm Optimization (PSO)- Bee Colony Optimization (BCO)-Firefly Algorithm-Artificial Bee Colony
Algorithm (ABC)-Grey Wolf Optimizer (GWO)-Differential Evolution Swarm (DES)-Applications in
Engineering Design Optimization-Emerging Trends and Hybrid Approaches

Unit:6 Contemporary Issues 2 hours

Expert lectures, online seminars - webinars
Total Lecture hours 60 hours
Text Book(s)
1 Computational Intelligence: Concepts to Implementations, Russell C. Eberhart and Yuhui Shi
2 Neural Networks and Deep Learning: A Textbook, Charu C. Aggarwal
3 Evolutionary Algorithms in Theory and Practice, Thomas Bäck
4 Fuzzy Logic with Engineering Applications, Timothy J. Ross
5 Swarm Intelligence, Russell C. Eberhart, Yuhui Shi, and James Kennedy

Reference Books
1 Konar A., “Computational Intelligence: Principles, Techniques and Applications”, Springer Verlag,
2005
2 Engelbrecht, A.P, “Fundamentals of Computational Swarm Intelligence”, John Wiley & Sons, 2006.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.larksuite.com/en_us/topics/ai-glossary/computational-intelligence
2 https://www.tutorialspoint.com/prompt_engineering/index.htm

Course Designed by: Dr. K. Geetha

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S S M M L M M S S
CO2 S S S M M L M M S S
CO3 S S S M M L M M S S
CO4 S S S M M L M M S S
CO5 S S S M M L M M S S
CO6 S S S M M L M M S S
CO7 S S S M M L M M S S

*S-Strong; M-Medium; L-Low

21
 Course code 24AI2C2 DEEP LEARNING TECHNIQUES L T P C
Core/Elective/Supportive CORE 2 0 4 4
Basic knowledge of mathematics, statistics, and Syllabus 2024-
Prerequisite machine learning concepts Version 2025
Course Objectives:
The main objectives of this course are to:
• Understand the principles of neural networks
• Understand the basic concepts of deep learning
• Understand and implement the architectures of deep learning.
• Familiarize with the applications of deep learning

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
Understand the deep learning concepts and apply them to different
1 K2/K3
problems
2 Design and apply Convolutional and Recurrent Neural Networks K1/K3
3 Understand and evaluate different deep learning architectures K2/K5
4 Design and create deep learning applications K6
5 Analyze the role of deep learning models in image processing K4
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 BASICS OF NEURAL NETWORKS 9 hours

Basics of neural networks - Basic concept of Neurons – Perceptron Algorithm – Feed Forward
and Back Propagation Networks.

Unit: 2 INTRODUCTION TO DEEP LEARNING 12 hours

Introduction to deep learning - Feed Forward Neural Networks – Gradient Descent – Back
Propagation Algorithm – Vanishing Gradient problem – Mitigation – ReLU Heuristics for
Avoiding Bad Local Minima– Heuristics for Faster Training – Nestors Accelerated Gradient
Descent – Regularization – Dropout.

Unit:3 CONVOLUTIONAL & RECURRENT NEURAL NETWORK 11 hours

Convolutional neural networks - Kernel Filters – Multiple Filters - CNN Architectures –
Convolution – Pooling Layers – Transfer Learning – Image Classification using Transfer
Learning - Introduction to RNNs, Unfolded RNNs, Seq2Seq RNNs, LSTM, RNN applications

Unit:4 DEEP LEARNING ARCHITECTURES 12 hours

LSTM, GRU, Encoder/Decoder Architectures – Autoencoders – Standard- Sparse – Denoising
– Contractive- Variational Autoencoders – Adversarial Generative Networks – Autoencoder
and DBM

Unit:5 APPLICATIONS OF DEEP LEARNING 14 hours

Applications of deep learning - Image Segmentation – Object Detection – Automatic Image
Captioning – Image Generation with Generative Adversarial Networks – Video to Text with
LSTM Models – Attention Models for Computer Vision

Unit:6 Contemporary Issues 2 hours

Expert lectures, online seminars - webinars
Total Lecture hours 60

Text Book(s)
1 Ian Good Fellow, Yoshua Bengio, Aaron 22 Courville, “Deep Learning”, MIT Press, 2017.
2 Goodfellow, I., Bengio, Y., and Courville, A., Deep Learning, MIT Press, 2016.

Reference Books
Mapping with Programme Outcomes
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S S M M M M M M M
CO2 S S S M M M M M M M
CO3 S S S M M M M M L S
CO4 M S M S M M L M L M
CO5 S S S L L M M M L M

*S-Strong; M-Medium; L-Low

DEEP LEARNING TECHNIQUES - LAB

List of Programs

1. Implementation of feed-forward neural network

2. Implementation of convolutional network
3. Image classification
4. Image segmentation
5. Time series forecasting
6. Text classification and machine translation
7. Text generation
8. Image classification

23
 Course Code 24AI2C3 DATA ENGINEERING L T P C
Core/Elective/Supportive CORE 2 0 4 4

Pre-requisite CONCEPTS OF FEATURE ENGINEERING, Syllabus 2024-2025

MODEL DEVELOPMENT MONITORING Version
Course Objectives:
 To understand the ‘X’ of data engineering
 To scan proficiency in data manipulation and transformation technology techniques using SQL,
python, and Spark tools.
 To learn how to design and implement efficient data pipelines for collectivity processing and
storing lay volumes of data

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 Understand the principles of data modeling and management. K2/K3
2 Gain proficiency in data storage technology and data engineering tools and K1/K3
platforms such as NoSQL, Postgre SQL, Apache Cassandra, Prest, Spark,
Python
3 Learn how to design and implement scalable data pipelines for processing K2/K5
large volumes of data

24
 K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 - Create
Unit 1 Data Modelling and Management 11 hours

Data modeling, relational data models, ER models – Graph models - Normalization and de-
normalization, OLTP and OLAP - Big data – Data Science – Processing big data – Languages – SQL,
Cypher

Unit 2 Database Management Essentials 12 hours

Embedded SQL, Constraints – Data Consistency – Query optimization – Object-oriented databases-
NoSQL data models – schema migrations - PostgreSQL, Apache Cassandra, Presto

Unit 3 Spark for Data Lakes and Python Programming 11 hours

Spark and data lakes: Python programming in Spark; Data wrangling – Sparkql, spark data frames-
SparkSQL, ETL in Spark, SparkMlLib, Comparison of Pyspark with H2O, Dask, and Vaex
Unit 4 Data Pipeline Management and Optimization 12 hours
Data Pipeline – Apache Airflow - Set up task dependencies- Create data connections using hooks-
Track data lineage - Set up data pipeline schedules - Partition data to optimize pipelines
Unit 5 Data Quality Assurance and Pipeline Management 14 hours
Write tests to ensure data quality - Backfill data - Build reusable and maintainable pipelines –
Implement subDAGs - Set up task boundaries - Monitor data pipelines
Total Lecture hours 60 hours
Text Book(s)
1 Database System Concepts, Abraham Silberschatz, Henry F. Korth, S. Sudarshan, McGraw-
Hill Education, Sixth edition-2011
2 NoSQL Distilled: Pramod J. Sadalage, Martin Fowler, Addison-Wesley, Second edition -
3 20122014.
Learning Spark: Lightning-Fast Big Data Analysis, Holden Karau, Andy Konwinski, Patrick
Wendell, MateiZaharia, O’Reilly Media, Inc., First edition-2015
Reference Books
1 Practical Machine Learning with H2O: Powerful, Scalable Techniques for Deep Learning and
AI, Darren Cook, O’Reilly Media, Inc., First edition-2016
2 Learning PySpark, Tomasz Drabas, Denny Lee, Packt, First edition-2017
3 https://medium.com/plotly/interactive-and-scalable-dashboards-with-vaex-and-dash-
9b104b2dc9f0
Course Designed By: Dr. D. RAMYACHITRA

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M M L L M L M L M
CO2 L S L L M M L L M M
CO3 L S M L M L L ML L M

*S-Strong; M-Medium; L-Low

25
 DATA ENGINEERING - LAB

List of Programs

1. Create an Entity-Relationship (ER) model for a given business scenario.

2. Convert the ER model into a relational schema and implement it using PostgreSQL.
3. Write complex SQL queries to retrieve data from a relational database. Include joins,
subqueries, and aggregate functions.
4. Set up an Apache Cassandra database and create a schema for a sample application.
5. Set up a Spark environment and perform basic data manipulation using Spark DataFrames.
6. Install and configure Apache Airflow.
7. Create and schedule a simple DAG (Directed Acyclic Graph) to perform a data processing
task.

26
Course
24AI2C4 PROBABILISTIC GRAPHICAL MODELS L T P C
Code
Core/Elective/Supportive CORE 4 0 0 4
Pre-Requisite Syllabus 2024-
Mathematics, Discrete Structure
Version 2025
Course Objective:
The main objectives of this course are:
 To give a comprehensive introduction to probabilistic graphical Models
 To make inferences, learning, actions, and decisions while applying these models.
 To introduce real-world trade-offs when using probabilistic graphical models in practice
 To develop the knowledge and skills necessary to apply these models to solve real-world
problems.

Expected Course Outcomes:

On the successful completion of the course, students will able to:
K1/K2
1 Understand basic concepts of probabilistic graphical modeling
Model and extract inference from various graphical models like Bayesian K2/K4
2
Networks, Markov Models
Perform Learning and take actions and decisions using probabilistic graphical K2/K4
3
models

27
 Represent real-world problems using graphical models: design inference K2/K4
4
algorithms: and learn the structure of the graphical model from data.
K2/K3/K6
5 Design real-life applications using probabilistic graphical models
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit: 1 INTRODUCTION TO PROBABILISTIC GRAPHICAL MODELING 12 Hours

Introduction to Probability Theory: Probability theory, basic concepts in probability, random
variables and joint distribution, independence and conditional independence, continuous spaces,
expectation, and variances. Introduction to Graphics: Nodes and edges, Subgraphs, Paths and Trails,
Cycle and Loops. Introduction to Probabilistic Graph Models: Bayesian Network, Markov Model,
Hidden Markov Model. Application of PGM

Unit: 2 Bayesian Network Model and Inference 12 Hours

Directed Graph Model: Bayesian Network- Exploiting Independence properties, Naïve Bayes Model,
Bayesian Network Model, Reasoning Patterns, Basic Independences in Bayesian Networks, Bayesian
Network Semantics, Graphs and Distribution, Modelling: Picking variables, picking Structure, Picking
Probabilities, D-separation. Local Probabilistic Models: Tabular CPDs, Deterministic CPDs, Context-
Specific CPDs, Generalized Linear Models. Exact inference variable elimination: analysis of
complexity, variable elimination, conditioning, inference with Structured CPDs.

Unit: 3 MARKOV NETWORK MODEL AND INFERENCE 12 Hours

Undirected Graph Model: Markov Model-Markov Network, Parameterization of Markov network,
Gibbi’s distribution, Reduced Markov Network, Markov Network Independencies, From Distributions
to Graph, Fine-Grained Parameterization, Over Parameterization. Exact inference variable elimination:
Graph Theoretic Analysis for Variable Elimination, Conditioning

Unit: 4 Hidden Markov model and inference 11 Hours

Template-Based Graph Model: HMM- Temporal Models, Template Variables and Template Factors,
Directed Probabilistic Models, Undirected Representation, Structural Uncertainty

Unit: 5 Learning and Taking Actions and Decisions 11 Hours

Learning Graphical Models: Goals of Learning, Density Estimation, Specific prediction tasks,
knowledge discovery. Learning as Optimization: Empirical risk, over fitting, Generalization,
Evaluating Generalization performance, selecting a learning procedure, goodness of Fit, Learning tasks,
Parameter Estimation: Maximum Like hood Estimation, MLE for Bayesian Networks. Causality:
Conditioning and Intervention, Correlation and Causation, Causal Models, Structural causal Models.
Utilities and Decisions: Maximizing Expected Utility, Utility curves, Utility Elicitation. Structured
Decision problems: Decision Tree

Unit: 6 CONTEMPORARY ISSUES 2 Hours

Discussion on case study - Expert lectures - Online seminars – Webinars – Workshops
Total Lectures 60 Hours
Text Books
Daphne koller and Nir Friedman, “ Probabilistic Graphical Models: Principles amd
1
Techniques”
David Barber, : Bayesian Reasoning and Machine Learning”, Cambridge University Prss, 1 st
2
edition, 2011.
Reference Books
28
 Finn Jensen and Thomas Nielsen, “ Bayesian Networks and Decision Graphs( Information
1
Science and Statistics)”, 2nd edition, springer, 2007.
2 Kevin P. Murphy, “ Machine Learning: A probabilistic Perspective”, MIT Press, 2012.
Martin Wainwright and Michael Jordan, M., “ Graphical Models, Exponential Families, and
3
Variational Inference”, 2008.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

https://www.coursera.org/specializations/probabilistic-graphical-models
1
2 https://www.mooc-list.com/tags/probabilistic-graphical-models
3 https://www.upgrad.com/blog/bayesian-networks/
4 https://link.springer.com/chapter/10.1007/978-3-319-43742-2_24
5 https://core.ac.uk/download/pdf/191938826.pdf
6 https://cs.brown.edu/research/pubs/these/ugrad/2005/dbooks.pdf
Course Designed BY:

Mapping with programme outcomes:

COS PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S S M M M M M M M
CO2 S S S M M M M M M M
CO3 S S S M M M M M L S
CO4 M S M S M M L M L M
CO5 S S S L L M M M L M
S- Strong; M- Medium; L-Low

29
Course code 24AI2C5 CLOUD AND BIG DATA ANALYTICS L T P C
Core/Elective/Supportive CORE 2 0 4 4
Fundamentals of Database Management, Syllabus 2024-
Prerequisite Data Mining, and System Software Version 2025
Course Objectives:
The main objectives of this course are:
• To explain the concepts and terminologies related to Big Data and Cloud Computing.
• To describe the challenges with Big Data analysis and techniques used to perform Big Data
analysis in the Cloud.
• To describe different types of cloud platforms and their advantages and disadvantages for Big
Data analysis
• To use a cloud-based platform to store, update, and manage Big Data and Create data-
driven models for Big Data analysis based on existing frameworks.
• To Apply data-driven models by deploying them to the Cloud.
Expected Course Outcomes:
On the successful completion of the course, students will be able to:
Understand the basic concepts of cloud computing and its
1 K2/K3
technologies and applications.
Analyze the need and use of different cloud platforms and
2 K3/K4
services.
3 Understand the concepts and terminologies of big data analytics. K2/K5
4 Understand and analyze the use of Hadoop and MapReduce. K2/K4/K5
Analyze and apply the concepts of cloud and big data analytics
5 K4/K5/K6
to solve real-time problems
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 INTRODUCTION TO CLOUD COMPUTING 12 hours

Introduction – Characteristics – Cloud Models – Cloud Services Examples – Cloud-based
Services & Applications. Cloud Concepts & Technologies: Virtualization – Load Balancing –
Scalability & Elasticity – Deployment – Replication – Monitoring – Software Defined
Networking – Network Function Virtualization

Unit:2 CLOUD SERVICES & PLATFORMS 12 hours

Cloud Platforms - Computational Services – Storage Services – Database Services –
Application Services – Content Delivery Services – Analytics Services –Deployment &
Management Services –Identity & Access Management Services – Open Source Private Cloud
Software.

Unit:3 INTRODUCTION TO BIG DATA ANALYTICS 10 hours

Introduction - Big Data - Scalability and Parallel Processing - Designing Data Architecture -
Data Sources, Quality, Pre-Processing and Storing - Data Storage and Analysis

Unit:4 HADOOP & MapReduce 12 hours

Introduction to Hadoop and its Ecosystem - Hadoop Distributed File System - MapReduce
Framework and Programming Model - Hadoop Yarn - Hadoop Ecosystem Tools.
MapReduce: Introduction - MapReduce Map Tasks, Reduce Tasks and MapReduce
Execution - Composing MapReduce for Calculations and Algorithms

Unit:5 CASE STUDY 12 hours

Real-world Case studies – Web Analytics, Web-scrapping, Google Analytics, Social medial
Analytics, Issues in integrating Big data with30Clouds- security concerns and measures to handle
them - Big Data in Marketing and Sales - Data and Healthcare - Big Data in Medicine - Big
Data in Advertising
 Mapping with Programme Outcomes
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 M S S L M M M M L S
CO2 M M S L M M M S L S
CO3 S S S L M M M M L M
CO4 M S S L M M M M M S
CO5 M S M M M M M S L S

*S-Strong; M-Medium; L-Low

CLOUD AND BIG DATA ANALYTICS - LAB

List of Programs

1. Install Virtual box/VMware Workstation with different Linux or Windows OS flavors on

top of Windows or 8.
2. Install a C compiler in the virtual machine created using a virtual box and execute Simple
Programs.
3. Find a procedure to transfer the files from one virtual machine to another virtual machine.

4. Simulate a cloud scenario using CloudSim and run a scheduling algorithm that is not
present in CloudSim
5. Installing Hadoop; Understanding different Hadoop modes. Startup scripts, Configuration
files.
6. Hadoop Implementation of file management tasks, such as adding files and directories,
retrieving files, and deleting files.
7. Run a basic Word Count Map Reduce program to understand the Map Reduce Paradigm.
8. Experiment on Hadoop Map-Reduce / PySpark: -Implementing simple algorithms in
Map-Reduce: Matrix multiplication.
9. Implement an application that stores big data in MongoDB / Pig using Hadoop / R.
10. Install Google App Engine. Create hello world app and other simple web applications
using Python/java
11. Working and installation of Microsoft Azure, Study Amazon EC2/Microsoft
Azure/Google Cloud Platform
12. Implementing basic AI pipelines using PyTorch or TensorFlow.

31
SEMESTER - III

32
 INTRODUCTION TO SPEECH
Course code 24AI3C1 L T P C
PROCESSING

Core/Elective/Supportive CORE 4 0 4
Syllabus 2024-
Pre-requisite Basic knowledge of Digital Data
Version 2025
Course Objectives:
The main objectives of this course are to:
 To introduce the fundamentals of speech signal processing.
 To acquire the fundamentals of the digital signal processing that allows them to assimilate the
concepts related to the speech processing.
 To present basic principles of speech analysis and construction of models.
 To give an overview of speech processing applications including speech synthesis, speech
recognition and speaker recognition.

Expected Course Outcomes:

On the successful completion of the course, student will be able to:
1 To understand fundamental of speech processing and its applications K1/K2
K1/K2/
2 To know about representation of Speech in digital form
K4
3 To familiar with speech synthesis and models K2/K3/K4
To understand about Speech recognition, approaches, applications and K1/K2/
4
tools K4/K5
To know about applications of speech processing- speaker identification
5 K2/K3/K4
and verification
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 10 -- hours
Introduction to speech processing – History – Applications- Speech production: Mechanism of
speech production- Acoustic phonetics – Digital models for speech signals – Speech waveform
representations- Sampling speech signals- Basics of quantization

Unit:2 10-- hours

Short-time analysis of speech- Short-time energy and Zero crossing rate-Short-time auto
correlation method – Short-time Fourier Transform –Speech spectrogram- Homomorphic speech
analysis-Cepstrum and Complex Cepstrum-The short-time cepstrum - Computation of Cepstrum -
Mel Frequency Cepstrum Co-efficients - Linear predictive analysis.

Unit:3 8-- hours

Text to Speech Synthesis: Basic principles - Rule based speech synthesis - Corpus based peech
synthesis -Linguistic processing - Prosodic processing

Unit:4 13-- hours

Speech Recognition: Speech recognition architecture- Types of speech recognition-Issues in
speech recognition-Speech databases-Performance evaluation of SR systems-Applications -
Feature extraction methods- Speech recognition methodologies: Acoustic-phonetic approach
Pattern recognition approach: Template based approach-Dynamic Time Warping- Hidden Markov

33
Model-Vector Quantization – Support Vector Machine - Neural network based approaches.
Language Model- Trigram language model –CMU SLM Toolkit.

Unit:5 13-- hours

Speaker Identification and Verification: Measuring speaker features- Statistical Vs Dynamic
features - Cepstral analysis – Similarity Vs Distance measures - Constructing speaker models –
Adaptation - Applications of speaker recognition - Text dependent speaker recognition - Text
independent speaker recognition- Generative approaches: Rationale - Gaussian mixture model
(GMM)- Neural network approaches - Discriminative approaches: Support Vector Machine(SVM)
- Kernels.

Unit:6 Contemporary Issues 2 hours

Expert lectures, online seminars - webinars

Total Lecture hours 56-- hours

Text Book(s)
1 L. R. Rabiner, R. W. Schaffer, “Digital Processing of Speech signals”, Prentice Hall, 1978.
Jacob Benesty, M. Mohan Sondhi, Yiteng Huang “Springer handbook of speech Processing”,
2
Springer, 2007.
Douglas O’Shaughnessy, “Speech Communications: Human and Machine”, Wiley- IEEE
3
Press, 1999.
4 L.R. Rabiner, B. H. Juang, “Fundamentals of speech recognition”, Prentice Hall,1993.

Reference Books
Thomas F. Quatieri - Discrete Time Speech signal Processing principles and practice, Third
1
Edition, Pearson Education, 2009.
Dr.Shaila D.Apte - Speech and Audio Processing, First Edition, WILEY Precise Textbook,
2
2015.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

https://www.tutorialspoint.com/artificial_intelligence_with_python/
1
artificial_intelligence_with_python_speech_recognition.htm
2 https://www.javatpoint.com/speech-recognition-python

Course Designed By: Dr. K. Geetha

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 M S S S S M L M S S
CO2 M S S S S M L M S S
CO3 M S S S S M L M S S
CO4 M S S S S M L M S S
CO5 M S S S S M L M S S

*S-Strong; M-Medium; L-Low

34
 INTRODUCTION TO SPEECH PROCESSING – LAB

List of Programs

1. Record and digitize speech signals, and explore quantization effects.

2. Understand the concept of sampling and its impact on speech signals
3. Generate and interpret the spectrogram of speech signals
4. Extract MFCC features from speech signals.
5. Perform LPC analysis on speech signals.
6. Synthesize speech signals using different techniques.
7. Detect voiced and unvoiced regions in a speech signal.
8. Identify and analyze formants in speech signals.
9. Train a basic speech recognition model using a small dataset.
10. Create a practical application using speech recognition for voice commands.
11. Train a model to recognize different speakers.
12. Preprocess data for speaker identification
13. Train a model to identify speakers from a given set of audio samples.

35
Course Code 24AI3C2 NATURAL LANGUAGE L T P C
PROCESSING
Core/Elective/Supportive ELECTIVE 2 0 4 4
Pre-Requisite Fundamentals of finite automata, regular Syllabu 2024-
expressions and grammar structures. s 2025
Version
Course Objective:
The main objectives of this course are:
1. To understand algorithms for the processing of linguistic information and
computational properties of natural languages.
2. To conceive basic knowledge on various morphological, syntactic and semantic NLP
tasks.
3. To familiarize various NLP software libraries and data sets publicly available.
4. To develop systems for various NLP problems with moderate complexity.
5. To learn steps for creating Machine learning models and Gen AI

Expected Course Outcomes:

On the successful completion of the course, student will be able to:
1 Describe the concepts of morphology, syntax, semantics, discourse K1/K2
& pragmatics of natural language.
2 Demonstrate understanding of the relationship between NLP and K2/K4
statistics & machine learning.
3 Discover various linguistic and statistical features relevant to the K2/K4
basic NLP task and Demonstrate the concept of semantic analysis
and word sense disambiguation.
4 Understand and Demonstrate Generative AI capabilities in NLP. K2/K4/K6
5 Understand the components of machine translation process and K2/K3/K6
develop the model for NLP applications.
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 INTRODUCTION 10 hours

Introduction - NLP tasks in syntax, semantics, and pragmatics. Applications such as
information extraction, question answering, and machine translation. The problem of
ambiguity. The role of machine learning. Brief history of the field - N-gram Language Models
- The role of language models. Simple N- gram models. Estimating parameters and smoothing.
Evaluating language models.

Unit:2 BASIC NLP TECHNIQUES 12 hours

Part Of Speech Tagging and Sequence Labeling - Lexical syntax. Hidden Markov Models
(Forward and Viterbi algorithms and EM training) - Basic Neural Networks. Any basic
introduction to perceptron and back propagation.

Unit:3 PARSING & SEMANTIC ANALYSIS 13 hours

LSTM Recurrent Neural Networks -Syntactic parsing - Grammar formalisms and treebanks.
Efficient parsing for context-free grammars (CFGs). Statistical parsing and probabilistic CFGs
(PCFGs). Lexicalized PCFGs. Neural shift-reduce dependency parsing - Lexical semantics and
word-sense disambiguation. Compositional semantics. Semantic Role Labelling and Semantic
Parsing.

36
 Unit:4 GENERATIVE AI USES, APPLICATIONS AND TOOLS 12 hours

Introduction to Generative AI – Generative AI capabilities – Generative AI uses and

applications across industries – Generative text and speech models – Generative image models
– Generative AI models - Generative Adversarial Networks (GANs) - Variational auto
encoders (VAEs).

Unit:5 MACHINE TRANSLATION 13 hours

Information Extraction (IE) - Named entity recognition and relation extraction. IE using
sequence labelling. -Machine Translation (MT) Basic issues in MT. Statistical translation,
word alignment, phrase-based translation, and synchronous grammars.

Unit:6 Contemporary Issues 2 hours

Discussion on case study - Expert lectures - Online seminars – Webinars – Workshops
Total Lectures 62
Text Books
1 Jurafsky Dan and Martin James H. “Speech and Language Processing” ,3rd Edition,
2018.
Learn Python Generative AI: Journey from autoencoders to transformers to large
language models, Zonunfeli Ralte, Indrajit Kar, BPB Publications, 2024.
Reference Books
1 Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta, Harshit Surana, Practical
Natural Language Processing, 2020.
2 Steven Bird, Ewan Klein, Edward Loper, Natural Language Processing with
Python, 2009.
3 Joseph Babcock, Raghav Bali, Generative AI with Python and TensorFlow 2:
Create images, text, and music with VAEs, GANs, LSTMs, Transformer models,
Packt publishing, 2021.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://onlinecourses.nptel.ac.in/noc19_cs56/preview
2 https://www.edx.org/learn/natural-language-processing
3 https://www.coursera.org/specializations/natural-language-processing
4 https://www.tutorialspoint.com/natural_language_processing/index.htm
5 https://www.geeksforgeeks.org/generative-ai-models/
Course Designed By:Dr.R.Porkodi

Mapping with programme outcomes:

COS PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S M M M M M L M M
CO2 S S M M M M M L M M
CO3 S S M M M M M L M M
CO4 S S M M M M M L M M
CO5 S S M M M M M L M M
S- Strong; M-Medium; L-Low

37
List of Programs

1. Illustrate part of speech tagging.

a. POS tagging and chunking of user defined text.
b. Named Entity recognition of user defined text.
c. Named Entity recognition with diagram using NLTK corpus – Treebank.
2. Implement word Tokenizer, Sentence and Paragraph Tokenizers.
3. Write a program to implement TF-IDF for any corpus.
4. Implement the various stemmers such as PorterStemmer, LancasterStemmer,
RegexpStemmer, SnowballStemmer, WordNetLemmatizer, etc.
5. Write a program to implement both user-defined and pre-defined functions to generate
(a) Uni-grams (b) Bi-grams (c) Tri-grams (d) N-grams
6. Implement N‐gram Language model to classify the text into class labels.
7. Implement LSA and Topic model.
8. Implementation text classification using Naïve Bayes, SVM.
9. Implementation of K‐means Clustering algorithm on text.
10. Convert the given text to speech and speech to Text. Extract the important features from
it.

38
Course code 24AI3C3 REINFORCEMENT LEARNING L T P C
Core/Elective/Supportive CORE 2 0 4 4
Basic knowledge of Mathematics, Statistics,
Programming, Data Structures and Syllabus 2024-
Prerequisite Algorithms, Artificial Intelligence, and Version 2025
Machine Learning concepts
Course Objectives:
The main objectives of this course are:
• To acquire knowledge on the essentials of reinforcement learning and the methods used to
solve different types of complex tasks.
• To understand the basic concepts of reinforcement learning, multi-arm bandit problems, and
Markov decision processes.
• To analyze the use of dynamic programming and Monte Carlo methods.
• To provide the concepts of temporal-difference learning and the use of tabular methods for
planning and learning.

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
Understand the reinforcement learning concepts and multi-arm
1 K2/K3
bandit problems
2 Analyze the need and use of finite Markov decision processes. K3/K4
Understand the dynamic programming concepts, efficiency, and
3 K2/K5
their applications
Understand and analyze the Role of Monto Carlo methods in
4 K2/K4/K5
reinforcement learning
Analyze and apply the concepts of temporal-difference learning
5 K4/K5/K6
and the use of tabular methods for planning and learning
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 The Reinforcement Learning Problem 12 hours

Reinforcement Learning - Examples - Elements of Reinforcement Learning - Limitations and
Scope - An Extended Example: Tic-Tac-Toe - History of Reinforcement Learning. Multi-arm
Bandits: An n-Armed Bandit Problem - Action-Value Methods - Incremental Implementation -
Tracking a Nonstationary Problem - Gradient Bandits - Associative Search (Contextual
Bandits).

Unit:2 Finite Markov Decision Processes 12 hours

The Agent-Environment Interface - Goals and Rewards - Returns - Unified Notation for
Episodic and Continuing Tasks - The Markov Property - Markov Decision Processes -
Value Functions - Optimal Value Functions - Optimality and Approximation.

Unit:3 Dynamic Programming 10 hours

Policy Evaluation - Policy Improvement - Policy Iteration - Value Iteration - Asynchronous
Dynamic Programming - Efficiency of Dynamic Programming.

Unit:4 Monte Carlo Methods 12 hours

Monte Carlo Methods: Monte Carlo Prediction - Monte Carlo Estimation of Action Values -
Monte Carlo Control - Monte Carlo Control without Exploring Starts - Off-policy Prediction
via Importance Sampling - Incremental Implementation – Off-Policy Monte Carlo Control -
Importance Sampling on Truncated Returns.

Unit:5 Temporal-Difference Learning 12 hours

39
TD Prediction - Advantages of TD Prediction Methods - Optimality of TD (0) - Sarsa: On-
Policy TD Control - Q-Learning: Off-Policy TD Control - Games, Afterstates, and Other
Special Cases. Planning and Learning with Tabular Methods: Models and Planning -
Integrating Planning, Acting, and Learning - When the Model Is Wrong - Prioritized Sweeping
 Mapping with Programme Outcomes
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S S L M M M M L M
CO2 S S S M M M M M L S
CO3 S S S M M M M M L M
CO4 M S S L M M M M S M
CO5 S M S M M M M M M M

REINFORCEMENT LEARNING - LAB

List of Programs

1. Q-Learning agent to play Tic-Tac-Toe.

2. N-armed bandit problem with ε-greedy strategy.
3. Markovian Decision Process
4. Markov Chain for simple prediction
5. Basic MDP solver using Value Iteration.
6. Monte Carlo methods for prediction and control.
7. TD (0) and Q-Learning algorithms for simple environments
8. Policy evaluation for a given policy.
9. SARSA algorithm
10. A small GRID game with reinforcement learning

40
 Course Code 24AI3C4 MULTI-AGENT SYSTEMS L T P C
Core/Elective/Supportive CORE 2 0 4 4
PROGRAMMING SKILLS , ARTIFICIAL
Syllabus 2024 -
Pre-requisite INTELLIGENCE BASICS AND
Version 2025
DISTRIBUTED SYSTEMS
Course Objectives:
 To understand fundamental concepts of multi agent system
 To learn various techniques for agent design and in plots
 To study practical applications
Expected Course Outcomes:

On the successful completion of the course, students will be able to:

Provide insight into fundamental concepts of agents and their various
1 K2/K3
algorithms.
2 Understand various strategies of problem-solving and learning K1/K3
3 Apply ML algorithms on given data and interpret the results obtained K2/K5
4 Design and apply the agents in various domains K6
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 - Create

Unit 1 Fundamentals of Data Management and Analysis 9 hours

Intelligent Agents - Abstract architectures for Intelligent agents - Concrete architectures for Intel-
ligent agents - Agent communications - Agent interaction protocols - Societies of Agents - Search
algorithms for agents - Constraint satisfaction problems - Path-Finding Problem Sieve for primes,
Modular exponentiation
Unit 2 Intelligent Agents and Search Algorithms Systems 12 hours
Distributed Problem-solving and Planning - Task and Result sharing - Planning representations and
execution - Learning in Multi-agent systems - Interactive Reinforcement Learning of coordination -
Learning and communication
Unit 3 Planning in Various Domains 11 hours
Partial Order Planning – Graphs – Non deterministic Domains Conditional Planning - Continuous
Planning – Multi Agent Planning.
Unit 4 Advanced Concepts in Agents and Learning 12 hours
Higher level Agents, Knowledge in Learning- Statistical Learning Methods -Logics for Multi agent
systems - Possible-Worlds Semantics for Modal Logics - Normal Modal Logics - Epistemic Logic for
Multiagent Systems.
Unit 5 Practical Applications of Agents in Various Domains 14 hours
Industrial and Practical Applications - Agents for Workflow and Business Process Management -
Agents for Electronic Commerce - Agents for Human-Computer Interfaces - Agents for Virtual
Environments
Total Lecture hours 60 hours
Text Book(s)
Stuart Russell and Peter Norvig, “Artificial Intelligence - A Modern Approach”, 2nd Edition,
1
Prentice Hall, 2002Hill Education, 2011
Stuart J. Russell and Peter Norvig “Artificial Intelligence A Modern Approach” Third Edition -
2
2009
Reference Books
1 Gerhard Weiss, ”Multi agent Systems”, Second Edition, MIT Press, 2016
2 Michael Wooldridge, “An Introduction to Multi Agent System”, John Wiley, First edition- 2002.
41
 for Data Scientists”, Shroff/O’Reilly, 2016
Course Designed By: Dr.D.RAMYACHITRA

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M L L L M L M L M
CO2 S M S L M L L M M L
CO3 L S S M M L M L M L
CO4 S S M M L M L M L M

*S-Strong; M-Medium; L-Low

42
 MULTI-AGENT SYSTEMS - LAB

List of programs

1. Create a basic intelligent which should be able to perceive its environment and take simple
actions based on predefined rules.
2. Implement a search algorithm (e.g., A*, BFS, DFS) for a path-finding problem. Use a grid-
based environment where the agent finds the shortest path from a start to a goal position.
3. Solve a simple CSP such as the Sudoku puzzle using backtracking and visualize the steps
taken by the algorithm.
4. Create a simulation where two agents communicate to achieve a common goal. Implement a
simple protocol for agent communication and demonstrate the interaction.
5. Develop a basic multi-agent system where agents must coordinate to complete a task (e.g.,
moving boxes to specific locations). Implement simple coordination strategies and observe
their effectiveness.
6. Implement a Q-learning algorithm for a simple grid-world environment. Train an agent to
reach a goal state while avoiding obstacles and maximizing rewards.
7. Implement a partial order planning algorithm for a given set of actions and goals.
Demonstrate the execution of the plan in a simulated environment.
8. Implement a basic machine learning model (e.g., decision tree) to classify agent actions
based on historical data. Use a small dataset and evaluate the model's performance.
9. Create an agent-based chatbot using a simple rule-based system. The chatbot should interact
with users and provide responses based on predefined rules.
10. Implement an agent that navigates a virtual environment (e.g., a maze) and collects items.
Use a simple graphical interface to visualize the agent's actions.

43
ELECTIVE

44
Course code 24AI1E1 REPRESENTATION LEARNING L T P C
Core/Elective/Supportive ELECTIVE 4 0 0 4
Syllabus 2024-
Pre-requisite Basic knowledge of Mathematics and statistics
Version 2025
Course Objectives:
The main objectives of this course are to:
 To introduce the fundamentals of Representation Learning.
 To acquire the fundamentals of the NLP.
 To give an overview of Self-supervised learning and Multimodal representation learning.

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 To understand the foundations for Representation Learning K1/K2
K1/K2/
2 To know about the representation of Natural languages
K4/K5
3 To be familiar with contrastive learning and to know the challenges K2/K3/K4
K1/K2/
4 To introduce Self-supervised learning
K4
5 To inculcate Multimodal representation learning K2/K3/K4
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 Representation Learning 12 hours

Introduction to Representation Learning - Introduction to autoencoders for representation learning,
early traditional approaches - Overview of visual self-supervised learning methods- Self-supervised
learning VS Transfer Learning, Pretext VS Downstream Task, Pretext tasks: Colorization, Jigsaw
puzzles, Image inpainting, Shuffle and Learn - Classify corrupted images, Rotation Prediction,
Semi-supervised learning

Unit:2 Natural Language Representations 11 hours

Learning Natural Language Representations – Basics of Natural Language Processing, RNN, self-
attention, and Transformer, Language pretext tasks, Pretext tasks for representation learning in
NLP. Contrastive Learning, SimCLR and mutual information-based proof- Contrastive learning,
theory, and proof of MI bound.

Unit:3 Contrastive Learning 11 hours

Understanding Contrastive learning &MoCOand image clustering- Contrastive Learning, L2
normalization, Properties of contrastive loss, Momentum encoder (MoCO): Issues and concerns
regarding batch normalization, Multi-view contrastive learning: Deep Image Clustering: task
definition and challenges, K-means and SCAN, PMI and TEMI. Vision Transformers and
Knowledge Distillation- Transformer encoder and Vision transformer, ViTs VS CNNs: receptive
field and inductive biases, Knowledge distillation and the mysteries of model ensembles,
Knowledge distillation in ViTs and masked image modeling

Unit:4 Self-Supervised Learning 12 hours

Self-supervised learning without negative samples - self-supervised methods, review of knowledge
distillation, Self-Supervised Learning & knowledge distillation, Masked-based visual representation
45
 learning, iBOT, DINOv2

Unit:5 Multimodal Representation Learning 12 hours

Multimodal representation learning, robustness, and visual anomaly detection- Defining Robustness
and Types of Robustness, Zero-shot learning, Contrastive Language Image Pretraining (CLIP),
Image captioning, Few-shot learning, Visual anomaly detection: task definition, Anomaly detection
scores, Anomaly detection metric AUROC

Unit:6 Contemporary Issues 2 hours

Expert lectures, online seminars - webinars

Total Lecture hours 60hours

Text Book(s)
1 Representation Learning for Natural Language Processing,Zhiyuan Liu, Yankai Lin,Maosong Sun
2 An introduction to representation learning- Michael A. Alcorn
3 Representation Learning: Propositionalization and Embeddings- by Marko Robnik-Sikonja, Nada
Lavrac, Vid Podpecan

Reference Books
1 Kevin Murphy. Probabilistic Machine Learning: Advanced Topics. MIT Press, 2023.
2 EthemAlpaydin. Introduction to Machine Learning, 3rd edition. MIT Press, 2014.

Course Designed By: Dr. K. Geetha

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M S M S M L M S M
CO2 S M S M S M L M S M
CO3 S M S M S M L M S M
CO4 S M S M S M L M S M
CO5 S M S M S M L M S M

*S-Strong; M-Medium; L-Low

46
Course code 24AI1E2 DATA VISUALIZATION L T P C

Core/Elective/Supportive ELECTIVE 4 0 4
Syllabus 2024-
Pre-requisite Basic knowledge of Digital Data
Version 2025
Course Objectives:
The main objectives of this course are to:
 To introduce students to the fundamental visualization concepts, and approaches of data
visualization systems.
 To familiarize students with the visualization techniques using different types of data

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 To understand the fundamentals of Visualization and its importance K1/K2
K1/K2/
2 To know about visualization Techniques for Spatial and geospatial Data
K4/K5
K2/K3/
3 To understand time-oriented data and to apply visualization
K4/K5
To be familiar with visualization techniques for Trees, Graphs, and K1/K2/
4
Networks K4/K5
To discover the main subjects, themes, or topics within large collections of K2/K3/
5
text data. K4/K5
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 12 hours
Unit 1: Introduction to Data Visualization – What is Visualization and Why imagery is
important - Applications of visualizations to problem solving - visualization pipeline- Data
foundation -External representation – Interactivity – Difficulty in Validation. Data Abstraction:
Dataset types – Attribute types – Semantics. Task Abstraction – Analyze, Produce, Search,
Query. Four levels of validation – Validation approaches

Unit:2 12 hours
Arrange tables: Categorical regions – Visualization Techniques for Spatial Data: Spatial axis
orientation – Spatial layout density. Arrange spatial data: Geometry – Scalar fields – Vector
fields – Tensor fields. Visualization Techniques for Geospatial Data: Overview of the special
characteristics and methods - basics of geospatial visualization: map projections- visualization
techniques for point, line, area, and surface data.

Unit:3 10 hours
Visualization Techniques for Time-Oriented Data: Importance and need of handling the
temporal dimension- different temporal data visualization techniques. Visualization Techniques
for Multivariate Data : techniques and presentations based on the graphical primitive used in the
rendering, namely, points, lines, or regions, techniques that combine two or more of these types
of primitives.

Unit:4 12 hours
Visualization Techniques for Trees, Graphs, and Networks: representing relationship between
data- part/subpart, parent/child, hierarchical relation and simple or complex: unidirectional or
47
bi-directional, nonweighted or weighted, certain or uncertain relationships. Connections, Matrix
views – Containment. Map color: Color theory, Color maps and other channels

Unit:5 12 hours
Text and Document Visualization - analyzing data from libraries, e-mail archives, all facets of
applications running on the World Wide Web. Visualizing blogs, wiki, twitter feed, digital
library- tasks deals with text, documents, or web-based object. Enabling interaction techniques
and designing effective visualization

Unit:6 Contemporary Issues 2 hours

Expert lectures, online seminars - webinars

Total Lecture hours 60 hours

Text Book(s)
Tamara Munzner, Visualization Analysis and Design, A K Peters Visualization Series,
1
CRC Press, 2014.
2 Scott Murray, Interactive Data Visualization for the Web, O’Reilly, 2013.
Alberto Cairo, The Functional Art: An Introduction to Information Graphics and
3
Visualization, New Riders, 2012

Reference Books
1 Fundamentals of Data Visualization by Claus O. Wilke, O’Reilly Media, Inc, March 2019:

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.tutorialspoint.com/business_writing_skills/data_visualization.htm
2 https://www.javatpoint.com/what-is-data-visualization

Course Designed By: Dr. K. Geetha

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 M S S M S M L M S S
CO2 M S S M S M L M S S
CO3 M S S M S M L M S S
CO4 M S S M S M L M S S
CO5 M S S M S M L M S S

*S-Strong; M-Medium; L-Low

48
Course Code 24AI1E3 AI in IoT L T P C

Core/Elective/Supportive ELECTIVE 4 0 0 4

Basic knowledge of Python Programming and Syllabus 2024-

Pre-requisite
Machine Learning Version 2025
Course Objectives:
The main objectives of this course are:
 Understand the general concepts in IoT and get familiar with the various hardware and
software components of it
 Understand how to build real-life IoT-based projects for different application domains
 Hands-on training to implement IoT with Raspberry Pi.

Expected Course Outcomes:

On the successful completion of the course, student will be able to:
1 Understand the architectural overview and design principles of IoT. K2
2 To develop a machine learning application using Raspberry Pi. K4/K5
3 Building Machine learning models for edge devices using Raspberry Pi. K4/K5
4 Understanding deep learning models using TensorFlowLite. K2 / K4
5 Understanding object detection using TensorFlow. K2 /K4
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 – Create

Unit:1 Introduction to IoT 10 hours

Introduction to IoT, Architectural Overview and Design Principles, Elements of IoT (Arduino,
Raspberry Pi, NodeMCU, Sensors & Actuators), IoT Applications, Sensing, Actuation,
Networking Basics, Embedded OS, IoT and Cloud, Security aspects in IoT.
Unit:2 Raspberry Pi 12 hours
IoT Application Development, Introduction to Raspberry Pi, Integrating Sensors and Actuators
with Raspberry Pi, Pushing and Managing Data in IoT Clouds, Programming APIs
(Python/Node.js/Arduino) for communication protocols (MQTT, ZigBee, Bluetooth, UDP,
TCP).
Unit:3 ML and Deep learning models 15 hours
Implementation of IoT with Raspberry Pi (lab - sensor, MQTT, visualization) Introduction to
ML and Deep learning models for IoT (challenges, opportunities, solutions).
Unit:4 TensorFlowLite 11 hours
Sensor data classification using ML in Raspberry Pi (lab), Introduction to TensorFlowLite,
Image classificationon Raspberry Pi (lab).
Unit:5 Case Study 10 hours
Object detection on Raspberry Pi (optional lab), building scalable ML pipeline using Flask,
Python, uWSGI, TensorFlow.
Unit:6 2 hours
Discussion on case study – Demo - Online seminars – Webinars - Workshops
Total Lecture hours 60 hours
Text Books
Vijay Madisetti, Arshdeep Bahga, ¨Internet of Things, “A Hands on Approach”, University
1
Press, 2014.
Reference Books

49
1 Raj Kamal, “Internet of Things: Architecture and Design”, McGraw Hill,2017.
Stuart Russell and Peter Norvig, “Artificial Intelligence: A Modern Approach” , 3rd Edition
2
Prentice Hall
3 Elaine Rich and Kevin Knight, “Artificial Intelligence”, 3rd Edition, Tata McGraw Hill.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.tensorflow.org/lite/tutorials
2 https://www.classcentral.com/course/introduction-iot-boards-12535
Course Designed By: Dr. P. B. Pankajavalli

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M L S L L L L M L
CO2 L S S M M M L L M M
CO3 M M S S M M L M M L
CO4 L L M M L M L M L M
CO5 L L M M L M L M M M

*S-Strong; M-Medium; L-Low

50
Course Code 24AI2E1 AI FOR ROBOTICS L T P C

Core/Elective/Supportive ELECTIVE 4 0 0 4
1. Data Structures and Algorithms
2. Foundation of Data Science Syllabus 2024-
Pre-requisite
3. Linear Algebra and Optimization Version 2025
4. Principles of AI and ML
Course Objectives:
The main objectives of this course are:
 To understand the principles of reinforcement learning which is one of the key learning
techniques for robots
 To understand uncertainty handling in robotics through probabilistic approaches
 To learn how measurements work for robots

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 Understand the basic introduction and methods in AI. K2
2 Explore the various reinforcement learning approaches. K2/K1
3 Build various solution methods using reinforcement in Robotics K3
4 Understand the various filters used for real time robotic implementation. K2 / K4
5 Understand the various models applied in robot perception. K2 /K4
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 – Create

Unit:1 Introduction to Robotics 10 hours

Overview: Robotics introduction, historical perspective on AI and Robotics, Uncertainty in
Robotics Reinforcement Learning: Basic overview, examples, elements, Tabular Solution
Methods – Multiarmed bandits, Finite Markov decision process.

Unit:2 Dynamic programming 12 hours

Dynamic programming (Policy Evaluation, Policy Iteration, Value Iteration), Monte Carlo
Methods, Temporal-Difference Learning (Q-learning, SARSA).

Unit:3 Approximation 15 hours

Approximate Solution Methods - On-policy Prediction with Approximation, Value function
approximation, Non-linear function approximation, Reinforcement Learning in robotic.

Unit:4 Filters 11 hours

Recursive state estimation: Robot Environment Interaction, Bayes filters, Gaussian filters – The
Kalman filter, The Extended Kalman Filter, The information filter, The particle filter Robot
motion: Velocity Motion Model, Odometry Motion Model, Motion and maps.

Unit:5 Models 10 hours

Measurement: Beam Models of Range Finders, Likelihood Fields for Range Finders,
Correlation- Based Sensor Models, Feature-Based Sensor Models, Overview of POMDP.

Unit:6 2 hours
Discussion on case study – Demo - Online seminars – Webinars - Workshops
Total Lecture hours 60 hours

51
Text Books
1 Sebastian Thrun, Wolfram Burgard, Dieter Fox, Probabilistic Robotics, MIT Press 2005
Richard S. Sutton, Andrew G. Barto, Reinforcement Learning: An Introduction”, Second
2
edition, MIT Press, 2018.
Reference Books
Jens Kober, Jan Peters, Learning Motor Skills: From Algorithms to Robot Experiments,
1
Springer, 2014.
2 Francis X. Govers, Artificial Intelligence for Robotics, Packt, 2018.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.tensorflow.org/lite/tutorials
2 https://www.classcentral.com/course/introduction-iot-boards-12535
Course Designed By: Dr. P. B. Pankajavalli

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M L S L L L L M L
CO2 L S S M M M L L M M
CO3 M S S M M M L M M M
CO4 S M M L M M L M M M
CO5 M M M S M M L M M M
*S-Strong; M-Medium; L-Low

52
 Course Code 24AI2E2 AI in HEALTHCARE L T P C

Core/Elective/Supportive ELECTIVE 2 0 4 4
A FOUNDATION IN BOTH MEDICAL Syllabus 2024-
Pre-requisite
KNOWLEDGE AND AI TECHNIQUES Version 2025
Course Objectives:
 To equip students with AI techniques for healthcare improvement.
 To explore machine learning, NLP, and computer vision in healthcare.
 To analyze medical data and assist in diagnosis.
 To personalize treatment plans and automate administrative tasks
Expected Course Outcomes:
On the successful completion of the course, student will be able to:
Master AI techniques tailored for healthcare applications, including machine learning,
1 natural language processing, and computer vision.
K2/K3
2 K1/K3
Analyse medical data, assist in diagnosis, and personalize treatment plans using AI
3 K2/K5
Understand ethical considerations and regulatory frameworks in AI-powered healthcare
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 – Create
Unit 1 AI Foundations: Definitions, Future Trends, and Applications 11 hours
Artificial Intelligence Overview: Definitions and Future Trends - Intelligent Agents and Problem-Solving
in Healthcare - Operationalizing AI in Consumerism and Supply Chain Management - Machine Learning,
AI, and Decision Support Sieve for primes, Modular exponentiation
Exploring Problem Solving: From Search Strategies to Real-World
Unit 2 12 hours
Applications"
Problem solving Methods - Search Strategies- Uninformed - Informed - Heuristics - Local Search
Algorithms and Optimization Problems - Constraint Satisfaction Problems -Constraint Propagation -
Backtracking Search - Case studies - Journey Mapping and Pain Points, - Patient Monitoring, Differential
Diagnosis, - Care Management - Preventive Screening
Advancing Medical AI: Learning Methods and Predictive Modeling
Unit 3 in diagnosis 11 hours
Learning methods, Rule-based systems- Decision tree learning- Reinforcement learning. AI in Medical
diagnosis. Taxonomies and Relationships, Predictive Modeling Process, Analytic Maturity Model,
Identifying Historic Addressable Opportunity, Predicting Addressable Opportunity, Measuring Predictive
Accuracy.
Foundations of AI: Exploring Predicate Logic, Prolog, and
Unit 4 Knowledge Representation with Case Studies 12 hours
First Order Predicate Logic - Prolog Programming - Unification - Forward Chaining-Backward Chaining -
Resolution - Knowledge Representation - Ontological Engineering-Categories and Objects - Events -
Mental Events and Mental Objects - Reasoning Systems for Categories - Reasoning with Default
Information. Case studies
Integrating Intelligent Agent Architectures in Biomedical
Unit 5 Applications 14 hours
Architecture for Intelligent Agents - Agent communication - Negotiation and Bargaining - Argumentation
among Agents - Trust and Reputation in Multi-agent systems. Biomedical applications. Blood pressure
control, Speech Recognition – Robot control for surgical applications - Hardware - Perception- Planning –
Moving image guidance.
Total Lecture hours 60 Hours
Text Book(s)
M. Tim Jones, “Artificial Intelligence: A Systems Approach ”, Jones and Bartlett Publishers, Inc.; First
1 Edition, 2015 Reprint. ISBN-13: 978-9380298139 Hall of India Private Limited. Third Edition 2009.
2 NoSQL Distilled: Pramod J. Sadalage, Martin Fowler, Addison-Wesley,Second edition – 2012-2014.
3 Arjun Panesar, Machine Learning and AI for Healthcare: Big Data for Improved Health Outcomes (1

53
 ed.),Apress, 019. ISBN 978-1484237984
Reference Books
William F. Clocksin and, Christopher S. Mellish, “Programming in Prolog: Using the ISO Standard”, Fifth
1 Edition, Springer, 2012 Reprint. ISBN 978-3-642-55481-0, DOI 10.1007/978- 3-642-5548.
Ian Millington, John Funge, “Artificial intelligence for Games”, Second edition, Morgan Kaufmann
2 Publishers, CRC Press, 2012, ISBN: 978-0-12-374731-0. for Data Scientists”, Shroff/O’Reilly, 2016
David L. Poole and Alan K. Mackworth, “Artificial Intelligence: Foundations of Computational Agents”,
3 Cambridge University Press, 2010. ISBN-13: 978-0521519007.
S. Russell and P. Norvig, “Artificial Intelligence: A Modern Approach”, Prentice Hall, Third Edition,2016.
4 ISBN-1537600311, 97-81537600314
Course Designed By: Dr.R.PORKODI

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S M S S S M M M M
CO2 S S M S S S M M M M
CO3 S S M S S S M M M M
CO4 S S M S S S M M M M
CO5 S S M S S S M M M M

*S-Strong; M-Medium; L-Low

54
 Course code 24AI2E3 MACHINE LEARNING FOR BIG DATA L T P C

Core/Elective/Supportive ELECTIVE 2 0 4 4
Syll
Fundamentals of Database Management, Data abus 2024-
Prerequisite Mining, and System Software Vers 2025
ion
Course Objectives:
The main objectives of this course are:
• To explain the concepts of machine learning and the need for handling big data.
• To describe the challenges of analyzing massive data sets.
• To describe different types of machine learning algorithms used for a variety of complex tasks.

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
Understand the basic concepts of machine learning and
1 K2/K3
MapReduce.
Analyze the use of machine learning algorithms for finding
2 K3/K4
similar items and data stream domain
3 Understand the concepts of frequent item sets and clustering. K2/K5
Understand and analyze the use of machine learning for
4 K2/K4/K5
recommendation systems and its applications on social networks.
Analyze the use of large-scale machine learning and deep learning
5 K4/K5/K6
concepts in different domains
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Unit:1 MACHINE LEARNING 12 hours

Concept of Machine Learning: Approaches to Modeling- Importance of Words in Documents -
Hash Functions- Indexes - Secondary Storage -The Base of Natural Logarithms - Power Laws -
Map Reduce – Algorithms Using MapReduce – Extensions to MapReduce – The Communication
Cost Model.

Unit:2 FINDING SIMILAR ITEMS & DATA STREAMS 12 hours

Finding similar items: Applications of Near-Neighbor Search - Shingling – LSH - Distance
Measures. Mining Data Streams: Stream data model - Sampling data - Filtering streams. Link
Analysis: Page Rank, Link Spam

Unit:3 FREQUENT ITEM SETS & CLUSTERING 10 hours

Frequent Item Sets: Market Basket Analysis, A-Priori Algorithm - PCY Algorithm. Clustering:
Hierarchical clustering, K-Means, Clustering in Non-Euclidean Spaces, BFR, CURE.

Unit:4 RECOMMENDATION SYSTEMS 12 hours

Recommendation Systems: Utility matrix - Content-based - Collaborative filtering - UV
Decomposition. Mining Social Network Graphs: Social networks as graphs–Clustering –
Partitioning - Simrank. Dimensionality Reduction: Eigen Value Decomposition- PCA – SVD

Unit:5 LARGE-SCALE MACHINE LEARNING 12 hours

Large Scale Machine Learning: Neural Networks
55 - The Support Vector Machines model and
use of Kernels to produce separable data and non-linear classification boundaries. Overview -
Deep learning; Tools for Data Ingestion; analytics and visualization
Mapping with Programme Outcomes
COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S S L M M M M L M
CO2 S S S M M M M M L M
CO3 S S S M M M M M M S
CO4 S S M L M M L M S M
CO5 S S S L M M M M L M

*S-Strong; M-Medium; L-Low

Course Code 24AI3E1 COMPUTER VISION L T P C

Core/Elective/Supportive ELECTIVE 2 0 4 4
Syllabus 2024-
Pre-requisite
Version 2025
Course Objectives:
 To Master the principles and algorithms of computer vision.
 To Gain proficiency in image and video processing using Python and OpenCV.
 To develop skills in object detection, recognition, and tracking.
 To apply computer vision techniques to real-world applications.

Expected Course Outcomes:

On the successful completion of the course, student will be able to:
1 Understand the computer vision fundamentals. K2/K3
2 Apply algorithms to analyse images/videos. K1/K3
3 Implement solutions using Python. K2/K5
4 Develop object detection/recognition applications. K6
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyse; K5 - Evaluate; K6 – Create

Foundations of Image Processing: Enhancing, Detecting, and

Unit 1 Transforming 11 hours
Introduction to Image Processing-Basic mathematical concepts: Image enhancement: Grey
level transforms, Spatial filtering. Extraction of special features: edge and corner detection.
Morphological processing, Image transforms, Discrete Fourier Transform, Fast Fourier
Transform. Frequency domain enhancement. Sieve for primes, Modular exponentiation

Advanced Techniques in Image Segmentation, Feature

Unit 2 12 hours
Detection, and Recognition
Image Segmentation Algorithms: contextual, non-contextual segmentation, texture
segmentation. Feature Detectors and Descriptors, Feature Matching-Object Recognition, Face
detection (Viola Jones), Face Recognition, Modern computer vision architectures based on
deep convolutional neural networks

Unit 3 Dynamic Vision: Tracking, Detection, and Action Recognition 11 hours

The Use of Motion in Segmentation Optical Flow & Tracking Algorithms, YOLO, Deep
SORT: Deep Learning to Track Custom Objects in a Video, Action classification with
convolutional neural networks, RNN,LSTM
56
 Advanced Image Registration and Camera Calibration
Unit 4 12 hours
Techniques
Image registration, 2D and 3D feature-based alignment, Pose estimation, Geometric intrinsic
calibration,-Camera Models and Calibration: Camera Projection Models – orthographic,
affine, perspective projective models. Projective Geometry, transformation of 2-d and 3-d,
Internal Parameters, Lens

Mastering Camera Calibration and 3D Reconstruction

Unit 5 14 hours
Techniques: From Distortion Models to SLAM
Distortion Models, Calibration Methods – linear, direct, and indirect and multi plane methods.
Geometry of Multiple views- Stereopsis, Camera and Epipolar Geometry, Fundamental
matrix; Homography, Rectification, DLT, RANSAC, 3-D reconstruction framework; Auto-
calibration., Introduction to SLAM (Simultaneous Localization and Mapping). algorithms.

Total Lecture hours 60 hours

Text Book(s)
Deep Learning (Adaptive Computation and Machine Learning series) Ian Goodfellow,
1
Yoshua Bengio, Aaron Courville, Francis Bach, January 2017, MIT Press
2 Introduction to Computer Vision and its Application, Richard Szelinski,2010
E. Trucco and A. Verri, Prentice Hall, 1998.Introductory techniques for 3D Computer
3
Vision.
Reference Books
Marco Treiber, “An Introduction to Object Recognition Selected Algorithms for a
1
Wide Variety of Applications”, Springer, 2010.
Forsyth and Ponce, “Computer Vision – A Modern Approach”, Second Edition,
2
Prentice Hall,2011
R. C. Gonzalez, R. E. Woods, ‘Digital Image Processing’, 4th edition Addison-
3
Wesley,2016
Course Designed By: Dr. R. PORKODI

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S S S L M M M M L M
CO2 S S S M M M M M L M
CO3 S S S M M M M M M S
CO4 S S M L M M L M S M
CO5 S S S L M M M M L M

*S-Strong; M-Medium; L-Low

57
Course Code 24AI3E2 QUANTUM AI L T P C

Core/Elective/Supportive ELECTIVE 4 0 0 4
Basic knowledge in:
• Machine Learning Syllabus 2024-
Pre-requisite
• Programming Languages Version 2025
• Probability
Course Objectives:
The main objectives of this course are:
 To understand how the physical nature, as described by quantum physics, can lead to
algorithms that imitate human behavior
 To explore possibilities for the realization of artificial intelligence using quantum
computation
 To learn computational algorithms as described by quantum computation

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 Understand the usage of quantum algorithms in AI. K2
2 To develop problem-solving techniques. K3
3 To understand quantum physics-based information and probability theory. K2
To identify the quantum physics relationship to AI by associative memory
4 K2 / K4
and Bayesian networks
To understand the principles of quantum computation and its mathematical
5 K2 /K4
framework.
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create
Unit:1 10 hours
Introduction - artificial intelligence - computation - Cantor’s diagonal argument - complexity
theory - Decision problems - P and NP - Church–Turing Thesis - Von Neumann architecture –
Problem Solving - Rules - Logic-based operators - Frames - Categorial representation - Binary
vector representation - Production System - Deduction systems - Reaction systems - Conflict
resolution.
Unit:2 12 hours
Human problem-solving - Information and measurement - Reversible Computation - Reversible
circuits - Toffoli gate.
Unit:3 15 hours
Introduction to quantum physics - Unitary Evolution - Quantum Mechanics - Hilbert space -
Quan- tum Time Evolution - Von Neumann Entropy - Measurement - Heisenberg’s uncertainty
principle - Randomness - computation with Qubits - Computation with m Qubit - Matrix
Representation of Serial and Parallel Operations - Quantum Boolean Circuits - Periodicity -
Quantum Fourier Transform - Unitary Transforms - Search and Quantum Oracle.
Unit:4 11 hours
Grover’s Amplification - Circuit Representation - Speeding up the Traveling Salesman Problem
- The Generate-and-Test Method - Quantum Problem - Solving - Heuristic Search - Quantum
Tree Search - Tarrataca’s Quantum Pro- duction System.
Unit:5 10 hours
A General Model of a Quantum Computer - Cognitive architecture - Representation – Quantum
Cognition - Decision making - Unpacking Effects - Quantum walk on a graph - Quantum

58
annealing - Optimization problems - Quantum Neural Computation - Applications on Quantum
annealing Computer - Development libraries - Quantum Computer simulation tool kits.
Unit:6 2 hours
Discussion on case study - Online seminars – Webinars - Workshops
Total Lecture hours 60 hours
Text Books
Andreas Wichert, Principles of Quantum Artificial Intelligence, First edition, World
1
Scientific Publishing, 2014.
Reference Books
Peter Wittek, Quantum Machine Learning: what Quantum means to data mining, Academic
1
Press, 2014.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.udemy.com/topic/quantum-computing/
Course Designed By: Dr. P. B. Pankajavalli

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M L M L S L M M M
CO2 S S S S M S L M M M
CO3 M M M M M M L M M S
CO4 S M M S S S L M M M
CO5 M S M M M M L M M M

*S-Strong; M-Medium; L-Low

59
Course Code 24AI3E3 APPLIED PREDICTIVE ANALYTICS L T P C

Core/Elective/Supportive ELECTIVE 4 0 0 4
Syllabus 2024-
Pre-requisite Linear Algebra and Probability
Version 2025
Course Objectives:
The main objectives of this course are:
 To familiarize students with the methods for exploration and visualization of data.
 To develop machine learning models for predictive tasks.
 To choose suitable performance measures for predictive models.
 To apply predictive modeling techniques in real-world data.

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 Understanding the basics of predictive analytics K2
2 To review the various analytical methods K3
To gain an in-depth understanding of supervised and unsupervised learning
3 K2
for predictive analytics
4 To understand the various analytics methods and time series approaches K2 / K4
5 To understand the principles of forecasting analytics K2 /K4
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create
Unit:1 10 hours
Introduction and Overview of Predictive Analytics – Building a Predictive Model - Predictive
Power and Overfitting - Data Partitioning – Exploratory Data Analysis - Data Visualization –
Dimension
Unit:2 12 hours
Reduction - Principal Components Analysis - Performance Evaluation - Evaluating Predictive
Performance - Judging Classifier Performance – Lift and Decile Charts – Oversampling.
Unit:3 12 hours
Prediction and Classification Methods - Multiple Linear Regression - Explanatory vs.
Predictive Modeling - Estimating the Regression Equation and Prediction - The k-NN
Classifier (Categorical Outcome) - The Naive Bayes Classifier - Classification and Regression
Trees - Logistic Regression.
Unit:4 14 hours
Neural Nets - Discriminant Analysis - Combining Methods: Ensembles - Uplift Modeling –
Association Rules and Collaborative Filtering - Clustering. Forecasting Time Series –
Components of a Time Series – Data Partitioning and Performance Evaluation for Time Series
– Na¨ıve Forecasts - Smoothing Methods - Introduction - Moving Average.
Unit:5 10 hours
Simple Exponential Smoothing – Advanced Exponential Smoothing–Regression-Based
Forecasting - Autocorrelation and ARIMA Models - Data Analytics - Social Network
Analytics - Text Mining -predictive analytics in business application - Other Case Studies.

Unit:6 2 hours
Discussion on case study - Online seminars – Webinars - Workshops
Total Lecture hours 60 hours
Text Books
1 Max Kuhn and Kjell Johnson, “Applied Predictive Modeling”, Springer, 2018.
60
Reference Books
GalitShmueli, Peter C. Bruce, InbalYahav, Nitin R. Patel, Kenneth C. LichtendahlJr“ Data
1 Mining for Business Analytics: Concepts, Techniques, and Applications in Python”,
Wiley, 2019.
Daniel T. Larose and Chantal D. Larose, “Data Mining and Predictive Analytics” (Wiley
2
Series on Methods and Applications in Data Mining), Wiley, 2015.
Ratner Bruce, ”Statistical and Machine-Learning Data Mining:: Techniques for Better
3
Predictive Modeling and Analysis of Big Data”, CRC Press, 2017.
Abbott Dean, ”Applied predictive analytics: Principles and techniques for the professional
4
data analyst”, John Wiley & Sons, 2014.

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.udemy.com/topic/quantum-computing/
Course Designed By: Dr. P. B. Pankajavalli

Mapping with Programme Outcomes

COs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10
CO1 S M M M L L L M M M
CO2 S S S M M M L M M M
CO3 S M M M M M L M M S
CO4 M S S M S S L M S S
CO5 M M S S S M L M M M

*S-Strong; M-Medium; L-Low

61
 JOB ORIENTED
&
VALUE ADDED
COURSES

JOB ORIENTED COURSE : DATA ANALYSIS USING EXCEL

Name of the Department Computer Science

62
 Dr. S. Vijayarani
Name of the Faculty Member i/c Assistant Professor
with Complete Address with Phone and Department of Computer Science
E-mail Bharathiar University, Coimbatore – 641 046
[email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 Hours
U.G. in Computer Science / Computer
Eligibility Applications / Information Technology or its
equivalent
Number of Candidates to be Admitted 30
Mode of the Course Both Regular and Online
Collaboration if any with Companies
(if Yes, Full Address of the Company Address , ---
Name of the Contact Person, Phone, e-mail etc.)
Registration Procedure
Job Opportunities:
 Data Analyst
 Data Scientist
The main objectives of this course are:
1. To understand the basics of the analysis process in Excel
2. To remember the various components and their functions in the Excel worksheet
3. To learn about advanced formulas creation and charts preparation
4. To implement different kinds of data analysis tasks
5. To handle pivot tables and macros
Expected Course Outcomes:
On the successful completion of the course, students will be able to:
1 Understand the need for MS-Excel and the working of various components K1/K2/K4
2 Experiment with the given data by using different functions, ranges and K2/K3/K4
formulas
3 Evaluate the data analysis results and visualize them by using charts K4/K5/K6
4 Analyze the pivot tables and the different spreadsheet tools K4/K5
5 Create the macros and applied them for analytical tasks K4 / K6
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create

Course Lecture / Practical / Project / Internship

Content
DATA ANALYSIS USING EXCEL (30 Hours, 2 Credits)
Module 1 Introduction to Excel: About Excel & Microsoft, Uses of Excel,
Excel software, Spreadsheet window pane, Title Bar, Menu Bar, 3 Hours
Standard Toolbar, Formatting Toolbar, the Ribbon, File Tab and
Backstage View, Formula Bar, Workbook Window, Status Bar,
Task Pane, Workbook & sheets
Module 2 Columns & Rows: Selecting Columns & Rows, Changing 3 Hours
Column Width & Row Height, Autofitting Columns & Rows,
Hiding/Unhiding Columns & Rows, Inserting & Deleting Columns
& Rows, Cell, Address of a cell, Components of a cell – Format,
value, formula, Use of paste and paste special
Module 3 Functionality Using Ranges: Using Ranges, Selecting Ranges, 2 Hours
63
 Entering Information into a Range, Using AutoFill
Module 4 Creating Formulas: Using Formulas, Formula Functions – Sum, 4 Hours
Average, if, Count, max, min, Proper, Upper, Lower, Using
AutoSum
Module 5 Advance Formulas: Concatenate, Vlookup, Hlookup, Match, 3 Hours
Countif, Text, Trim
Module 6 Spreadsheet Charts: Creating Charts, Different types of charts, 4 Hours
Formatting Chart Objects, Changing the Chart Type, Showing and
Hiding the Legend, Showing and Hiding the Data Table
Module 7 Data Analysis: Sorting, Filter, Text to Column, Data Validation 3 Hours
Module 8 PivotTables: Creating PivotTables, Manipulating a PivotTable, 3 Hours
Using the PivotTable Toolbar, Changing Data Field, Properties,
displaying a PivotChart, Setting PivotTable Options. Adding
Subtotals to PivotTables
Module 9 Spreadsheet Tools: Moving between Spreadsheets, Selecting 3 Hours
Multiple Spreadsheets, Inserting and Deleting Spreadsheets
Renaming Spreadsheets, Splitting the Screen, Freezing Panes,
Copying and Pasting Data between Spreadsheets, Hiding,
Protecting worksheets
Module 10 Making Macros: Recording Macros, Running Macros, Deleting 2 Hours
Macros
Text Books
1 Hector Guerrero, Excel Data Analysis Modeling and Simulation, Second Edition, Springer,
2019
2 Berk & Carey, Data Analysis with Microsoft Excel, Brooks / Cole Cengage Learning, 2010
3 Ash Narayan Sah, Data Analysis using Microsoft Excel, Excel Books, 2009

Reference Books
1 Stephen Nelson and Elizabeth C.Nelson, Excel Data Analysis for Dummies, 3 rd Edition, John
Wiley & Sons, Inc., 2016
2 Paul McDefries, Microsoft Excel Data Analysis for Dummies, John Wiley & Sons, Inc., 2019

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://www.coursera.org/learn/excel-data-analysis
2 https://www.datacamp.com/courses/data-analysis-in-excel
3 https://online.rice.edu/courses/excel-data-analysis
4 https://www.tutorialspoint.com/excel_data_analysis/index.htm
5 https://www.excel-easy.com/data-analysis.html

JOB ORIENTED COURSE : POWER BI FOR DATA ANALYTICS

Name of the Department Computer Science
64
 Dr. S. Vijayarani
Name of the Faculty Member i/c Assistant Professor
with Complete Address with Phone and Department of Computer Science
E-mail Bharathiar University, Coimbatore – 641 046
[email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 Hours
U.G. in Computer Science / Computer
Eligibility Applications / Information Technology or its
equivalent
Number of Candidates to be Admitted 40
Mode of the Course Both Regular and Online
Collaboration if any with Companies
(if Yes, Full Address of the Company Address
, ---
Name of the Contact Person, Phone, e-mail
etc.)
Registration Procedure
Job Opportunities:
 Data Analyst
 Data Scientist
The main objectives of this course are:
To understand the key concepts of business intelligence and the Power BI ecosystem
1. To perform different operations by using the data
2. To learn about the creation of data models and final reports
3. To understand the use of dashboards, apps and security
4. To conduct the business data analysis tasks

Expected Course Outcomes:

On the successful completion of the course, students will be able to:
1 Understand the key concepts of business intelligence and Power BI Desktop K1/K2
2 Perform data transformation tasks and create the data models K3 / K6
3 Apply advanced visualization and create the reports K3/K4/K6
4 Create the dashboards and apps K4/K5/K6
5 Use data gateways and refreshing datasets. K3/K4/K5
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 – Create

Course Lecture / Practical / Project / Internship

Content
POWER BI FOR DATA ANALYTICS (30 Hours, 2 Credits)

Module 1 Introduction to Power BI: Key concepts of business

intelligence, The Power BI ecosystem, Power BI Licensing, 3 Hours
Power BI Desktop and Service
Module 2 Power BI Desktop: Downloading and installing Power BI 3 Hours
Desktop, Touring the Desktop, generating data, Creating
Visualizations
Module 3 Connecting and Shaping Data: Getting data, transforming data, 2 Hours
65
 Merging, Copying and Appending Queries, Verifying and
Loading data
Module 4 Creating Data Models and Calculations: Creating a data 4 Hours
model, creating calculations, checking and troubleshooting
calculations
Module 5 Unlocking Insights: Segmenting data, Using report navigation 3 Hours
features, Advanced visualization techniques
Module 6 Creating the final report: Preparing the final report, creating 4 Hours
the final report pages, Finishing up
Module 7 The Service: Getting an account, Introducing the Service, 3 Hours
Publishing and Sharing
Module 8 Using Reports in the Service: Viewing reports, exporting 3 Hours
reports, embedding reports, Editing and creating reports
Module 9 Understanding Dashboards, Apps and Security: 3 Hours
Understanding dashboards, understanding apps, Understanding
security and permissions
Module 10 Data Gateways and Refreshing Datasets: Installing and using 2 Hours
data gateways, Refreshing datasets

Text Books
1 Greg Deckler Learn Power BI - A beginner's guide to developing interactive business
intelligence solutions using Microsoft Power BI, Packt Publishing, 2019

Reference Books
1 Alberto Ferrari and Marco Russo, Introducing Microsoft Power BI, Microsoft Press, 2016
2 Devin Knight, Brian Knight, Mitchell Pearson, Manuel Quintana, Brett Powell, Microsoft
Power BI Complete Reference- Bring your data to life with the powerful features of Microsoft
Power BI, Packt Publishing, 2018

Related Online Contents [MOOC, SWAYAM, NPTEL, Websites etc.]

1 https://powerbi.microsoft.com/en-us/learning/
2 https://www.udemy.com/topic/microsoft-power-bi/
3 https://www.simplilearn.com/power-bi-certification-training-course
4 https://intellipaat.com/power-bi-training/
5 https://www.tutorialspoint.com/power_bi/index.htm
6 https://www.javatpoint.com/power-bi

VALUE ADDED COURSE: SOFTWARE TESTING TOOLS

Name of the Department Computer Science

66
 Dr.K. Geetha
Assistant Professor
Name of the Faculty Member i/c Department of Computer Science
With Complete Address with Phone and e- Bharathiar University
mail Coimbatore – 641 046.
Phone : 9965497121
E mail : [email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 Hours
U.G. in Computer Science/Computer
Eligibility Applications/Information Technology or its
equivalent
Number of Candidates to be Admitted 40
Registration Procedure
Job Opportunities: Opportunities available in IT sectors

The objectives of the Course are:

The main objectives of this course are to:
1 Inculcate the knowledge on the fundamentals of security
2 Present the different types of software testing,
3 Learn the different types of errors
4 Examine the tools for Software Testing
5 Testing few test cases using tool

Course Content Lecture / Practical / Project / Internship

Expected Course Outcomes
On the successful completion of the course, student will be able to:
1 Understand and Remember the basic concepts of Software Testing K1/K2
2 Understand and Remember the types of testing K1/K4
3 Analyze the types of errors K2/K4
4 Analyze and developing test cases K2/K4/K6
5 Experimenting test cases using testing tools available as open source K3/K4/K5
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create
Module 1 Introduction to Software Testing and Terminology 2 hours
Module 2 Types of Testing 2 hours
Module 3 Types of errors 2 hours
Module 4 Penetration testing and security 2 hours
Module 5 Types of Hacking 2 hours
Module 6 Developing test cases 4hours
Module 7 Unit testing - test cases 4 hours
Module 8 Functional testing with test cases 4 hours

67
Module 9 Security testing with test cases 4 hours
Module 10 Penetration testing with test cases 4 hours

Text Book(s)
1 Software Testing- A Craftsman’s Approach, Paul C. Jorgensen, Fourth Edition, CRC Press,
2014
2 Penetration Testing- A Hands-On Introduction to Hacking, by Georgia Weidman, No Starch
Press, USA, 2014

Related Online Contents

1 https://www.tutorialspoint.com/software_testing/index.htm
2 https://www.geeksforgeeks.org/software-testing-basics/

VALUE ADDED COURSE: CYBER SECURITY AND DIGITAL FORENSICS

Name of the Department Department of Computer Science

Dr. R. Porkodi
Associate Professor
Name of the Faculty Member i/c Department of Computer Science
With Complete Address with Phone and Bharathiar University
e-mail Coimbatore – 46
0422-2428349
[email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 hrs
Eligibility
Number of Candidates to be Admitted 40
Both Regular and Online
Mode of the Course
Collaboration if any with Companies
(if Yes, Full Address of the Company
---
Address , Name of the Contact Person,
Phone, e-mail etc.)
Registration Procedure
Job Opportunities:
To become cyber security expert to identify IT breaches, vulnerabilities and threats facing companies
in today’s digital world.

The objectives of the Course are:

1 To learn the impact of Cyber security risk in an Ethical, Social, and Professional Manner
2 To provide knowledge on data acquisition methods, tools, collecting, preserving and seizing of
various digital evidences.
3 To understand the security services for email
Course Outcomes:
68
On the successful completion of the course, student will be able to:
1 Understand the basics of cyber space, ethical hacking and attacks in cyber world.
2 Understand unauthorized access to digital devices and cyber psychology.
3 Study of Collection of evidences, preservation and forensic analysis.
4 Describe the digital forensics software and hardware, tools, technologies, and practices in
forensics.
5 Understanding the email tracking, IP tracking, cracking of passwords and forensic analysis of
different artifacts.

Course Content Lecture / Practical / Project / Internship

Module 1 Ethical hacking, Attack Vectors, Cyberspace and Criminal Behaviour, 3 hrs
Traditional Problems associated with Computer Crimes, brief history of
the internet, contaminants and destruction of data, unauthorized access.
Module 2 Computer intrusions, white-collar crimes, viruses and malicious code, 3 hrs
virus attacks, pornography, software piracy, mail bombs, exploitation,
stalking and obscenity in internet.
Module 3 Introduction to Digital forensics, Forensic software and handling, 3 hrs
forensic hardware and handling. Forensic analysis and its advanced tools,
forensic technology and practices.
Module 4 Biometrics: face, iris and fingerprint recognition, Audio-video evidence 3 hrs
collection, Preservation and Forensic Analysis.
Module 5 Investigation Tools, e-discovery, EDRM Models, digital evidence 3 hrs
collection and preservation.
Module 6 Email investigation, email tracking, IP tracking, email recovery, 3 hrs
Module 7 search and seizure of computer systems, password cracking. 3 hrs
Module 8 Forensic Analysis of OS artifact, Internet Artifacts, File System Artifacts, 3 hrs
Registry Artifacts, Application Artifacts.
Module 9 Report Writing, Mobile Forensic- identification, collection and 3 hrs
preservation of mobile evidences.
Module 10 Social media analysis, data retrieval, Email analysis from mobile phones. 3 hrs

Book(s) for Study

1 M.T.Britz, Computer Forensics and Cyber Crime, Pearson Education, 2012.
2 Charles P. Fleeger, "Security in Computing", Prentice Hall, New Delhi, 2009.
3 BehrouzA.Forouzan, Cryptography & Network Security, Tata McGraw Hill, India, New Delhi,
2009.

Book(s) for reference

1 Bruce Schneier, Applied Cryptography, John Wiley & Sons, New York, 2004.
2 William Stallings, Cryptography and Network Security, Prentice Hall, New Delhi, 2006.
3 Neal Krawetz, Introduction to Network Security, Thomson Learning, Boston, 2007.

Related Online Contents

1 https://www.w3schools.com › cybersecurity
2 https://www.javatpoint.com/cyber-security-tutorial
69
3 https://www.tutorialspoint.com/python_digital_forensics

JOB ORIENTED COURSE - MOBILE APPLICATION DEVELOPMENT

Name of the Department Computer Science

Dr. R. Porkodi
Associate Professor
Name of the Faculty Member i/c Department of Computer Science
With Complete Address with Phone and Bharathiar University
e-mail Coimbatore – 46
0422-2428349
[email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 Hours
U.G. in Computer Science/Computer
Eligibility Applications/Information Technology or its
equivalent
Number of Candidates to be Admitted 40
Both Regular and Online
Mode of the Course

Collaboration if any with Companies

(if Yes, Full Address of the Company Address , ---
Name of the Contact Person, Phone, e-mail etc.)
Registration Procedure
Job Opportunities:
 To become mobile app developer in Retail, healthcare sector, Travel and tourism
industry, Entertainment industry, Financial services and Media organizations.

The objectives of the Course are:

1 Provides a comprehensive overview and focuses on developing multiplatform mobile

applications using the Web skills.
2 Strengthen the skills of students in learning hybrid application framework to develop and
target multiple mobile platforms with a single codebase.
3 Enrich the knowledge of students in Ionic one of fastest growing mobile application
framework.
4
Course Outcomes:
On the successful completion of the course, student will be able to:
1 Understand the basics of mobile devices, app store, development environments,
characteristics, history of mobile application frameworks.
70
2 Understand the mobile application frameworks and setting up java, eclipse, android
development components. Creating user interface design for mobile applications and
managing application data.
3 Understanding the enterprise requirements and testing methodologies for mobile
applications.
4 Understanding the hybrid mobile app development frameworks: CSS3, HTML 5, Iconic,
Angular JS, Node.JS and developing the hybrid mobile applications
5 Understanding the mobile app deployment process, Usage of Sqlite, mongo DB and
Mysql and IBM BlueMix.

Course Content Lecture / Practical / Project / Internship

Module 1 Introduction to Mobile Devices: Introduction - Mobile vs. 3 hours

Desktop devices - App Store, Google Play, Windows Store -
Development environments - PhoneGAP
Module 2 Native vs. web applications - Mobile Connectivity Evolution - 3 hours
Characteristics of mobile applications - History of mobile
application frameworks
Module 3 Application models of mobile application frameworks - Setting 3 hours
up an android development environment: setting up java,
eclipse, android development components, verify the
development environment
Module 4 User interface design for mobile applications - Managing 3 hours
application data
Module 5 Addressing enterprise requirements in mobile applications: 3 hours
performance, scalability, modifiability, availability, and
security
Module 6 Testing methodologies for mobile applications - Publishing, 3 hours
deployment, maintenance and management
Module 7 Hybrid Mobile App Development Frameworks: Introduction to 3 hours
CSS3.HTML5 - Full-Stack Web Development
Module 8 Hybrid Mobile App Development: Ionic and AngularJS - 3 hours
node.JS
Module 9 APP deployment: Angular ui-router and Resolve - Using Local 3 hours
Storage(Sqlite) -Databases - mongoDB, MySQL
Module 10 Ionic Adding Platforms - Building and Deploying the App - 3 hours
Hybrid Mobile Development and IBM BlueMix

Text Book(s)
1 Bill Phillips, Chris Stewart, Brian Hardy, and Kristin Marsicano, Android Programming: The Big
Nerd Ranch Guide, Big Nerd Ranch LLC, 3rd edition, 2017.
2 Rajiv Ramnath, Roger Crawfis, and Paolo Sivilotti, Android SDK 3 for Dummies, Wiley.
3 Brian Fling, Mobile Design and Development, O’Reilly Media, Inc., 2009.

71
Reference Book(s)
1 Maximiliano Firtman, Programming the Mobile Web, O’Reilly Media, Inc., 2nd ed., 2013.

Related Online Contents

1 https://developer.android.com/
2 https://www.w3schools.in/category/android-tutorial/
3 https://www.tutorialspoint.com/android/index.htm

JOB ORIENTED COURSE - SMART APPLICATIONS WITH INTERNET OF THINGS

Name of the Department Computer Science
Dr.P.B.Pankajavalli
Name of the Faculty Member i/c Assistant Professor
With Complete Address with Phone and Dept. of Computer Science
e-mail Bharathiar University, Coimbatore
Phone : 2428603, [email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 Hours
U.G. in Computer Science/Computer
Eligibility Applications/Information Technology or its
equivalent
Number of Candidates to be Admitted 40
Mode of the Course Both Regular and Online
Collaboration if any with Companies
(if Yes, Full Address of the Company
No
Address , Name of the Contact Person,
Phone, e-mail etc.)
Registration Procedure
Job Opportunities:
Hardware and device development, Sensor networking professionals
IoT cloud engineer, Product Manager
The objectives of the Course are:
The main objectives of this course are to:
1 To understand the concept of sensors and microcontrollers
2 To remember basic syntax in C programming
3 To apply sensor on microcontrollers
4 To understand the interfacing of cloud with sensors
5 To evaluate and visualize the data in the cloud
Expected Course Outcomes:
1 Understand the basics of sensors and sensor networks K2/K3
2 Create basic arduino code and to gain knowledge on K1/K2/K4
built in code
3 Develop small IoT prototype using different sensors. K3/K4
72
4 Explore the usage of buzzers, motors, relays and LED K3/K4
lights
5 Deploy interface with cloud and to visualize data K2/K3/K5
K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5- Create
Course Content Lecture / Practical / Project / Internship
Smart Applications with Internet of Things (30 Hours, 2 credits)
Module 1 Anatomy of Sensors Networks – Topology of Sensor Network 2 hours
– Type of Sensor Nodes – Sensors- Sensors measures
Module 2 Analog Sensors- Digital Sensors – Storing senor data – 2 hours
Examples
Module 3 Understanding the Arduino board – Arduino Board types- 3 hours
Virtronics Simulator for Arduino- Tinkercad -Arduino IDE -
Installing and Setting up the Arduino IDE - Connecting the
Arduino IDE with devices
Module 4 Program Structure in C - Basic Syntax - Data Types / 4 hours
Variables / Constants - Operators, Conditional Statements and
Loops -Functions, Array and Pointers - Strings and I/O -
Arduino C Library functions - Working with Arduino inbuilt
examples.
Module 5 Understanding Sensors and Devices - Understanding basic 3 hours
electronic components and power elements - Understanding the
Inputs from Sensors - Working with Temperature Sensors,
Ultrasound Sensor, Humidity sensor, Motion Sensor
Module 6 Working with IR Sensor - Working with Proximity Sensor - 3 hours
Working with Photo Diode - Working with Accelerometer and
vibration sensor - Introduction to Raspberry Pi.
Module 7 Understanding the Outputs - Activating LED Lights - 3 hours
Activating Relays - Activating Buzzer
Module 8 Running DC Motors - Running - Stepper Motors and Servo 3 hours
Motors
Module 9 Introduction to cloud – Thingspeak IoT Analytics Platform – 3 hours
API key – Thingspeak login – API Key Process
Module 10 ESP8266 WI-FI Module – Installation of ESP8266 board 4 hours
package to Arduino IDE – Circuit Diagram – Graph
visualization – Introduction to Adafruit, Bolt, Blynk, and
IFTTT

Text Book(s)
1 Michael Margolis, “Arduino Cookbook” 2nd Edition, O'Reilly Media, 2011.
2 Charles Bell, “Beginning Sensor Networks with Arduino and Raspberry Pi”, 1st Edition,
Technology in Action, 2013.

Reference Book(s)
1 Arvind Ravulavaru, Enterprise Internet of Things Handbook: Build end-to-end IoT solutions
using popular IoT platforms, Packt Publishing Limited, 2018.

Related Online Contents

1 https://electronics-project-hub.com/send-data-to-thingspeak-using-esp8266/
73
2 https://virtronics.com.au/Simulator-for-Arduino.html
3 https://www.instructables.com/id/ESP8266-to-IFTTT-Using-Arduino-IDE/
Course Designed by: Dr.P.B.Pankajavalli

VALUE ADDED COURSE - REMOTE SENSING AND GIS

Name of the Department Computer Science
Dr.D.Napoleon
Assistant Professor
Name of the Faculty Member i/c Department of Computer Science
With Complete Address with Phone and e- Bharathiar University
mail Coimbatore – 641 046.
Phone : 9655162717
E mail : [email protected]
Inter / Intra Department Course Intra Department Course
Duration of the Course 30 Hours
U.G. in Computer Science/Computer
Eligibility Applications/Information Technology or its
equivalent
Number of Candidates to be Admitted 40
Registration Procedure
Job Opportunities: GIS Analysts/Sr. GIS Analyst, GIS Engineer, Senior GIS Executive, Sr.
Modeling Analyst

The objectives of the Course are:

The main objectives of this course are to:
1 Explain the basics of geographic information systems (GIS) and related areas such as geodesy
and remote sensing
2 Select and acquire both primary and secondary spatial data for use in GIS
3 Manage, and analyze digital data in raster and vector formats
4 Describe how common analytical methods and techniques work
5 Create and present a GIS project.
Course Content Lecture / Practical / Project / Internship
Expected Course Outcomes
On the successful completion of the course, student will be able to:

1. Understand and Remember the basic concepts of remote sensing K1/K2

2. Understand and Remember the functionalities of GIS-Photogrammetry K1/K2
3. Analyze the Statistical Concepts based on the Images K2/K4
4. Analyze and Evaluate the case studies K3/K4/k5
5. Create and analyze environmental Monitoring and Assessment K2/K4/K6

74
 K1 - Remember; K2 - Understand; K3 - Apply; K4 - Analyze; K5 - Evaluate; K6 - Create
Module 1 Fundamentals & Physics of Remote Sensing- Platforms and Sensors- 2 hours
Fundamentals of Geographic Information System-Digital Cartography-
Photogrammetry-Surveying and Global Positioning System
Module 2 Fundamentals of GIS-Photogrammetry, Surveying& GPS-Information 2 hours
Extraction from Satellite Images-Thermal and Microwave Remote
Sensing-Hyper spectral Remote Sensing

Module 3 GIS Data Analysis-Geodesy-Fundamental Statistical Concepts-Geo- 4 hours

statistics & Statistical applications in GIS
Module 4 Advance Remote Sensing: Data Processing & Applications-Fundamental 4 hours
Statistical Concepts & Geo-Statistics
Module 5 Application of Geo-informatics-Spatial decision support system 6 hours
Module 6 Fundamental of Research-Research Methodology and Project 6 hours
Management
Module 7 Application of Geo-Informatics and Spatial Decision Support System 4 hours
Module 8 Generation of Case Studies(Compulsory Field study) 4 hours
Module 9 Environmental Monitoring and Assessment- QGIS Customization Using 4 hours
Python
Module 10 Customization of Geospatial Tools-GIS Customization Using ArcGIS 4 hours

Text Book(s)
1 George Joseph and C Jeganathan, Fundamentals of Remote Sensing,3rd Edition, January 2018
2 Lillesand , Kiefer, Chipman ,Remote Sensing and Image Interpretation, 6 th Edition, January 2011
3 Basudeb Bhatta, Remote Sensing and GIS, 2nd Edition, August 2011

Related Online Contents

1 https://onlinecourses.nptel.ac.in/noc19_ce41/preview
2 https://www.coursera.org/lecture/spatial-analysis-satellite-imagery-in-a-gis/what-is-remote-
sensing-27nfo
3 https://gisgeography.com/remote-sensing-earth-observation-guide/

75