|
|
|
|
|
| |
Assesment Pattern | |
ESE-50% CIA-50% | |
Examination And Assesments | |
1. Evaluation Pattern: 50% CIA + 50% ESE 2. Tutorials / Assignments / Tests / Quiz / Seminar. 3. Attendance is part of the CIA component. 4. Minimum percentage to pass in each paper is 50% (CIA + ESE).
| |
Department Overview: | |
The department was established in the year 1990, with a curriculum in line with industry expectations and research. The department also provides opportunities to work on collaborative projects with industry and international universities, faculty expertise in recent technologies and Alumni support are some of the department highlights. The following programmes are offered by the department; Undergraduate Programmes BSc CME-Bachelor of Science (BSc) in Computer Sc, Maths, Electronics Postgraduate Programmes Master of Science (Artificial Intelligence and Machine Learning) Research Programmes | |
Mission Statement: | |
VISION
The Department of Computer Science endeavors to imbibe the vision of the University “Excellence and Service”. The department is committed to this philosophy which pervades every aspect and functioning of the department. MISSION
“To develop IT professionals with ethical and human values”. To accomplish our mission, the department encourages students to apply their acquired knowledge and skills towards professional achievements in their careers. The department also molds the students to be socially responsible and ethically sound. | |
Introduction to Program: | |
Machines are gaining more intelligence to perform human-like tasks. Artificial Intelligence has spanned across the world irrespective of domains. MSc (Artificial Intelligence and Machine Learning) will enable to capitalise this wide spectrum of opportunities to the candidates who aspire to master the skill sets with a research bent. The curriculum supports the students to obtain adequate knowledge in the theory of intelligence with hands-on experience in relevant domains with tools and techniques to address the latest demands from the industry.It comprises foundational courses from computer Science and advanced courses in the area of Artificial Intelligence and Machine Learning including Natural Language Processing, Deep Learning, Image processing, Soft Computing and IIoT. Research labs, guest lectures, Seminars, practical courses on latest tools, real time application development, multiple elective streams from specialised domains and interdisciplinary are an integral part of the curriculum. Exposure to handle the complex heterogeneous data to solve societal problems is the most preferred skill set required today. | |
Program Objective: | |
Programme Outcome/Programme Learning Goals/Programme Learning Outcome: PO1: Conduct investigation and develop innovative solutions for real world problems in industry and research establishments related to Artificial Intelligence and Machine LearningPO2: Apply programming principles and practices for developing automation solutions to meet future business and society needs. PO3: Ability to use or develop the right tools to develop high end intelligent systems PO4: Adopt professional and ethical practices in Artificial Intelligence application development PO5: Understand the importance and the judicious use of technology for the sustainability of the environment. Programme Specific Outcome: NA: NAProgramme Educational Objective: NA: NA | |
MAI131 - MATHEMATICAL FOUNDATION FOR COMPUTATIONAL INTELLIGENCE (2024 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:3 |
Course Objectives/Course Description |
|
This course aims to provide fundamental knowledge of mathematical foundations for computational Intelligence in Artificial Intelligence and Machine Learning. |
|
Learning Outcome |
|
CO1: Understand the concepts of Linear and Matrix Algebra, Vector spaces, eigen
values and eigen vectors. CO2: Understand the Statistical concepts and Probability theorem for AI and ML
applications CO3: Design and Develop different real time applications using different mathematical concepts. (Python, R, and other tools) |
Unit-1 |
Teaching Hours:9 |
LINEAR EQUATIONS IN LINEAR ALGEBRA
|
|
Systems of Linear Equations-Row reduction and Echelon Forms-Vector Equations-Matrix Equation-Solution Sets of Linear Systems-Applications of Linear Systems-Linear Independence-Introduction to Linear Transformations-The Matrix of Linear Transformation-Linear Models in Business, Science and Engineering | |
Unit-2 |
Teaching Hours:9 |
MATRIX ALGEBRA
|
|
Matrix Operations-The Inverse of a Matrix-Characterizations of Invertible Matrices-Partitioned Matrices-Matrix Factorizations-The Leontief Input-Output Model- Application to Computer Graphics-Subspaces OF RN-Dimension and Rank | |
Unit-3 |
Teaching Hours:9 |
VECTOR SPACES, EIGEN VALUES, AND EIGEN VECTORS
|
|
Vector Spaces and Subspaces-Null Spaces, Column Spaces and Linear Transformations-Linearly Independent Sets; Bases- Coordinate Systems-The Dimension of a Vector Space-Rank-Change of Basis-Applications to Difference Equations-Application to Markov Chains.
Eigenvectors and Eigenvalues-The Characteristics Equation-Diagonalization-Eigenvectors and Linear Transformations-Complex Eigenvalues-Discrete Dynamical Systems-Application of Differential Equations-Iterative Estimate for Eigenvalues | |
Unit-4 |
Teaching Hours:9 |
DATA SHINE
|
|
Presentation of data using graphs-Computation of central tendency and dispersion-Correlation and Regression-Case studies | |
Unit-5 |
Teaching Hours:9 |
PROBABILITY
|
|
Definition of Probability, conditional probability, Total probability theorem, Bayes theorem.
Random Variables: Continuous and discrete random variable-Definition probability mass function- Probability density function - Expectation and variance-Standard discrete distributions-Bernoulli, binomial, Poisson and geometric-Standard continuous distributions-Normal and Exponential. | |
Text Books And Reference Books: [1] David C. Lay, Steven R. Lay, and Judi J. McDonald, “Linear Algebra and Its Applications”, Pearson, Fifth Edition,2016. [2]Gupta S.C & Kapoor V.K, “Fundamentals of Mathematical statistics”, Sultan Chand & sons, 2020.
[3]Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, “An Introduction to Statistical Learning with Applications in R” Springer, Second Edition,2021 | |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI132 - INTRODUCTION TO STATISTICS FOR MACHINE LEARNING (2024 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:3 |
Course Objectives/Course Description |
|
This course is designed to teach the basic statistical concepts. This will help students to develop an understanding of random variables, probability distributions, and high-dimensional random variables, as well as sampling distributions and inferential statistics. |
|
Learning Outcome |
|
CO1: Understand the probability concepts applied to random data.
CO2: Apply various probability distributions to both continuous and discrete data. CO3: Formulate testing of hypothesis procedures
|
Unit-1 |
Teaching Hours:9 |
INTRODUCTION TO DATA AND DESCRIPTIVE MEASURES
|
|
Data - qualitative and quantitative data: binary, categorical, continuous - measures of central tendency - measures of dispersion – skewness | |
Unit-2 |
Teaching Hours:9 |
PROBABILITY AND RANDOM VARIABLE
|
|
Random experiment - events - probability - classical definition - addition rule - random variable: discrete and continuous - expectation – bivariate and multivariate random vectors: definition – expectation and covariance matrix (only statement) | |
Unit-3 |
Teaching Hours:9 |
PROBABILITY DISTRIBUTIONS
|
|
Probability distributions for discrete data: Bernoulli - binomial - Poisson – multinomial ,Probability distributions for continuous data: Normal – logistic distribution – multivariate normal: pdf and mean vector and covariance matrix (only statement)
| |
Unit-4 |
Teaching Hours:9 |
STATISTICAL INFERENCE FOR NUMERICAL DATA
|
|
Population and sample - parameter and statistic – sampling error - sampling distributions: chi-square, t, F (only definition and statement of applications) – hypotheses: null and alternative – types of errors – level of significance – p-value - test statistics – critical region
One sample and two sample t-test – ANOVA (only hypothesis, the test statistic and numerical illustration) | |
Unit-5 |
Teaching Hours:9 |
STATISTICAL INFERENCE FOR CATEGORICAL DATA
|
|
Inference for single proportions – Inference for two proportions - testing for the goodness of fit using chi-square – Testing for independence (two-way tables) | |
Text Books And Reference Books:
1. Barr, Christopher, David M. Diez, and Cetinkaya Rundel. OpenIntro statistics. (2019). | |
Essential Reading / Recommended Reading
| |
Evaluation Pattern ESE-50% CIA-50% | |
MAI133 - FOUNDATIONS OF ARTIFICIAL INTELLIGENCE (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
This course aims at developing an understanding about the fundamental concepts in defining and simulating perception, identifying the problems where AI is required. And the different AI techniques available to define and explain learning algorithms
|
|
Learning Outcome |
|
CO1: Express the modern view of AI and its foundation CO2: Illustrate Search Strategies with algorithms and Problems. CO3: Implement Proportional logic and apply inference rules. |
Unit-1 |
Teaching Hours:5 |
INTRODUCTION TO AI
|
|
Introduction to AI, The Foundations of AI, AI Technique -Tic-Tac-Toe. Problem characteristics, Production system characteristics, Production systems: 8-puzzle problem. | |
Unit-2 |
Teaching Hours:5 |
INTELLIGENT AGENTS
|
|
Intelligent Agents: Agents and Environments, Good Behavior: The concept of rationality – The nature of Environments, The Structure of Agents -Expert Systems-Types of Expert Systems | |
Unit-3 |
Teaching Hours:8 |
LOCAL SEARCH ALGORITHM
|
|
Searching: Uninformed search strategies – Breadth first search, depth first search. Generate and Test, Hill climbing, simulated annealing search, Greedy best first search, A* search, AO* search | |
Unit-4 |
Teaching Hours:7 |
KNOWLEDGE REPRESENTATION
|
|
Propositional logic - syntax & semantics - First order logic. Inference in first order logic, propositional Vs. first order inference, unification & lifts, Clausal form conversion, Forward chaining, Backward chaining, Resolution
| |
Unit-5 |
Teaching Hours:5 |
ETHICS AND SOCIAL IMPLICATIONS OF AI
|
|
Ethical Considerations on AI – bias – privacy – philosophical challenge in human judgement – faulty algorithms - Social Implications of AI – Case studies Planning and Acting in the Real World | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern ESE-50% CIA-50% | |
MAI134 - RESEARCH METHODOLOGY (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
The research methodology module is intended to assist students in planning and carrying out research projects. The students are exposed to the principles, procedures and techniques of implementing a research project. The course starts with an introduction to research and carries through the various methodologies involved. It continues with finding out the literature using computer technology, basic statistics required for research and ends with linear regression. |
|
Learning Outcome |
|
CO1: Understand the essence of research and the necessity of defining a research problem. CO2: Apply research methods and methodologies including research design, data collection, data analysis, and interpretation CO3: Create scientific reports according to specified standards |
Unit-1 |
Teaching Hours:6 |
RESEARCH METHODOLOGY
|
|
Defining research problem - selecting the problem - necessity of defining the problem - techniques involved in defining a problem- Ethics in Research. | |
Unit-2 |
Teaching Hours:6 |
RESEARCH DESIGN
|
|
Principles of experimental design Working with Literature: Importance, finding literature, using your resources, managing the literature, keep track of references, using the literature, literature review. On-line Searching: Database – SCIFinder – Scopus - Science Direct - Searching research articles - Citation Index - Impact Factor - H-index etc | |
Unit-3 |
Teaching Hours:6 |
RESEARCH DATA
|
|
Measurement of Scaling: Quantitative, Qualitative, Classification of Measure scales, Data Collection, Data Preparation. | |
Unit-4 |
Teaching Hours:6 |
SCIENTIFIC WRITING
|
|
Scientific Writing and Report Writing: Significance, Steps, Layout, Types, Mechanics and Precautions, Latex: Introduction, text, tables, figures, equations, citations, referencing, and templates (IEEE style), paper writing for international journals, Writing scientific report. | |
Unit-5 |
Teaching Hours:6 |
REPORT WRITING
|
|
Latex: Introduction-Text-Tables- Figures- Equations- Citations- Referencing and Templates (IEEE style). | |
Text Books And Reference Books: [1] C. R. Kothari, Research Methodology Methods and Techniques, 3rd. ed. New Delhi: New Age International Publishers, Reprint 2014. [2] Zina O’Leary, The Essential Guide of Doing Research, New Delhi: PHI, 2005. | |
Essential Reading / Recommended Reading [1] J. W. Creswell, Research Design: Qualitative, Quantitative, and Mixed Methods Approaches, 4thed. SAGE Publications, 2014. [2] Kumar, Research Methodology: A Step by Step Guide for Beginners, 3rd. ed. Indian: PE, 2010. a | |
Evaluation Pattern ESE-50% CIA-50% | |
MAI171 - MACHINE LEARNING (2024 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:4 |
Course Objectives/Course Description |
|
This course is designed to introduce the principles and design of machine learning techniques. This course aims to provide foundations for conceptual aspects of machine learning algorithms along with their applications to solve real world problems. |
|
Learning Outcome |
|
CO1: Understand the basic principles of machine learning models CO2: Evaluate and prepare data for machine learning models. CO3: Formulate machine learning problems and their solutions CO4: Evaluate different models used for classification |
Unit-1 |
Teaching Hours:15 |
INTRODUCTION TO DATA PREPROCESSING
|
|
Getting to Know your data: Data Objects and Attribute Types, Measuring Data Similarity and Dissimilarity – Data Preprocessing: An Overview – Data Cleaning – Data Integration – Data Reduction – Data Transformation – Data Discretization. INTRODUCTION TO MACHINE LEARNING: Origins of Machine Learning – Basic learning process – Machine Learning in Practice – Types of Machine Learning Algorithms Lab Exercises: 1. Data Exploration for identifying different datasets 2. Preprocessing the dataset using normalization techniques | |
Unit-2 |
Teaching Hours:15 |
RULE BASED MACHINE LEARNING
|
|
Mining Frequent Patterns, Associations and Correlations - Basic Concepts - Frequent Itemset Mining Methods – Pattern Evaluation Methods Lab Exercises: 1. Identify frequent itemsets using Apriori Algorithm 2. Generate FP Tree for a transaction dataset | |
Unit-3 |
Teaching Hours:15 |
ADVANCED PATTERN MINING:
|
|
Pattern Mining – Pattern Mining in Multilevel, Multidimensional space – Constraint-based Frequent Pattern Mining – Mining High-Dimensional Data and Colossal Patterns – Mining Compressed or Approximate Patterns – Pattern Exploration and Application Lab Exercises: 1. Explore generating multilevel association rules 2. Explore multidimensional associations | |
Unit-4 |
Teaching Hours:15 |
SUPERVISED LEARNING I:
|
|
Classification – Basic Concepts – Decision Tree Induction – Bayes Classification Methods – Rule-Based Classification – Model Evaluation and Selection – Techniques to improve Classification Accuracy. Lab Exercises: 1. Demonstrate Naïve Bayes classifier 2. Construct Decision Tree for a dataset and identify the order of attributes | |
Unit-5 |
Teaching Hours:15 |
SUPERVISED LEARNING II:
|
|
Bayesian Belief Networks – Support Vector Machines – Classification using Frequent Patterns – Lazy Learners – Self Study: Additional topics regarding classification Lab Exercises: 1. Explore SVM Classifier 2. Demonstrate Lazy Learner | |
Text Books And Reference Books: [1] Data Mining: Practical Machine Learning Tools and Techniques, Ian H. Witten, Eibe Frank, Mark A. Hall, Morgan and Kaufmann Publisher, Third Edition, 2014 [2] Introduction to Machine Learning, E. Alpaydin, 3rd Edition, MIT Press, 2014. [3] Machine Learning with R: Expert techniques for predictive modeling, Brett Lantz, 3rd Edition, Packt Publishing, 2019 | |
Essential Reading / Recommended Reading [1] Data Mining Concept and Techniques, Jiawei Han, Micheline Kamber, Jian Pie, Morgan and Kaufmann Publisher, Third Edition, 2012 [2] Data Mining Techniques, Arun K Pujari, Second Edition, Universities Press India Pvt. Ltd. 2010 Note: Python libraries like MLxtend and Scikit Learn can be used for lab exercises | |
Evaluation Pattern ESE-50% CIA-50% | |
MAI172 - ADVANCED DATABASE TECHNOLOGIES (2024 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:4 |
Course Objectives/Course Description |
|
To provide a strong foundation for database application design and development by introducing the fundamentals and advanced concepts of database technologies. |
|
Learning Outcome |
|
CO1: Understand the basic concepts of database management systems, structured query language, transactions, and related database facilities. CO2: Analyze the database requirements and develop the logical design of the database.
CO3: Design NoSQL database applications using storing, accessing, and querying.
CO4: Develop new applications in databases based on knowledge of existing techniques. |
Unit-1 |
Teaching Hours:15 |
DATABASE SYSTEM CONCEPTS AND CONCEPTUAL MODELING
|
|
Data models, schemas and instances, DBMS architecture and data independence, Database languages and interfaces, database system environment, and Classification of DBMS. Using High-Level Conceptual Data Models for Database Design - Entity Types, Entity Sets, Attributes, and Keys - Relationship Types, Relationship Sets, Roles, and Structural Constraints, Enhanced Entity Relationship Model -SQL Data Definition and Data Types, Specifying Constraints in SQL, Basic Retrieval Queries in SQL, Additional features of SQL. Complex Queries, Triggers, Views, and Schema Modification More Complex SQL Retrieval Queries, Specifying Constraints as Assertions and Actions as Triggers, Views (Virtual Tables) in SQL, Schema Change Statements in SQL. Lab Exercises: 1. DDL, DML, and TCL commands
2. Use of integrity constraints and referential integrity. | |
Unit-2 |
Teaching Hours:15 |
RELATIONAL DATA MODEL, DATABASE DESIGN, AND INTRODUCTION TO FILE ORGANIZATION
|
|
Design Guidelines for Relation Schemas - Functional Dependencies - Normal Forms Based on Primary Keys - Second and Third Normal Forms - Boyce-Codd Normal Form – Multivalued Dependency and Fourth Normal Form - Join Dependencies and Fifth Normal Form – Inference Rules, Equivalence and Minimal Cover - Properties of Relational Decompositions - Nulls and Dangling Tuples - File Organization - Organization of Records in Files - Ordered Indices - B+ Tree Index Files - Static Hashing - Bitmap Indices. Lab Exercises: 3. Data Retrieval using JOINS
4. Subqueries and Correlated queries | |
Unit-3 |
Teaching Hours:15 |
TRANSACTION PROCESSING, CONCURRENCY CONTROL, AND RECOVERY
|
|
Transaction - Introduction to transaction processing- transaction and system concept- Desirable properties of the transaction- Transaction support in SQL- concurrency control techniques – Two-phase Locking techniques for concurrency- Concurrency Control Based on Timestamp Ordering. Recovery Concepts- NO-UNDO/REDO Recovery Based on Deferred Update- Recovery Techniques Based on Immediate Update- Shadow Paging. Lab Exercises: 5. Views in SQL
6. Stored Procedures and Triggers | |
Unit-4 |
Teaching Hours:15 |
DISTRIBUTED DATABASES AND NOSQL SYSTEMS
|
|
Distributed databases: Distributed Database concepts- Types - Data Fragmentation- Replication- Allocation Techniques. Overview of Transaction Management - Overview of Concurrency Control and Recovery.NOSQL Databases-Introduction to NOSQL Systems, The CAP Theorem, Document-Based NOSQL Systems and MongoDB, NOSQL Key-Value Stores, Column-Based or Wide Column NOSQL Systems, NOSQL Graph Databases. Lab Exercises: 7. NOSQL CRUD operations
8. .NOSQL Aggregate functions | |
Unit-5 |
Teaching Hours:15 |
NoSQL STORES AND INDEXING AND ORDERING DATA SETS
|
|
Accessing Data from Column-Oriented Databases Like HBase-Querying Redis Data stores- Querying in Neo4J-Changing Document Databases-Schema Evolution in Column-Oriented Databases-HBase Data Import and Export-Data Evolution in Key/Value Stores-Map-Reduce- Basic Map-Reduce-Map-Reduce Calculations-2 stage example. Indexing and Ordering Data Sets-Essential Concepts Behind A Database Index-Indexing and Ordering in MongoDB-Creating and Using Indexes in MongoDB-Indexing and Ordering in CouchDB-Indexing in Apache Cassandra-Indexing and Ordering in Neo4J. Lab Exercises: 9. NoSQL data IMPORT and EXPORT
10. MAP-REDUCE in NoSQL | |
Text Books And Reference Books: [1] Elmasri & Navathe, Fundamentals of Database Systems, Addison-Wesley, 7th Edition, 2021. [2]Shashank Tiwari, Professional NoSQL, Wrox Press, Wiley, 2021, ISBN: 978-0-470-94224-6 | |
Essential Reading / Recommended Reading [1] Korth F. Henry and Silberschatz Abraham, Database System Concepts, McGraw Hill, 6th Edition, 2010. [2] O’neil Patric, O’neil Elizabeth, Database Principles, Programming and Performance, Argon Kaufmann Publishers, 2nd Edition, 2002. [3] Ramakrishnan and Gehrke, Database Management System, McGraw-Hill, 3rd Edition, 2003. [4]Gaurav Vaish, Getting Started with NoSQL, Packt Publishing, 2013. | |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI231 - KNOWLEDGE VISUALIZATION (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
Data visualization techniques allow people to use their perception to better understand the data. The goal of this course is to introduce students to data visualization which includes principles and techniques. Students will learn the value of visualization, specific techniques in information visualization and scientific visualization. |
|
Learning Outcome |
|
CO1: Understand the usage of various visualization structures like tables,tree,network etc.,
CO2: Evaluate information visualization systems and other forms of visual presentation for their effectiveness CO3: Design and build data visualization system |
Unit-1 |
Teaching Hours:6 |
UNIT 1
|
|
Value of Visualization – What is Visualization and Why do it: External representation – Interactivity – Difficulty in Validation. Data Abstraction: Dataset types – Attribute types – Semantics. Task Abstraction – Analyze, Produce, Search, Query. | |
Unit-2 |
Teaching Hours:6 |
UNIT 2
|
|
Four levels of validation – Validation approaches – Validation examples. Marks and Channels. Rules of thumb – Arrange tables: Categorical regions – Spatial axis orientation – Spatial layout density. Arrange spatial data: | |
Unit-3 |
Teaching Hours:6 |
UNIT 3
|
|
Geometry – Scalar fields – Vector fields – Tensor fields. Arrange networks and trees: Connections, Matrix views – Containment. Map color: Color theory, Color maps and other channels. | |
Unit-4 |
Teaching Hours:6 |
UNIT 4
|
|
Manipulate view: Change view over time – Select elements – Changing viewpoint – Reducing attributes. Facet into multiple views: Juxtapose and Coordinate views | |
Unit-5 |
Teaching Hours:6 |
UNIT 5
|
|
Partition into views – Static and Dynamic layers – Reduce items and attributes: Filter – Aggregate. Focus and context: Elide – Superimpose – Distort – Case studies. | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI232 - DATA ENGINEERING AND KNOWLEDGE REPRESENTATION (2024 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:3 |
Course Objectives/Course Description |
|
To provide a foundational knowledge of data engineering and knowledge representation. To store , retrieve, analyze and design data for various applications To represent different sorts of knowledge, such as uncertain or incomplete knowledge, |
|
Learning Outcome |
|
CO1: To store and retrieve data effectively CO2: To analyze the data from different sources
CO3: To analyze and design knowledge based systems
|
Unit-1 |
Teaching Hours:9 |
DATA ENGINEERING and DATA MODELS
|
|
Data Engineering Introduction to Data Engineering - Data Engineering versus Data Science – Data Engineering tools– Data Engineering Lifecycle Data Models
Data Systems – Reliability – Scalability – Maintainability -Data Models and Query Languages. - Relational Model Versus Document Model - Query Languages for Data -Query Languages for Data,Declarative Queries on the Web ,MapReduce Querying ,Graph-Like Data Models Property Graphs ,The Cypher Query Language ,Graph Queries in SQL ,Triple-Stores and SPARQL | |
Unit-2 |
Teaching Hours:9 |
BUILDING DATA PIPELINES
|
|
Introduction – Data Engineering ecosystem - Building data pipelines—Extract, Transform, Load -ETL Process – Data Structures related to Database – Other data integration methods – Benefits and Challenges of ETL – ETL tools
Data Warehousing - Stars and Snowflakes: Schemas for Analytics- Column-Oriented Storage - Column Compression -Sort Order in Column Storage - Writing to Column-Oriented Storage | |
Unit-3 |
Teaching Hours:9 |
DATA STORAGE AND RETRIEVAL
|
|
Data Storage and Retrieval Non Relational data Non Relational data – NoSQL- Language-Specific Formats JSON, XML, and Binary Variants - Modes of Dataflow Dataflow Through Databases DATA in Distributed systems
Data in distributed systems – Partitioning and Replication - Partitioning of Key-Value Data - Partitioning and Secondary Trouble with Distributed Systems- Faults and Partial Failures - Unreliable Networks - Unreliable Clocks | |
Unit-4 |
Teaching Hours:9 |
Knowledge Representation
|
|
Knowledge Representation - Ontological Engineering - Categories and Objects . Events - Mental Events and Mental Objects - Reasoning Systems for Categories - Reasoning with Default Information Uncertain knowledge and reasoning- Quantifying Uncertainty - Acting under Uncertainty - Basic Probability Notation | |
Unit-5 |
Teaching Hours:9 |
Knowledge Representation in an uncertain domain
|
|
Probabilistic Reasoning-Representing Knowledge in an Uncertain Domain -The Semantics of Bayesian Networks -Efficient Representation of Conditional Distributions -Exact Inference in Bayesian Networks -Relational and First-Order Probability Models | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI233 - DESIGN AND ANALYSIS OF ALGORITHMS (2024 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:3 |
Course Objectives/Course Description |
|
This core course covers principles of algorithm design, elementary analysis of algorithms, and fundamental data structures. The emphasis is on choosing appropriate data structures and designing correct and efficient algorithms to operate on these data structures. |
|
Learning Outcome |
|
CO1: Analyze the complexity of polynomial algorithms.
CO2: Apply various design strategies for solving problems
CO3: Distinguish NP hard and NP complete problems from other problems
|
Unit-1 |
Teaching Hours:9 |
UNIT 1
|
|
Algorithms as technology – Analyzing and Designing algorithms – Asymptotic notations – Recurrences – Methods to solve recurrences – Heap Sort - Quick Sort – Sorting in linear time – Radix sort – Selection in linear time. Introduction: Algorithms, Pseudo code for expressing algorithms, performance analysis Space complexity, Time Complexity, Asymptotic notation- Big oh notation, omega notation and theta notation | |
Unit-2 |
Teaching Hours:9 |
UNIT 2
|
|
Divide and conquer methodology – Multiplication of large integers – Strassen's matrix multiplication – Greedy method – Prim's algorithm – Kruskal's algorithm – algorithm for Huffman codes, Knapsack problem, Spanning trees, Minimum cost spanning trees, Single source shortest path problem. | |
Unit-3 |
Teaching Hours:9 |
UNIT 3
|
|
Dynamic Programming: General method, applications- Matrix chained multiplication,
Optimal binary search trees, 0/1 Knapsack problem, All pairs shortest path problem, Traveling sales person problem, Reliability design. | |
Unit-4 |
Teaching Hours:9 |
UNIT 4
|
|
Backtracking: General method, Applications- n-queue problem, Sum of subsets problem, Graph coloring, Hamiltonian cycles. | |
Unit-5 |
Teaching Hours:9 |
UNIT 5
|
|
Branch and Bound: General method, applications- Travelling sales person problem, 0/1 Knapsack problem- LC branch and Bound solution, FIFO branch and Bound solution. NP-Hard and NP-Complete Problems: Basic concepts, Non deterministic algorithms, NP-Hard and NP Complete classes | |
Text Books And Reference Books: [1] Fundamentals of Computer Algorithms, Ellis Horowitz, SartajSahni and Rajasekharan, Universities press [2] Design and Analysis of Algorithms, P. h. Dave,2nd Edition, Pearson Education | |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI251 - RESEARCH PROJECT LAB - I (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:1 |
Course Objectives/Course Description |
|
This course is intended to carry out supervised research in a particular domain. The students are expected to identify, formulate and analyze the research problem. The students are also expected to conduct critical review of literature, choosing the study design, deciding on the sample design, become proficient in tools to solve the research problem. Students are expected to adhere research ethical practices at every phase of development and submit the intermediate reports.
|
|
Learning Outcome |
|
CO1: Identify and formulate the research problem in the chosen domain. CO2: Analyze the research gaps and propose the novel solutions to the chosen problem |
Unit-1 |
Teaching Hours:30 |
RESEARCH PROJECT
|
|
The students are expected to carry out the following: · Identify the background of research and conduct critical review of literature to understand the context. · Identification of research gaps · Formulate research questions/Objectives and hypothesis based on the research problem. · Methodology or approach intended to be adopted in the execution of the research · Expected outcome of research | |
Text Books And Reference Books: - | |
Essential Reading / Recommended Reading - | |
Evaluation Pattern CIA ESE 50% 5O% | |
MAI271 - JAVA PROGRAMMING (2024 Batch) | |
Total Teaching Hours for Semester:90 |
No of Lecture Hours/Week:8 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
This course will help the learner to gain sound knowledge in object-oriented principles, GUI application development, web application development and enterprise application development by using different features of Java technologies. |
|
Learning Outcome |
|
CO1: Understanding and applying the principles of object-oriented programming in the construction of robust, maintainable programs. CO2: Analyze the various societal and environmental problems critically to apply the concepts of generic, lambda and collections. CO3: Develop sustainable and innovative GUI/Web based/Enterprise solutions for real-time problems. |
Unit-1 |
Teaching Hours:18 |
INTRODUCTION TO OBJECT ORIENTED PROGRAMMING (OOP) AND CLASSES
|
|
Introduction to Object Oriented Programming (OOP) Object-Oriented Programming (OOP) Principles- Class Fundamentals - Declaring Objects - Introducing Methods - Overloading methods – Constructors - Parameterized Constructors - this Keyword. Class Features Garbage Collection - the finalize () Method - Introducing Access Control - Understanding static - Introducing nested and inner classes - String class - String Buffer Class - Command Line Arguments. Lab Exercises: 1. Identify a domain of your choice, list out ten entities in the domain. For each entity, identify minimum 10 attributes and assign the data type for each attribute with proper justification. 2. Implement the concept of class, data members, member functions and access specifiers, function overloading and constructor overloading
3. Implement the features of static keyword, command line argument, String class and String Buffer class | |
Unit-2 |
Teaching Hours:18 |
INHERITANCE, INTERFACES & PACKAGES AND MULTITHREADING IN JAVA
|
|
Inheritance in Java Inheritance Basics - Multilevel Hierarchy- Using super - Method overriding - Dynamic Method Dispatch- Abstract keyword- Using final with inheritance - The Object Class. Interfaces and Packages Inheritance in java with Interfaces – Defining Interfaces - Implementing Interfaces - Extending Interfaces- Creating Packages - CLASSPATH variable - Access protection - Importing Packages - Interfaces in a Package. Multithreading Java Thread Model - Life cycle of a Thread - Java Thread Priorities - Runnable interface and Thread Class- Thread Synchronization – Inter Thread Communication. Lab Exercises: 4. Implement the concept of inheritance, super, abstract and final keywords. 5. Implement the concept of package and interface.
6. Implement the concept of multithreading. | |
Unit-3 |
Teaching Hours:18 |
GENERICS, LAMBDA AND THE COLLECTIONS FRAMEWORK
|
|
Generics Generics Concept - General Form of a Generic Class – Bounded Types – Generic Class Hierarchy - Generic Interfaces – Restrictions in Generics. Lambda Expression Introduction to Lambda expression- Block Lambda Expressions - Generic Functional Interfaces - Passing lambda expressions as arguments - Lambda expressions and exceptions- Lambda expressions and variable capture. The Collections Framework The Collections Overview – Collection Interface – List Interface – Set Interface – SortedSet Interface – Queue Interface - ArrayList Class – LinkedList Class – HashSet Class – Using an Iterator – The For Each Statement. Working with maps – The map interfaces, the map classes. Comparators- the collection algorithms Lab Exercises: 7. Implement the concept of Generics 8. Implement the concept of the lambda expression
9. Implement the concept of a collection framework | |
Unit-4 |
Teaching Hours:18 |
JAVA BEANS AND JDBC
|
|
JDBC Introduction to JDBC- Connecting to the database- Basic JDBC Operations – Essential JDBC Classes – JDBC Drivers – JDBC-ODBC Bridge – Connecting to a database with driver manager – JDBC database URL. JAVA BEANS Java beans - Advantages of Beans – Introspection- Bound and Constrained Properties – Persistence – Customizers - The JavaBeans API. JAVA SWING Swing Basics – Components and Containers – JLabel and ImageIcons- JTextField – Swing Buttons – JTabbedPane – JScrollPane – JList – JComboBox – JTable – Swing Menus. Lab Exercises: 10. Implement the concept of JDBC and Java Beans
11. Implement the features of java swing package | |
Unit-5 |
Teaching Hours:18 |
JAVA SERVLETS & JSP
|
|
JAVA SERVLETS Servlets Basics – Life Cycle of a Servlet –A Simple Servlet - The Servlet API – Servlet Interfaces – Generic Servlet Class- HttpServletRequest Interface – HttpServeltResponse JSP The JSP development model – component of jsp page – Page directive – Action – scriptlet – JSP expression, JSP Syntax and semantics, JSP in XML. Lab Exercises: 12. Implement the concept of java servlets
13. Implement the concept of JSP | |
Text Books And Reference Books: [1] Schildt Herbert, Java : The Complete Reference, Tata McGraw- Hill, 11 th Edition,2019 [2] The complete reference JSP 2.0, Tata McGraw- Hill, 2nd Edition, Phil Hanna
| |
Essential Reading / Recommended Reading [1] Cay S Horstmann, Core Java Volume 1 Fundamentals, Prentice Hall, 11th Edition, 2018. | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI272 - ADVANCED MACHINE LEARNING (2024 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:4 |
Course Objectives/Course Description |
|
This course covers the most popular machine learning algorithms such as regression techniques with a modern outlook focusing on the recent advances and examples. It also aims to provide the foundations for dimensionality reduction techniques and clustering techniques with their applications to solve real world problems. |
|
Learning Outcome |
|
CO1: Demonstrate classification and clustering techniques
CO2: Evaluate different models used for feature selection
CO3: Understand the strengths and weaknesses of many popular machine learning techniques.
CO4: Design and implement various machine learning algorithms in a range of real-world applications
|
Unit-1 |
Teaching Hours:15 |
REGRESSION METHODS
|
|
Understanding Regression: Simple Linear regression - Ordinary least squares estimation - Gradient Descent - multiple linear regression - Multivariate linear regression – Polynomial regression – Regularization – Ridge and Lasso Regression - Understanding regression trees and model trees - Logistic regression - Bias and Variance Trade-off – Overfitting and underfitting models. Self-Study: Support Vector Regression, Decision Tree Regression – Random Forest Regression Lab Exercises: 1. Implement various types of linear regression techniques
2. Explore non-linear regression techniques | |
Unit-2 |
Teaching Hours:15 |
DIMENSIONALITY REDUCTION
|
|
Factor Analysis, Low Variance Filter, High Correlation Filter, Backward Feature Elimination – Forward Feature Selection – Principal Component Analysis – Factor Analysis – Multidimensional Scaling - Linear Discriminant Analysis – Independent Component Analysis – Isomap – Maximum Relevance Minimum Redundancy Self-Study: - Combining Multiple Learners Lab Exercises: 1. Demonstrate Feature selection
2. Explore and compare PCA, LDA and ICA techniques | |
Unit-3 |
Teaching Hours:15 |
Unsupervised Learning
|
|
Cluster Analysis - Partitioning Methods – K-Means – K-Medoids – Hierarchical Methods – Agglomerative Vs Divisive – Distance measures in algorithmic methods – BIRCH – Chameleon – Probabilistic Hierarchical Clustering – Evaluation of Clustering: Assessing clustering Tendency – Determining the Number of Clusters – Measuring Clustering Quality Lab Exercises: 1. Demonstrate K-Means algorithm with optimum number of clusters 2. Demonstrate Hierarchical clustering
3. Evaluate quality of clusters | |
Unit-4 |
Teaching Hours:15 |
Reinforcement Learning
|
|
Introduction – Single State Case: K-Armed Bandit – Elements of Reinforcement Learning – Model-Based Learning – Temporal Difference Learning – Generalization – Partially Observable States Self-study and Discussion: Case Studies and recent applications. Lab Exercises: 1. Explore model based reinforcement learning
| |
Unit-5 |
Teaching Hours:15 |
Neural Networks
|
|
Application scope of Neural Networks – Fundamental Concept of ANN: The Artificial Neural Network – Biological Neural Network – Comparison between Biological neuron and Artificial Neuron – Evolution of Neural Network. Basic models of ANN – Learning Methods – Activation Functions – Importance Terminologies of ANN – Single / Multilayer perceptron Lab Exercises: 1. Calculate the output of a simple neuron using binary and bipolar sigmoidal activation functions
2. Demonstrate classification using MLP | |
Text Books And Reference Books: [1] Introduction to Machine Learning, E. Alpaydin, 3rd Edition, MIT Press, 2014. [2] Data Mining Concept and Techniques, Jiawei Han, Micheline Kamber, Jian Pie, Morgan and Kauf [3] S.N.Sivanandam, S. N. Deepa, Principles of Soft Computing, Wiley-India, 3rd Edition,2018.
Note: Scikit learn python library can be used for lab exercises. | |
Essential Reading / Recommended Reading [1] Reinforcement Learning: An Introduction, Richard S. Sutton and Andrew G. Barto, Bradford Books, 2018 [3] Machine Learning with R: Expert techniques for predictive modeling, Brett Lantz, 3rd
Edition, Packt Publishing, 2019 | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI331A - AI IN AGRICULTURE (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
To explore the current and potential applications of AI and various technologies in agriculture, such as crop monitoring, yield prediction, soil analysis, Plant Disease Identification and pest control to improve the agriculture productivity in India |
|
Learning Outcome |
|
CO1: To Understand the basic concepts and techniques of artificial intelligence and how they can be applied in the field of agriculture.
CO2: To develop skills in the design and implementation of AI & IoT-based agriculture systems. |
Unit-1 |
Teaching Hours:6 |
Smart Farming using Artificial Intelligence
|
|
Introduction – Role of AI in advanced farming - Role of IoT in advanced farming - Role of Robotics in advanced farming – Smart Farming – Smart Agriculture – AI in Agriculture - How Data Analytics Transforming Agriculture – Agricultures Data Analytics Benefits – Challenges of AI in Agriculture - Case Study | |
Unit-2 |
Teaching Hours:6 |
Precision Agriculture
|
|
History of Precision Agriculture – Introduction – Components – Tools and Techniques – Site Specific Crop Management – VRA & VRT – Adoption of Smart Precision Agriculture - Modern Day Agriculture – Smart Precision Agriculture – Agriculture Digital Farming – Benefits – Soil Management – High Accuracy in Disease prediction, Detection and Control – Application of WSN in Precision Agriculture | |
Unit-3 |
Teaching Hours:6 |
AI and Data Analytics in Agriculture
|
|
Prediction of Crop Yield and Pest Disease Infestation – Prediction system for Cropyield and livestock – Climate Condition Monitoring and Automated Systems – Decision Making system for Crop Selection based on Soil. | |
Unit-4 |
Teaching Hours:6 |
Agriculture Data Mining and Information Extraction
|
|
Introduction – Data Mining Techniques in Farming – Case Studies in Agricultural Data Mining – Research Challenges – Machine Learning and its Application in Food Processing and Preservation. | |
Unit-5 |
Teaching Hours:6 |
Modern Agricultural Applications using AI
|
|
Introduction – Smart farming Tools – Technological Advancements – Climate – Smart Agriculture – Evolution of Cutting Edge Technologies that are revolutionizing the Agriculture in India – Smart Farming Applications - Future Scope and Challenges. | |
Text Books And Reference Books: [1]Artificial Intelligence and Smart Agriculture Technology, Utku Gose, V B Surya Prasath, Hossain, Subrato Bharati, Prajoy Podder, CRC Press,1st Edition 2022
[2]AI, Edge and IoT-based Smart Agriculture, Ajith Abraham, Sujata Dash, Joel J.P.C. Rodrigues, Academic Press, 2021,Agriculture 5.0,Latief Ahmad, Firasath Nabi,CRC Press 2021 | |
Essential Reading / Recommended Reading [1]Smart farming technologies for sustainable Agricultural Development, Digital Computer Fundamentals, Floyd, Thomas L, Pearson International, 11th Edition, 2015
[2]Smart farming technologies for sustainable Agricultureal Development, Poonia, Ramesh C., Gao, Xiao-Zhi, Raja, Linesh,IGI Global, 2018 | |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI331B - AI IN CYBER SECURITY (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
To select suitable ethical principles and commit to professional responsibilities and human values and contribute value and wealth for the benefit of the society. |
|
Learning Outcome |
|
CO1: Identify existing legal framework and laws on cyber security. CO2: Apply the security aspects of social media platforms and ethical aspects associated with use of social media. |
Unit-1 |
Teaching Hours:6 |
Introduction to AI for Cyber security
|
|
Applying AI in cyber security-The evolution from expert systems to data mining and AI-The different forms of automated learning-The characteristics of algorithm training and Optimization-Beginning with AI via Jupyter Notebooks-Introducing AI in the context of cyber security. | |
Unit-2 |
Teaching Hours:6 |
AI for Cyber Security Arsenal
|
|
Classification-Regression-Dimensionality Reduction-Clustering-Video anomaly detection Natural Language processing (NLP) for Social media analysis-Large-scale image Processing.
| |
Unit-3 |
Teaching Hours:6 |
Detecting Cyber Security Threats with AI
|
|
How to detect spam with Perceptron’s- Image spam detection with support vector machines (SVMs)-Phishing detection with logistic regression and decision Trees-Spam detection with Naive Bayes-Spam detection adopting NLP | |
Unit-4 |
Teaching Hours:6 |
Protecting Sensitive Information and Assets
|
|
Authentication abuse Prevention-Account Reputation Scoring-User authentication with keystroke Recognition-Biometric authentication with facial recognition. | |
Unit-5 |
Teaching Hours:6 |
Fraud Prevention with AI Solutions
|
|
How to leverage machine learning (ML) algorithms for fraud Detection-How bagging and boosting techniques can improve an algorithm's Effectiveness-How to analyze data with Jupyter Notebook-How to resort to statistical metrics for results evaluation. | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading [1] Cyber Security Understanding Cyber Crimes, Computer Forensics and Legal Perspectives by Sumit Belapure and Nina Godbole, Wiley India Pvt. Ltd.
[2] Data Privacy Principles and Practice by Natraj Venkataramanan and Ashwin Shriram, CRC Press. | |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI331C - AI IN COGNITIVE SCIENCES (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
It is designed to be a challenging course, involving significant independent work, readings, assignments, and projects. It covers structured knowledge representations, as well as knowledge-based methods of problem solving, planning, decision-making, and learning in cognitive system with help of AI models. |
|
Learning Outcome |
|
CO1: To understand the basics and fundamental concepts, methods, and prominent issues in knowledge-based artificial intelligence CO2: To understand the specific skills and abilities needed to apply those concepts to the design of knowledge-based AI agents
CO3: To find the relationship between knowledge-based artificial intelligence and the study of human cognition |
Unit-1 |
Teaching Hours:6 |
Introduction and Fundaments
|
|
Introduction to Knowledge-Based AI – Where KB AI fits into AI as a whole - Cognitive systems: what are they? - AI and cognition: how are they connected?
Fundamentals- Semantic Networks - Generate & Test - Means-Ends Analysis - Problem Reduction - Production Systems | |
Unit-2 |
Teaching Hours:6 |
Common Sense Reasoning and Planning
|
|
Frames - Understanding - Common Sense Reasoning - Scripts - Logic - Planning | |
Unit-3 |
Teaching Hours:6 |
Learning and Analogical Reasoning
|
|
Learning by Recording Cases - Incremental Concept Learning - Classification - Version Spaces & Discrimination Trees- Case-Based Reasoning - Explanation-Based Learning - Analogical Reasoning | |
Unit-4 |
Teaching Hours:6 |
Visuospatial Reasoning and Design & Creativity
|
|
Constraint Propagation - Visuospatial Reasoning- Configuration - Diagnosis - Design - Creativity | |
Unit-5 |
Teaching Hours:6 |
Metacognition
|
|
Learning by Correcting Mistakes - Meta-Reasoning - AI Ethics | |
Text Books And Reference Books: 1. Artificial Intelligence: A Modern Approach. Stuart J., and Peter Norvig. 2nd ed. Upper Saddle River, N.J.: Prentice Hall/Pearson Education, 2003. ISBN: 0137903952 | |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI332A - BIG DATA ANALYTICS (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
The student can understand the Big Data Platform and its Use cases and get an overview of Apache Hadoop. The course will provide HDFS Concepts and Interfacing with HDFS and the student can understand Map Reduce Jobs. It provides knowledge in NOSQL Data Base, Apache Hadoop architecture, ecosystem, and explores related applications including HDFS, Spark, and MapReduce with Hive and Pig. |
|
Learning Outcome |
|
CO1: To explore the fundamental concepts of big data analytics. CO2: Provide an overview of Apache Hadoop with NOSQL and REDIS Data Store
CO3: Understand Map Reduce Jobs/spark framework for processing Big Data for Analytics. |
Unit-1 |
Teaching Hours:6 |
INTRODUCTION TO BIG DATA ANALYTICS
|
|
Big Data Overview: Data Structures - Analyst Perspective on Data Repositories - State of the Practice in Analytics - Current Analytical Architecture - Drivers of Big Data - Emerging Big Data Ecosystem and a New Approach to Analytics - Key Roles for the New Big Data Ecosystem - Examples of Big Data Analytics. | |
Unit-2 |
Teaching Hours:6 |
NOSQL BIG DATA MANAGEMENT
|
|
NoSQL Definition and introduction - Document databases – MongoDB - Storing data and accessing data from MongoDB - Querying MongoDB - Document store internals - MongoDB reliability and durability - Horizontal scaling - CRUD operations in MongoDB - Creating and using indexes in MongoDB.
Understanding Key/Value Stores in Memcached and Redis-Eventually Working with Column-Oriented Databases-HBase Distributed Storage Architecture. | |
Unit-3 |
Teaching Hours:6 |
UNDERSTANDING MAPREDUCE
|
|
Introduction to Hadoop and MapReduce Programming Hadoop Overview, HDFS (Hadoop Distributed File System), Processing– Data with Hadoop, Managing Resources and Applications with Hadoop YARN (Yet Another Resource Negotiator). Introduction to MAPREDUCE Programming: Introduction, Mapper, Reducer, Combiner, Partitioner, Searching, Sorting, Compression | |
Unit-4 |
Teaching Hours:6 |
HIVE
|
|
Introduction to Hive - Hive Architecture - Characteristics - Comparison with RDBMS (Traditional Database) – HIVE modes – HIVE Server2(HS2) - Hive Data Types and File Formats - Hive Data Model - Hive Integration and Workflow Steps -Hive Built-in Functions - HiveQL - HiveQL. Data Definition Language (DDL) - HiveQL. Data Manipulation Language (DML) - HiveQL for Querying the Data - Aggregation - Join - Group by Clause. | |
Unit-5 |
Teaching Hours:6 |
SPARK
|
|
Introduction - Spark and Big Data Analytics Spark - Introduction to Big Data Tool-Spark - Introduction to Data Analysis with Spark - Spark SQL - Using Python Advanced Features with Spark. | |
Text Books And Reference Books: [1] Raj Kamal, Preeti Saxena, Big Data Analytics, Introduction to Hadoop, Spark, and Machine-Learning, McGraw-Hill India, 2019. [2] Boris lublinsky, Kevin t. Smith, Alexey Yakubovich, Professional Hadoop Solutions, Wiley, 2015. [3] Gaurav Vaish, Getting Started with NoSQL, Packt Publishing,2013.
[4] High performance spark by Holden Karau and Rachel Warren published by O’Reilly Media 2017. | |
Essential Reading / Recommended Reading [1] Pethuru Raj, Anupama Raman, Dhivya Nagaraj and Siddhartha Duggirala, High-Performance Big-Data Analytics: Computing Systems and Approaches, Springer, 2015. [2] Jonathan R. Owens, Jon Lentz and Brian Femiano, Hadoop Real-World Solutions Cookbook, Packt Publishing, 2013. [3] Garry Turkington, Hadoop Beginner's Guide, Packt Publishing, 2013. [4] John Sharp, Data Access for Highly-Scalable Solutions: Using SQL, NoSQL, and Polyglot Persistence,Microsoft,2013 | |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI332B - AUGMENTED REALITY AND VIRTUAL REALITY (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
This course will introduce students to the concepts and applications of Augmented Reality and Virtual Reality technologies. Students will learn the fundamentals of AR/VR, the differences between the two, and how to create AR/VR applications. The course will cover a variety of topics such as AR/VR hardware, software, 3D modeling, user interfaces, and interaction design. |
|
Learning Outcome |
|
CO1: Understand the fundamentals of AR/VR
CO2: Understand the process to create AR/VR Applications CO3: Develop user interfaces for AR/VR |
Unit-1 |
Teaching Hours:6 |
Introduction to AR/VR
|
|
Overview of AR/VR, Brief history of AR/VR, Differences between AR and VR, Advantages and Disadvantages of AR/VR, Applications of AR/VR | |
Unit-1 |
Teaching Hours:6 |
AR/VR Hardware and Software
|
|
AR/VR devices, software and sensors, VR headsets and controllers, AR/VR software platforms, AR/VR development tools. | |
Unit-2 |
Teaching Hours:6 |
AR/VR Design Principles
|
|
Interaction design principles for AR/VR, User interface design for AR/VR, Human factors in AR/VR design | |
Unit-2 |
Teaching Hours:6 |
AR/VR Content Creation
|
|
Introduction to 3D modeling, Creating 3D assets for AR/VR, creating models for AR/VR, adding interactivity to AR/VR experiences, Texturing and lighting for AR/VR. Using Unity3D or Unreal Engine for AR/VR development. | |
Unit-3 |
Teaching Hours:6 |
AR/VR Deployment
|
|
Testing and debugging AR/VR applications, Deploying AR/VR applications to devices, AR/VR best practices | |
Unit-3 |
Teaching Hours:6 |
AR/VR Development
|
|
Designing intuitive interfaces for AR/VR, User interface considerations for different AR/Vr devices, Developing AR/VR applications, AR/VR programming languages, AR/VR frameworks and libraries, Best practices for AR/VR UI.
| |
Unit-4 |
Teaching Hours:6 |
AR/VR Project Development
|
|
AVR emerging technologies, potential future applications, challenges and opportunities. | |
Unit-5 |
Teaching Hours:6 |
PROJECT
|
|
Students will work on their AR/VR projects - AR/VR Project Presentation - Students will present their AR/VR projects to the class - Industry Visit/ Experiential Learning
| |
Text Books And Reference Books: Bernhard Jung (Editor), Paul Grimm (Editor), Ralf Doerner (Editor), Wolfgang Broll (Editor),”Virtual and Augmented Reality (Vr/Ar): Foundations and Methods of Extended Realities (Xr)” ,Springer; 1st ed. 2022 edition 13 January 2022 | |
Essential Reading / Recommended Reading Bernhard Jung (Editor), Paul Grimm (Editor), Ralf Doerner (Editor), Wolfgang Broll (Editor),”Virtual and Augmented Reality (Vr/Ar): Foundations and Methods of Extended Realities (Xr)” ,Springer; 1st ed. 2022 edition 13 January 2022 | |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI332C - FORENSIC SCIENCES (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
To provide extensive knowledge about computer forensic and recognize diverse aspects of forensics science. It is also used to acquire the knowledge to examine and analyze evidence from image, video, email, data, document, mobile and network. |
|
Learning Outcome |
|
CO1: Develop fundamental knowledge and skills required to understand contemporary computer forensics. CO2: Design and develop solutions for complex forensic problems
|
Unit-1 |
Teaching Hours:6 |
Contemporary Computer Crime
|
|
Web-Based Criminal Activity: Interference with Lawful Use of Computer. Malware: Viruses and Worms-DoS and DDoS Attacks- Botnets and Zombie Armies- Spam- Ransomware and the Kidnapping of Information. Theft of Information, Data Manipulation, and Web Encroachment: Traditional Methods of Proprietary Information Theft-Trade Secrets and Copyrights- Political Espionage. Terrorism: Cyberterrorism- Threatening and Harassing Communications-Cyberstalking and Cyber harassment- Cyberbullying. | |
Unit-2 |
Teaching Hours:6 |
Image and video forensics
|
|
Image Forensics: Importance of image forensic detection, Active Methods: Digital watermarking, digital signatures. Passive methods: Image source identification, image tamper detection.
Video Forensics: Active approaches, Blind approaches: copy-move, splicing, Frame insertion, frame deletion, frame duplication, frame replacing, frame shuffling | |
Unit-3 |
Teaching Hours:6 |
E-Mail and Web Forensics
|
|
Opening Pandora’s Box of E-Mail-Following the route of e-mail packets- Becoming Exhibit A- Scoping Out E-Mail Architecture: E-mail structures- E-mail addressing- E-mail lingo- E-mail in motion- Seeing the E-Mail Forensics Perspective: Dissecting the message- Expanding headers- Checking for e-mail extras- Extracting e-mail from clients- Getting to know e-mail file extensions- Copying the e-mail- Printing the e-mail- Investigating Web-Based Mail- Searching Browser Files- Looking through Instant Messages | |
Unit-4 |
Teaching Hours:6 |
Data and Document Forensics
|
|
Delving into Data Storage- Finding Digital Cavities Where Data Hides- Extracting Data- Rebuilding Extracted Data- Document Forensics: Finding Evidential Material in Documents: Metadata- Honing In on CAM (Create, Access, Modify) Facts- Discovering Documents. | |
Unit-5 |
Teaching Hours:6 |
Mobile & Network Forensics
|
|
Mobile Forensics: Keeping Up with Data on the Move- Making a Device Seizure- Cutting-Edge Cellular Extractions- Network Forensics: Mobilizing Network Forensic Power- Identifying Network Components- Saving Network Data. Wiretap Act-Communications Assistance for Law Enforcement Act-Foreign Intelligence Surveillance Act-Comprehensive Crime Control Act-Electronic Communications Privacy Act and the Privacy Protection Act. | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI351 - RESEARCH PROJECT LAB - II (2024 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:1 |
Course Objectives/Course Description |
|
The students are expected to reveal the core competency aimed by this course which includes
development of effective solution to the chosen problem, deployment of solution and research findings. The students are expected to submit the final report as well as they are expected to defend their research work. |
|
Learning Outcome |
|
CO1: Analyze proposed solutions to the identified research problem CO2: Develop a solution to the problem and analyze results. |
Unit-1 |
Teaching Hours:30 |
RESEARCH PROJECT LAB ? II
|
|
| |
Text Books And Reference Books: nvl | |
Essential Reading / Recommended Reading Relevant solutions for the research problem. | |
Evaluation Pattern CIA - 100% | |
MAI371 - DEEP LEARNING (2024 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:4 |
Course Objectives/Course Description |
|
The main objective of this course is to make students comfortable with the tools and techniques required to handle large datasets. Several libraries and datasets publicly available will be used to illustrate the application of these algorithms. This will help students develop the skills required to gain experience of doing independent research and study. |
|
Learning Outcome |
|
CO1: Recognize the basic concepts and techniques of deep learning CO2: Evaluate and prepare to apply deep learning algorithms. CO3: Apply deep learning models for applications. CO4: Identify appropriate tools to implement the solutions to problems related for deep learning. |
Unit-1 |
Teaching Hours:15 |
DEEP FEEDFORWARD NETWORKS
|
|
An overview of ANN, Back Propagation Neural Networks, Deep Feedforward Networks: Deep network for Universal Boolean function representation, classification and Approximation, perceptron Learning, Perceptron with activation functions Lab Exercises: 1. Demonstrate MLP in Keras/Tensorflow
2. Demonstrate Deep Feedforward Network | |
Unit-2 |
Teaching Hours:15 |
REGULARIZATION FOR DEEP MODELS
|
|
Regularization for Deep models: L2 and L1 Regularization, Constrained Optimization and Under- Constrained, Early Stopping, Parameter Tying and Parameter Sharing, Sparse representations, Dropout Lab Exercises: 1. Demonstrate Regularization L1 for Deep learning model
2. Demonstrate Regularization L2 for Deep learning model | |
Unit-3 |
Teaching Hours:15 |
CONVOLUTIONAL NEURAL NETWORK
|
|
The Convolution Operation, Pooling, Structured Outputs, Variants of convolution, Variants of CNN – ImageNet, Alexnet, VGG16, ResNet, Applications in Computer Vision Lab Exercises: 1. Demonstrate Convolution Neural Network
2. Demonstrate VGG16 or ResNet | |
Unit-4 |
Teaching Hours:15 |
RECURRENT NEURAL NETWORKS
|
|
Sequence Processing, Unfolding Computational Graphs, Training recurrent networks The Long Short-Term Memory (LSTM), Optimization for Long- Term Dependencies, Encoder-Decoder Sequence-to-Sequence processing Lab Exercises: 1. Demonstrate Recurrent Neural Network
2. Demonstrate Short-Term Long Memory (LSTM) | |
Unit-5 |
Teaching Hours:15 |
AUTOENCODERS
|
|
The architecture of autoencoders - relationship between the Encoder, Bottleneck, and Decoder, how to train autoencoders? Types of autoencoders: Undercomplete autoencoders, Sparse autoencoders, Contractive autoencoders, Denoising autoencoders, Variational Autoencoders Lab Exercises:
| |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI372 - NATURAL LANGUAGE PROCESSING (2024 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:4 |
Course Objectives/Course Description |
|
Students who complete this course will gain a foundational understanding in natural language processing methods and strategies. They will also learn how to evaluate the strengths and weaknesses of various NLP technologies and frameworks as they gain practical experience in the NLP toolkits available. Students will also learn how to employ literary-historical NLP-based analytic techniques like stylometry, topic modeling, synsetting and named entity recognition in their personal research. |
|
Learning Outcome |
|
CO1: To understand various approaches on syntax and semantics in NLP CO2: To apply various methods to discourse, generation, dialogue and summarization using NLP.
CO3: To analyze various methodologies used in Machine Translation, machine learning techniques used in NLP including unsupervised models |
Unit-1 |
Teaching Hours:15 |
INTRODUCTION
|
|
Introduction to NLP- Background and overview- NLP Applications -NLP hard Ambiguity- Algorithms and models, Knowledge Bottlenecks in NLP- Introduction to NLTK, Case study. Lab Exercises: 1. Write a program to tokenize text.
2. Write a program to count word frequency and to remove stop words. | |
Unit-2 |
Teaching Hours:15 |
PARSING AND SYNTAX
|
|
Word Level Analysis: Regular Expressions, Text Normalization, Edit Distance, Parsing and Syntax- Spelling, Error Detection and correction-Words and Word classes- Part-of Speech Tagging, Naive Bayes and Sentiment Classification: Case study. Lab Exercises: 3. Write a program to program to tokenize Non-English Languages
4. Write a program to get synonyms from WordNet | |
Unit-3 |
Teaching Hours:15 |
SMOOTHED ESTIMATION AND LANGUAGE MODELLING
|
|
N-gram Language Models: N-Grams, Evaluating Language Models -The language modelling problem | |
Unit-3 |
Teaching Hours:15 |
Semantic Analysis and Discourse Processing
|
|
Semantic Analysis: Meaning Representation-Lexical Semantics- Ambiguity-Word Sense Disambiguation. Discourse Processing: cohesion-Reference Resolution- Discourse Coherence and Structure. Lab Exercises: 5. Write a program to get Antonyms from WordNet 6. Write a program for stemming non-English words | |
Unit-4 |
Teaching Hours:15 |
NATURAL LANGUAGE GENERATION AND MACHINE TRANSLATION
|
|
Natural Language Generation: Architecture of NLG Systems, Applications. Machine Translation: Problems in Machine Translation-Machine Translation Approaches. Evaluation of Machine Translation systems. Case study: Characteristics of Indian Languages. Lab Exercises: 7. Write a program for lemmatizing words Using WordNet
8. Write a program to differentiate stemming and lemmatizing words | |
Unit-5 |
Teaching Hours:15 |
Unsupervised Methods in NLP
|
|
Graphical Models for Sequence Labelling in NLP. Lab Exercises: 9. Write a program for POS Tagging. 10. Write a program to implement Word Embeddings. 11. Case study-based program (IBM) or Sentiment analysis or ChatGpt | |
Unit-5 |
Teaching Hours:15 |
INFORMATION RETRIEVAL AND LEXICAL RESOURCES
|
|
Information Retrieval: Design features of Information Retrieval Systems-Classical, Non- classical, Alternative Models of Information Retrieval – valuation Lexical Resources: Word Embeddings - Word2vec-Glove.
| |
Text Books And Reference Books: [1] Speech and Language Processing, Daniel Jurafsky and James H., 3rd Edition, Martin Prentice Hall, 2023.
[2] Foundations of Statistical Natural Language Processing. Cambridge, MA: MIT Press,1999. | |
Essential Reading / Recommended Reading [1] Roland R. Hausser, Foundations of Computational Linguistics: Human computer Communication in Natural Language, Springer, 2014. [2] Steven Bird, Ewan Klein and Edward Loper, Natural Language Processing with Python, O’Reilly Media, First edition, 2009.
| |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI373 - COMPUTER VISION (2024 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:4 |
Course Objectives/Course Description |
|
The Objective of this course is to cover the basic theory and algorithms that are widely used in computer vision. Develop hands-on experience in using computers to process images for image enhancement, restoration, filtering and feature extraction to recognize objects. |
|
Learning Outcome |
|
CO1: Describe the theoretical background of image processing. CO2: Design various image enhancement methods and filtering techniques
CO3: Apply restoration, compression and segmentation methods in both frequency and spatial domain.
CO4: Perform feature extraction and classification using real time dataset. |
Unit-1 |
Teaching Hours:15 |
INTRODUCTION TO DIGITAL IMAGE PROCESSING
|
|
Fundamentals: Fundamental Steps in Image Processing, Elements of Digital Image Processing System, Image Sampling and Quantization, Basic relationships: Neighbors, Connectivity, Distance Measures between pixels, Image formation model, Grayscale and Color images representation, Introduction to Digital Video. Lab Exercises: 1. Program to perform Resize, Rotation of binary, Gray-scale and color images using various methods.
2. Demonstrate frame extraction from the video and display the color components of the images. | |
Unit-2 |
Teaching Hours:15 |
IMAGE ENHANCEMENT Spatial Domain
|
|
Gray Level Transformations, point operations, Histogram Processing, Histogram equalization, Basics of Spatial Filters, Smoothening and Sharpening Spatial Filters. | |
Unit-2 |
Teaching Hours:15 |
IMAGE ENHANCEMENT Frequency Domain
|
|
Introduction to Fourier Transform and the frequency Domain, Smoothing and Sharpening, Frequency Domain Filters, DCT, Homomorphic Filtering Lab Exercises: 3. Program to implement various image enhancement techniques using Built-in and user defined functions. 4. Program to implement Linear Spatial Filtering using Built-in and user defined functions
5. Program to implement Low and High Pass Filtering of images in frequency domain. | |
Unit-3 |
Teaching Hours:15 |
IMAGE RESTORATION AND IMAGE COMPRESSION
|
|
A model of the Image Degradation / Restoration Process, Noise Models, Restoration in the presence of Noise, Periodic Noise Reduction by Frequency Domain Filtering. Image Compression models: Huffman coding, Run length coding, LZW coding, JPEG. Lab Exercises: 6. Program to implement Non-Linear Spatial Filtering using Built-in and user defined functions
7. Demonstrate denoising of the images | |
Unit-4 |
Teaching Hours:15 |
IMAGE SEGMENTATION AND REPRESENTATION
|
|
Point, Line and Edge detection, Thresholding – Basic global thresholding, optimum global thresholding using Otsu’s Method. Region Based Segmentation – Region Growing and Region Splitting and Merging. Representation – Chain codes, Polygonal approximations using minimum perimeter polygons. Lab Exercises: 8. Demonstrate Edge detection using various methods.
9. Perform frame extraction from the video and display the color components of the images. | |
Unit-5 |
Teaching Hours:15 |
DESCRIPTION AND OBJECT RECOGNITION
|
|
Boundary descriptors – Fourier descriptors, regional descriptors –Topological descriptors. Introduction to Patterns and Pattern Classes: Minimum distance classifier, K-NN classifier. Object detection and recognition – Face recognition (Eigen faces).
Lab Exercises: 10. Program to demonstrate Fourier descriptors 11. Extracting feature descriptors from the image dataset. 12. Implement image classification using extracted relevant features. | |
Text Books And Reference Books: [1] Digital Image Processing, R. C. Gonzalez & R. E. Woods, Pearson Education, 4th Edition, 2018. [2] Fundamental of Digital Image Processing, A.K. Jain, PHI, 4th Edition, 2011. [3] Digital Image Processing Using MATLAB, Rafael C. Gonzalez, Richard E. Woods and Steven L Eddins, PHI, 2nd Edition, 2017.
[4] Computer Vision: Algorithms and Applications, Richard Szeliski, Springer Science & Business Media, 2nd Edition, 2022. | |
Essential Reading / Recommended Reading [1] Digital Image Processing: An algorithmic approach, M. A. Joshi, PHI, 2nd Edition 2009.
[2] Digital Image Processing and analysis, B.Chanda, D. DuttaMajumdar, PHI, 1st Edition, 2011. | |
Evaluation Pattern CIA - 50% ETE - 50% | |
MAI431 - INTERNET OF THINGS (2023 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:3 |
Course Objectives/Course Description |
|
By completing the syllabus, the students will learn basics of Internet of Things (IoT), and its execution using multiple robotic sensors and they will be able to impart knowledge on the infrastructure, sensor technologies and networking technologies of Internet of Things (IoT). They will learn to analyze, design, and develop IoT solutions and to know the use of AI in IoT. |
|
Learning Outcome |
|
CO1: Evaluate the components of the IoT ecosystem within the context of the robotic paradigm. CO2: Examine fundamental circuits, sensors, data conversion processes, and shield libraries for interfacing with the physical world. CO3: Apply embedded programming constructs and principles of Tiny ML for practical implementation. CO4: Demonstrate the process of prototyping IoT solutions to address real-world socio-economic challenges. |
Unit-1 |
Teaching Hours:9 |
Introduction to IoT:
|
|
IoT Fundamentals- Definition & Characteristics of IoT - Challenges and Issues - Physical Design of IoT, Logical, Design of IoT - IoT Functional Blocks, Security. IoT Reference Architecture- Control Units – Communication modules – Bluetooth – Zigbee – Wi-fi – GPS- IOT Protocols(IPv6, 6LoWPAN, RPL, CoAP etc..), MQTT, Wired Communication, Power Sources, Technologies behind IoT -Four pillars of IOT paradigm, - RFID, Wireless Sensor Networks, SCADA (Supervisory Controland Data Acquisition), M2M - IOT Enabling Technologies – Big-Data Analytics, Cloud Computing, Embedded Systems. | |
Unit-2 |
Teaching Hours:9 |
IoT Physical Devices and Endpoints :
|
|
Introduction to Sensors and Actuator- Sensor and Actuator Characteristics- Primary factors driving the deployment of sensor technology. Generations of IoT sensors-Industrial sensors, First Generation, Advanced Generation, Integrated IoT Sensors –Sensors' Swarm, Printed Electronics, IoT Generation Roadmap. Introduction to different IoT tools, Developing application through IoT tools, developing sensor based application through embedded system platform, implementing IoT concepts with python. | |
Unit-3 |
Teaching Hours:9 |
Introduction to Arduino and Raspberry Pi
|
|
Introduction to Arduino and Raspberry Pi- Controlling Hardware- Connecting LED, Buzzer, Controlling AC Power devices with Relays, Controlling servo motor, speed control of DC Motor, Sensors- Light sensor, Temperature and Humidity Sensor DHT11, Motion Detection Sensors etc. Introduction to ESP32/8266- programming with micro-python and connectivity with cloud using wi-fi module | |
Unit-4 |
Teaching Hours:9 |
IoT Architecture and Development model of Edge Computing
|
|
IoT Architecture and Development model of Edge Computing IoT General Architecture, IoT architecture with AI, Issues and Challenges in IoT with cloud AI, Revised IoT architecture with Fog AI and Edge AI, Tiny ML working principle, Tiny ML as SaaS model, High Computing Machine based architecture, Distributed Training, Compression techniques. Case Study e.g. Water management in public utilities. | |
Unit-5 |
Teaching Hours:9 |
Programming framework for Internet of Things
|
|
IoT Programming Approaches: Node-Centric Programming - Database approach - Model-Driven Development - IoT Programming Frameworks: Contiki and Cooja, Communication Technologies for Low Power WirelessInteractions e.g. RPL and analysis through simulator. Introduction to Wireshark and Foren6 as data analytical tools. | |
Text Books And Reference Books: Essential Reading / Recommended Reading [1] Tsiatsis, Vlasios, Tsiatsis, Vlasios, Stamatis Karnouskos, Jan Holler, David Boyle, and Catherine Mulligan, Internet of Things: technologies and applications for a new age of intelligence, 2nd edition, Academic Press, 2018. [2] DiMarzio J. F., Beginning Android Programming with Android Studio, 4th edition., Wiley,2016 | |
Essential Reading / Recommended Reading [1] Donald Norris, The Internet of Things: Do-It-Yourself Projects with Arduino, Raspberry Pi, and BeagleBone Black, 1st edition, McGraw Hill Education, 2015 [2] Simone Cirani, Gianluigi Ferrari, Marco Picone, Luca Veltri. Internet of Things: Architectures, Protocols and Standards, 1st edition, Wiley Publications, 2019. [3] Peter Warden and Daniel Situnayake. Tiny ML: Machine Learning with Tensorflow Lite on Arduino and Ultra-Low-Power Microcontrollers, o'reilly, January 2020 Note: Unit 1 & Unit 2 Textbook 2, Unit 3 Textbook 1, Unit 4 Textbook 3 and for Unit 5 web resources are preferable | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI432 - MULTI AGENT SYSTEMS (2023 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
Course Objectives This course introduces the fundamental concepts and techniques in Artificial Intelligence and Machine Learning. It covers both theoretical aspects and practical applications through hands-on labs.
|
|
Learning Outcome |
|
CO1: Understand the basic components to build a multiagent system CO2: Evaluate the different multi agent learning approaches
|
Unit-1 |
Teaching Hours:6 |
AGENT ARCHITECTURE AND ORGANIZATIONS
|
|
Introduction to Intelligent Agents – Examples of Agents – Intelligent Agents – Agents and Objects – Agents and Expert systems – Architecture for Intelligent Agents – Belief-Desire-intention Architecture – Layered Architecture – InteRRaP - Applications
| |
Unit-2 |
Teaching Hours:6 |
MULTI AGENT ORGANIZATION
|
|
Introduction – Background – From Intelligent Agents to Multi Agents – From Multi Agent Systems to Multiagent organization – Sources of Inspiration – Autonomy and Regulation – Examples – Multiagent Organization – OperA Framework – Institutions – Events and states – Example of Institutional modelling – InstAL – Agents in organizations.
| |
Unit-3 |
Teaching Hours:6 |
AGENT COMMUNICATIONS
|
|
Conceptual Foundations of Communication in Multi agent systems – Communicative Acts – Agent Communication Primitives – Commitment based multiagent approaches – Commitment – Commitment Protocol Specification – Evaluation with respect to multiagent systems – Engineering with Agent Communication – Programming with communications – Modelling communications – Communication based methodologies – Advanced topics and challenges | |
Unit-4 |
Teaching Hours:6 |
TRUST AND REPUTATION IN MULTIAGENT SYSTEMS
|
|
Computational representation of trust values - Trust and Reputation as beliefs – Trust Process in Multiagent System – general overview – Trust Evaluations – Trust Decisions – Coping up with diversity of trust models – Reputation in multiagent societies – Reputation building process – Centralized and Decentralized models – Using reputation – Pitfalls when using reputation – Combining trust and reputation models with other agreement technologies.
| |
Unit-5 |
Teaching Hours:6 |
MULTIAGENT LEARNING
|
|
Introduction – Challenges in Multiagent Learning – Reinforcement Learning for Multiagent Systems – Evolutionary Game theory as a Multiagent learning paradigm – Swarm Intelligence as a Multiagent Learning paradigm – Neuro Evolution as a Multiagent Learning paradigm – Case study
| |
Text Books And Reference Books:
Multiagent Systems - Algorithmic, Game-Theoretic, and Logical Foundations by Yoav Shoham, Kevin Leyton-Brown · 2008, Cambridge University Press
| |
Essential Reading / Recommended Reading
Multiagent Systems, Gerhard Weiss, The MIT Press, Cambridge, Massachusetts, London, England, 2nd Edition, 2013
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI451 - SPECIALIZATION PROJECT (AI_ML PROJECT) (2023 Batch) | |
Total Teaching Hours for Semester:60 |
No of Lecture Hours/Week:6 |
Max Marks:100 |
Credits:3 |
Course Objectives/Course Description |
|
This course is designed to provide students with real-world project development and deployment environments. |
|
Learning Outcome |
|
CO1: Ability to identify and develop socially and environmentally relevant deployment environments. CO2: Ability to apply appropriate design/development methodology and tools.
CO3: Develop competence to work as a team and effective division of work (Work Diary)
CO4: Ability to complete the solution as a product CO5: Professional computing practices and regulations |
Unit-1 |
Teaching Hours:60 |
Specialization project
|
|
Specialization project | |
Text Books And Reference Books: NA | |
Essential Reading / Recommended Reading NA | |
Evaluation Pattern CIA 50% ETE 50% | |
MAI471 - CLOUD COMPUTING (2023 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
This course presents a top–down view of cloud computing, from applications and administration to programming and infrastructure. Students will gain knowledge on the state–of–the–art solutions for cloud computing developed by Google, Amazon, Microsoft, etc. Students will utilize existing Machine Learning based Cloud services to solve relevant problems. |
|
Learning Outcome |
|
CO1: Understand various service delivery models of a cloud computing architecture CO2: Demonstrate and evaluate the basic cloud technologies and services
CO3: Select and apply Machine Learning Pipeline Cloud services to resolve business problems
CO4: Label, build, train, and deploy a custom Machine Learning model using NLP/Image Recognition services through a guided, hands on approach in Cloud environments
|
Unit-1 |
Teaching Hours:15 |
OVERVIEW OF CLOUD COMPUTING
|
|
Overview – Characteristics – Deployment Models – Service Models – Cloud Architecture – Cloud Service Delivery Platforms Virtualization – Load Balancing – Scalability & Elasticity Deployment – Replication – Monitoring – Service Level Agreements – Security – Billing. Lab Exercises: 1. Demonstration of Cloud Service Delivery Platforms
2. Creating and running compute machines using AWS/GCP/Azure | |
Unit-2 |
Teaching Hours:16 |
BASIC CLOUD SERVICES
|
|
Identity and Access Management Services – Compute Services – Amazon Elastic Compute Cloud – Google Compute Engine – Windows Azure Virtual Machines – Storage Services – Amazon Simple Storage Service – Google Cloud Storage – Database Services – Amazon Relational Data Store – Amazon DynamoDB – Google Cloud SQL – Google Cloud Datastore. Lab Exercises:
| |
Unit-3 |
Teaching Hours:15 |
MACHINE LEARNING SERVICES IN CLOUD
|
|
Machine Learning – Types of ML – Business Use Cases – ML Pipeline – Python Tools and Libraries – Machine Learning Frameworks and infrastructure – ML managed Services – ML Challenges – Amazon SageMaker – Implementing a ML pipeline with Amazon SageMaker. Lab Exercise:
1. Creation of models using ML Pipeline Cloud Services | |
Unit-4 |
Teaching Hours:16 |
FORECAST AND IMAGE RECOGNITION CLOUD SERVICES
|
|
Amazon Forecast: Overview – Processing Timeseries Data – Amazon Forecast Workflow – Forecast Algorithms – Evaluating Forecast. Computer Vision: Overview – Image and Video Analytics – Facial Recognition – Amazon Rekognition – Preparing Custom Datasets for Computer Vision – Labelling images with Amazon Ground Truth. Lab Exercises: 1. Perform Video Analysis using Cloud Recognition Service
2. Implement Forecasting Service | |
Unit-5 |
Teaching Hours:13 |
CLOUD BASED NATURAL LANGUAGE PROCESSING SERVICES
|
|
Overview – NLP Managed Services: Amazon Transcribe – Amazon Comprehend – Amazon Polly – Amazon Translate – Cloud Natural Language API. Lab Exercises: 1. Create a Chatbot using NLP cloud services
2. Analyze text, identify entities, Extract information using NLP API | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI472 - PRINCIPLES OF LARGE LANGUAGE MODELS (2023 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
This course aims to explore the principles and applications of Large Language Models (LLMs). It covers the foundations of language models, implementation of conversational agents, transformers in natural language processing, domain-specific models, and advanced topics in large language models. |
|
Learning Outcome |
|
CO1: Understand the basic principles and components of Large Language Models. CO2: Implement and fine-tune language models for specific tasks. CO3: Explore the integration of domain-specific models into applications. CO4: Investigate advanced topics, including combining multiple language models and ethical considerations in language generation. |
Unit-1 |
Teaching Hours:15 |
FOUNDATIONS OF LANGUAGE MODELS
|
|
Overview of language models and their significance-Key Characteristics of LLMs-Types of language models: discriminative vs. generative-Historical evolution of language models-Role of language models in natural language understanding-Introduction to LangChain and its role in LLM development-Key features and components of LangChain-Setting up the LangChain environment for development-Utilizing transfer learning techniques in language modeling-Concept of prompt engineering in fine-tuning models-Optimizing prompts for specific language tasks-Understanding the impact of prompt formulation on model output Lab Exercises: 1.Implement transfer learning to fine-tune a language model on a specific dataset.
Self-Learning: NLP Tokenization, Word Embeddings and Sequence Modelling | |
Unit-2 |
Teaching Hours:15 |
BASIC TRANSFORMER USAGE
|
|
Basic understanding of transformer model architecture-Components like self-attention and feed-forward layers-Simple illustration of transformer operations-Use cases of transformers in language tasks-Basics of using transformers for text classification-Overview of pre-trained transformer models-Introduction to using transformers for text generation-Basic techniques for generating creative text with transformers Lab Exercises: 2.Develop a simple transformer model using a basic deep learning library.
3.Implement a basic text generation task using transformers. | |
Unit-3 |
Teaching Hours:15 |
TRANSFORMERS IN NATURAL LANGUAGE PROCESSING
|
|
Evolution of NLP models and the significance of transformers-Key advantages of transformers over traditional methods-Challenges and limitations in implementing transformers-In-depth exploration of the transformer architecture-Mathematical foundations behind transformer operations-Introduction to BERT and its significance in NLP-Bidirectional context representation in BERT-BERT for sequence classification-BERT for token classification-BERT for question/answering-Overview of RoBERTa as an optimization of BERT-Key differences and improvements in RoBERTa architecture-Comparative analysis of BERT and RoBERTa in various NLP tasks Lab Exercises: 5.Implement fine-tuning procedures on BERT for sentiment analysis. 6.Implement BERT for token classification in NER tasks.
7.Develop a sequence-to-sequence transformer model for language translation using PyTorch. | |
Unit-4 |
Teaching Hours:15 |
DOMAIN-SPECIFIC MODELS
|
|
Understanding the need for domain-specific language models-The role of fine-tuning in creating domain-specific models-Considerations for ethical and responsible use of domain-specific models-Techniques for fine-tuning LLMs for domain-specific applications-An overview of domain adaptation and transfer learning-Integrating user feedback for continuous improvement in domain-specific models-Leveraging prompt engineering in domain-specific model interactions Lab Exercises: 8.Implement tokenization and encoding for the legal text dataset.
9.Develop a Python script to load the fine-tuned model and tokenizer. | |
Unit-5 |
Teaching Hours:15 |
APPLICATIONS AND FUTURE TRENDS OF LARGE LANGUAGE MODELS
|
|
Modern Large Language Models-GPT-3 and ChatGPT-Tailoring large language models for industry-specific use cases-Applications in finance, healthcare, legal, and other sectors-Introduction to multimodal applications integrating text and other modalities-Use of large language models in conjunction with image and audio data-Future directions and challenges in advancing multimodal AI with LLMs-Emerging trends in large language models and AI research-Ethical considerations in shaping the future of AI and LLMs Lab Exercises: 10.Develop a Python script for handling multimodal inputs.
| |
Text Books And Reference Books:
2. Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs,Ben Auffarth,Packt Publishing,1st edition,2023 | |
Essential Reading / Recommended Reading
| |
Evaluation Pattern ETE = 50% CIA = 50% | |
MAI473A - ADVANCED DATA ANALYTICS (2023 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:2 |
Course Objectives/Course Description |
|
This course is designed to develop proficiency in advanced data analysis methods, including machine learning algorithms, statistical models, and predictive analytics. This course explores the ethical implications of data analytics, focusing on privacy, bias, and responsible use of data in decision-making processes. This course also analyzes real-world case studies and practical applications of advanced data analytics across different industries, gaining insights into industry best practices. |
|
Learning Outcome |
|
CO1: Understand the advanced data analysis methods CO2: Apply principles and techniques to social media and image data CO3: Implement classification and Clustering techniques for real-world text and image data. |
Unit-1 |
Teaching Hours:9 |
INTRODUCTION
|
|
Introduction to advanced data analytics techniques, Need for Advanced Data Analytics, Statistical Methods for Data Analysis: Time series analysis, Complexities of modern datasets, Recent Technologies and Frameworks for Data Analytics, Role of data analytics in Text, Social Media, and Image. Ethical considerations related to data analytics. Lab Exercises: 1. Implementation of time series analysis based on web data. | |
Unit-2 |
Teaching Hours:9 |
TEXT ANALYTICS
|
|
Text Preprocessing- TF-IDF, NER, N-gram modeling. Mining Textual Data: Text Clustering, Text Classification Lab Exercises: 2. Implementation of text classification and clustering with TF-IDF and N-gram. | |
Unit-3 |
Teaching Hours:9 |
SOCIAL MEDIA ANALYTICS
|
|
Essentials of Social Graphs, Social Networks, Models, Information Diffusion in Social Media. Analyzing social media: Behavioral Analytics, Influence, and Homophily, Recommendation in social media. Lab Exercises: 3. Implementation of user Behavioral Analysis on any social media. | |
Unit-4 |
Teaching Hours:9 |
IMAGE ANALYTICS
|
|
Image Representation and Image Processing- Segmentation-Image Coding and Compression - Lossless compression versus lossy compression-Measures of the compression efficiency- Hufmann, Recent Trends in Image analytics, Introduction to Video Analytics. Lab Exercises: 4. Implementation of Image classification and Image Clustering 5. Compare Compression Techniques. | |
Unit-5 |
Teaching Hours:9 |
CASE STUDIES:
|
|
Predictive Analytics for Patient Admissions - Location-based Case study using GIS, Healthcare: Image Analytics for health image, - 3D image Analytics using CT scans. | |
Text Books And Reference Books: [1].John Atkinson-Abutridy, Text Analytics: An Introduction to the Science and Applications of Unstructured Information Analysis, CRC Press, 2022 [2]. Rafael C. Gonzalez and Richard E. Woods, Digital Image Processing, Third Ed., Prentice-Hall,2020 | |
Essential Reading / Recommended Reading [1] William K. Pratt, Digital Image Processing, John Wiley, 4th Edition, 2020. 2. Anil K. Jain [2] Fundamentals of Digital Image Processing, Prentice Hall of India,2020 Web Resources: 2. https://keras.io/examples/vision/3D_image_classification/ | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI473B - WEB MINING (2023 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:2 |
Course Objectives/Course Description |
|
To provide students with a comprehensive understanding of the principles and techniques used in web mining, exploring various approaches to extract knowledge and insights from the vast amount of data available on the web. |
|
Learning Outcome |
|
CO1: Analyze web page structure and extract relationships between websites using web structure mining techniques CO2: Discover user behavior patterns and build recommendation systems based on web usage mining methods CO3: Extract meaningful information and knowledge from web content using text mining and information retrieval techniques CO4: Classify opinions and sentiment expressed on the web, identify aspects and sentiment towards entities, and potentially detect spam |
Unit-1 |
Teaching Hours:9 |
Information Retrieval & Web Search:
|
|
Basic concepts of Information Retrieval- Relevance Feedback- Evaluation Measures- Text and Web page pre-processing- Inverted Index and it’s compression- Latent Semantic Indexing- Web Search-Meta Search-Combing Multiple Rankings- Web Spamming Lab Exercises:
2. Web Page Analysis and Spam Detection
| |
Unit-2 |
Teaching Hours:9 |
Web Structure Mining:
|
|
Social Network Analysis- Co-citation and Bibliographic Coupling- Page Rank-HITS-Community Discovery Web Crawling – Basic crawler Algorithm- Implementation Issues- Universal Crawlers- Focused Crawlers- Tropical Crawlers- Evaluation-Crawler Ethics and Conflicts-Some New Developments Lab Exercises
| |
Unit-3 |
Teaching Hours:9 |
Web Content Mining:
|
|
Wrapper Induction- Instance Based Wrapper Learning- Automatic Wrapper Generation problems- String matching and Tree Matching- Multiple Alignments- Building DOM Trees- Extraction based on a single list page- Extraction based on Multiple Pages Information Integration- Introduction to Schema Matching- Pre-processing for schema matching- Domain and Instance level Matching- Combining Similarities- 1:m Match- Integration of Web query interfaces- Constructing a Unified Global Query Interface Lab Exercises
| |
Unit-4 |
Teaching Hours:9 |
Opinion Mining and Sentiment Analysis
|
|
The Problem of Opinion Mining- Document Sentiment Classification-Sentence Subjectivity and Sentiment Classification- Opinion Lexicon Expansion- Aspect Based Opinion Mining- Mining Comparative Opinions- Opinion Search and Retrieval- Opinion Spam Detection- Utility of Reviews Lab Exercises
| |
Unit-5 |
Teaching Hours:9 |
Web Usage Mining
|
|
Data Collection and Preprocessing- Data Modelling for Web Usage Mining- Discovery and Analysis of Web Usage patterns- Recommended Systems and Collaborative Filtering- Query Log Mining Lab Exercises
| |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI473C - BUSINESS INTELLIGENCE (2023 Batch) | |
Total Teaching Hours for Semester:45 |
No of Lecture Hours/Week:4 |
Max Marks:100 |
Credits:2 |
Course Objectives/Course Description |
|
The aim of Business Intelligence course is to explain the Analytics and Decision Support system in complex business senarios.it aims to illustrate neural network, sentiment analysis, decision making and various data visualization techniques in real time scenarios. |
|
Learning Outcome |
|
CO1: Explain the Business Intelligence, Analytics and Decision Support system
CO2: Explore with the basic rudiments of business intelligence system CO3: Understand the modeling aspects behind Business Intelligence analytics and expert systems. |
Unit-1 |
Teaching Hours:9 |
An Overview of Business Intelligence, Analytics, and Decision Support
|
|
Changing Business Environments and Computerized Decision Support, Managerial Decision Making, Information Systems Support for Decision Making, An Early Framework for Computerized Decision Support, The Concept of Decision Support Systems (DSS), A Framework for Business Intelligence (BI), Business Analytics Overview. Exercises:
1. Import the legacy data from different sources such as (Excel, SqlServer, Oracle etc.) and load in the target system. | |
Unit-2 |
Teaching Hours:9 |
Descriptive Analytics
|
|
Data Warehousing Process Overview, Data Warehousing Architectures, Data Integration and the Extraction, Transformation, and Load (ETL) Processes, Data Warehouse Development, Real-Time Data Warehousing. Business Reporting Definitions and Concepts, Data and Information Visualization, Different Types of Charts and Graphs, Performance Dashboards. Exercises: 1. Perform the Extraction Transformation and Loading (ETL) process to construct the database in the Sqlserver / Power BI.
2. Data Visualization from ETL Process. | |
Unit-3 |
Teaching Hours:9 |
Predictive Analytics
|
|
Basic Concepts of Neural Networks, Developing Neural Network–Based Systems, Support Vector Machines, Text Mining Process, Text Mining Tools, Sentiment Analysis Process, Sentiment Analysis and Speech Analytics, Web Content and Web Structure Mining, Web Usage Mining, Web Analytics Maturity Model and Web Analytics Tools, Social Media Analytics.
Exercises:
| |
Unit-4 |
Teaching Hours:4 |
Prescriptive Analytics
|
|
Decision Support Systems Modeling, Structure of Mathematical Models for Decision Support, Decision Modeling with Spreadsheets, Mathematical Programming Optimization, Multiple Goals, Sensitivity Analysis, What-If Analysis, and Goal Seeking, Decision Analysis with Decision Tables and Decision, Multi-Criteria Decision Making With Pairwise Comparisons, Problem-Solving Search Methods, Genetic Algorithms and Developing GA Applications. Exercises: 1.Implementation of Classification algorithm.
2. Practical Implementation of Decision Tree. | |
Unit-5 |
Teaching Hours:9 |
Big Data and Future Directions for Business Analytics
|
|
Big Data and Analytics, Big Data Technologies, Geospatial Analytics, Cloud Computing and BI, Issues of Legality, Privacy, and Ethics, An Overview of the Analytics Ecosystem: Reporting/Analytics, Predictive Analytics, Prescriptive Analytics.
Exercises: 1.Prediction Using Linear Regression
2.Data Analysis using Time Series Analysis
| |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading [1] Ramesh Sharda, Dursun Delen, EfraimTurban, J.E.Aronson,Ting-Peng Liang, David King, “Business Intelligence and Analytics: System for Decision Support”, 10th Edition, Pearson Global Edition, 2013 | |
Evaluation Pattern CIA 50% ETE 50% | |
MAI531 - HUMAN COMPUTER INTERACTION (2023 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
The course aims to offer foundational understanding of interaction levels, design models, techniques, and validations within human-computer interface and interactions, foster design-oriented thinking for evaluating interactive design. |
|
Learning Outcome |
|
CO1: Ability to design an interactive design with cognitive aspects and data interpretation CO2: Discover the requirements for the good interactive design prototypes with the evaluation of design |
Unit-1 |
Teaching Hours:6 |
INTRODUCTION TO INTERACTIVE DESIGN
|
|
Good Design and Poor Design – Interaction design – User Experience – Understanding users- Process of Interactive design – Practical Issues – Conceptualizing Interaction | |
Unit-2 |
Teaching Hours:6 |
CONGNITIVE ASPECTS AND TYPES OF INTERACTION
|
|
Cognition – Frameworks – Social Interaction – Face to face – Remote - Co Presence – Social Engagement – Emotional : Emotions and User Experience – Annoying Interfaces – Affective and Emotional AI – Persuasive Technologies and Behavioual change – Anthropomorphism – Interface Types – Natural User Interfaces | |
Unit-3 |
Teaching Hours:6 |
IMPACTS OF DATA IN THE INTERACTIVE DESIGN
|
|
Data Gathering: – Five key issues – Data Recording – Interviews – Questionnaire- Observation. Data Analysis and Interpretation: Quantitative and Quantitative – Tools – Presentation .Data at Scale : Approaches – Visualization and Ethical Concern. | |
Unit-4 |
Teaching Hours:6 |
DISCOVERING REQUIREMENTS AND DESIGN PROTOTYPES
|
|
Requirements – Data gathering –Bringing Life – Personas and Scenario – Use cases – Prototype – Conceptual Design – Concrete Design – Generation of Prototypes
| |
Unit-5 |
Teaching Hours:6 |
PRACTISE AND EVALUATION OF DESIGN
|
|
Agile UX – Design patterns – Open Sources – Tools for design – Types of Evaluation – Evaluation Case studies – Issues – Usablity testing – Inspection – Analytics- Predictive Models | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI532A - GRAPH NEURAL NETWORK (2023 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
This course is designed to introduce foundations of graphs, building robust and scalable graph neural networks for complex and deep models. |
|
Learning Outcome |
|
CO1: Understand representation of graphs, its properties CO2: Explore different sampling methods CO3: Apply graph neural networks for creating deep models |
Unit-1 |
Teaching Hours:6 |
Foundations of Graphs
|
|
Graph Representations – Properties and Measures – Spectral Graph Theory – Graph Signal Processing – Complex Graphs – Computational Tasks on Graphs | |
Unit-2 |
Teaching Hours:6 |
Graph Embedding and Graph Neural Networks (GNN)
|
|
Graph Embedding for Simple Graphs – Graph Embedding on Complex Graphs – Graph Neural Networks: - The General GNN Frameworks – Graph filters – Graph Pooling – Parameter learning for Graph Neural Networks | |
Unit-3 |
Teaching Hours:6 |
Robust and Scalable Graph Neural Networks
|
|
Graph Adversarial Attacks – Graph Adversarial Defenses – Node-wise Sampling Methods – Layer-wise Sampling methods – Subgraph-wise Sampling Methods | |
Unit-4 |
Teaching Hours:6 |
Graph neural Networks for Complex Graphs and Deep models
|
|
Heterogeneous Graph Neural Networks – Bipartitie Graph Neural networks – Multidimensional Graph Neural Networks – Signed Graph neural networks – Hypergraph Neural networks – Dynamic Graph Neural Networks -Autoencoders on Graphs – Recurrent neural networks on Graphs – Variational Autoencoders on Graphs – Generative Adversarial Networks on Graphs | |
Unit-5 |
Teaching Hours:6 |
Applications
|
|
Graph Neural networks in Natural Language Processing – Computer Vision - Data Mining | |
Text Books And Reference Books: Deep Learning on Graphs, Cambridge University Press, 2021 | |
Essential Reading / Recommended Reading [1] Graph Neural Networks: Foundations, Frontiers, and Applications Hardcover – Import, 4 January 2022
[3] https://mitpress.ublish.com/book/knowledge-graphs-fundamentals-techniques-and-applications | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI532B - MODERN OPTIMIZATION TECHNIQUES (2023 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
This course is designed to provide an in-depth understanding of modern optimization techniques and their applications in various domains. |
|
Learning Outcome |
|
CO1: Understand the theoretical foundations of optimization techniques. CO2: Apply different optimization algorithms to solve real-world problems effectively. |
Unit-1 |
Teaching Hours:6 |
Fundamentals of Optimization
|
|
Introduction to Optimization, Convex Optimization, Non-Convex Optimization, Gradient Descent, Newton's Method, Constrained Optimization | |
Unit-2 |
Teaching Hours:6 |
Metaheuristic Optimization Techniques
|
|
Genetic Algorithms, Simulated Annealing, Particle Swarm Optimization, Ant Colony Optimization, Tabu Search, Differential Evolution | |
Unit-3 |
Teaching Hours:6 |
Evolutionary Strategies
|
|
Evolution Strategies, Genetic Programming, Evolutionary Algorithms for Multi-objective Optimization, Evolutionary Optimization for Dynamic Environments | |
Unit-4 |
Teaching Hours:6 |
Swarm Intelligence
|
|
Swarm Intelligence Fundamentals, Particle Swarm Optimization, Ant Colony Optimization, Artificial Bee Colony Algorithm, Firefly Algorithm, Bat Algorithm | |
Unit-5 |
Teaching Hours:6 |
Applications of Modern Optimization Techniques
|
|
Optimization in Machine Learning, Engineering Optimization Problems, Optimization in Finance, Optimization in Logistics and Supply Chain Management | |
Text Books And Reference Books:
Modern Optimization Methods for Science, Engineering and Technology” by G R Singha,Sirajuddin Ahmed and Rajesh Chamorshikar Paperback – Import, 20 November 2019 | |
Essential Reading / Recommended Reading NA | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI532C - MACHINE LEARNING FOR DATA PRIVACY (2023 Batch) | |
Total Teaching Hours for Semester:30 |
No of Lecture Hours/Week:3 |
Max Marks:50 |
Credits:2 |
Course Objectives/Course Description |
|
This program offers safeguards and instruments designed to protect data and analytics processes against potential threats, unauthorized access, and any malicious activities that could impact them, spanning both online and offline domains. The comprehensive coverage includes the security of data at rest, in transit, during processing, as well as safeguarding big data analytical models and machine learning techniques. |
|
Learning Outcome |
|
CO1: Learn to explore various types and properties of digital data privacy and types of attacks.
CO2: Examine data security solutions in machine learning techniques.
CO3: Demonstrate LDP mechanisms in data privacy controls.
|
Unit-1 |
Teaching Hours:6 |
BASIC TERMS, TECHNIQUES AND TYPES OF ATTACKS
|
|
Privacy-preserving data analysis, Basic Terms - The model of computation, Towards defining private data analysis, Formalizing differential privacy, about differential privacy promises. Threats and attacks for ML systems, Reconstruction attacks, Model inversion attacks
| |
Unit-2 |
Teaching Hours:6 |
ADVANCED CONCEPTS OF DIFFERENTIAL PRIVACY FOR MACHINE LEARNING
|
|
Applying differential privacy in machine learning - Input perturbation, Algorithm perturbation, Output perturbation. Differentially private supervised learning algorithms, Differentially private naive Bayes classification, Implementing differentially private naive Bayes classification, Differentially private logistic regression, Differentially private linear regression | |
Unit-3 |
Teaching Hours:6 |
ADVANCED LDP MECHANISMS FOR MACHINE LEARNING
|
|
Advanced LDP mechanisms - The Laplace mechanism for LDP, Duchi’s mechanism for LDP, The Piecewise mechanism for LDP, The Piecewise mechanism for LDP, Using LDP naive Bayes with continuous features. | |
Unit-4 |
Teaching Hours:6 |
PRIVACY-PRESERVING SYNTHETIC DATA GENERATION
|
|
Overview of synthetic data generation- about importance of synthetic data, Application aspects of using synthetic data for privacy preservation, Generating synthetic data, Private information sharing vs. privacy concerns, Using k-anonymity against re-identification attacks | |
Unit-5 |
Teaching Hours:6 |
BUILDING PRIVACY-ASSURED MACHINE LEARNING APPLICATIONS
|
|
Privacy-preserving machine learning techniques, Privacy protection in data processing and mining, Protecting privacy by modifying the input, Protecting privacy by modifying the input, Privacy-preserving data management and operations. | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
| |
Evaluation Pattern CIA-50% ETE-50% | |
MAI571 - SPEECH PROCESSING AND RECOGNITION (2023 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:7 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
This course enables the learners to understand fundamentals of speech recognition, speech production and representation. It also enables the learners to impart knowledge on automatic speech recognition and pattern comparison techniques. This course helps the learners to develop automatic speech recognition model for different applications. |
|
Learning Outcome |
|
CO1: Understand the speech signals and represent the signal in time and frequency domain. CO2: Analyze different signal processing and speech recognition methods. CO3: Implement pattern comparison techniques and Hidden Markov Models (HMM) CO4: Develop speech recognition system for real time problems. |
Unit-1 |
Teaching Hours:15 |
FUNDAMENTALS OF SPEECH RECOGNITION
|
|
Introduction- The Paradigm for Speech Recognition- Brief History of speech recognition research- The Speech Signal: The process of speech production and perception in human beings- the speech production system- representing speech in time and frequency domain- speech sounds and features. Lab Programs:
| |
Unit-2 |
Teaching Hours:15 |
SIGNAL PROCESSING AND ANALYSIS METHODS FOR SPEECH RECOGNITION
|
|
Introduction- spectral analysis models- the bank of filters front end processor- linear predictive coding model for speech recognition- vector quantization. Lab Programs: 3. Implement sampling and quantization techniques for the given speech signals.
4. Explore linear predictive coding model for speech recognition | |
Unit-2 |
Teaching Hours:15 |
APPROACHES TO AUTOMATIC SPEECH RECOGNITION BY MACHINE
|
|
The acoustic phonetic approach-The pattern recognition approach-The artificial intelligence approach. | |
Unit-3 |
Teaching Hours:15 |
PATTERN COMPARISON TECHNIQUES
|
|
Speech detection- distortion measure- Mathematical consideration- Distortion measure – Perceptual consideration- Spectral Distortion Measure- Incorporation of spectral dynamic feature into distortion measure- Time alignment and normalization. Lab Programs:
| |
Unit-4 |
Teaching Hours:15 |
THEORY AND IMPLEMENTATION OF HIDDEN MARKOV MODELS
|
|
Introduction- Discrete time Markov processes- Extension to hidden Markov Models- Coin - toss models- The urn and ball model- Elements of a Hidden Markov Model- HMM generator of observation- The three basic problems for HMM’s- The Viterbi algorithm- Implementation issues for HMM’s. Lab Programs: 7. Implement simple hidden Markov Model for a particular application. 8.Apply Viterbi dynamic programming algorithm to find the most likely sequence of hidden states.
| |
Unit-5 |
Teaching Hours:15 |
TASK ORIENTED APPLICATION OF AUTOMATIC SPEECH RECOGNITION
|
|
Task specific voice control and dialog- Characteristics of speech recognition applications- Methods of handling recognition error- Broad classes of speech recognition applications- Command and control applications- Voice repertory dialer- Automated call-type recognition- Call distribution by voice commands- Directory listing retrieval- Credit card sales validation. Lab Programs: 9. Demonstrate automatic speech recognition for Call distribution by voice commands.
10. Apply speech recognition system to access telephone directory information from spoken spelled names (Directory listing retrieval). | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading [1] Fundamentals of Speech Recognition, Lawrence R Rabiner and Biing- Hwang Juang. Prentice-Hall Publications, 20209.
[2] Introduction to Digital Speech Processing, Lawrence R. Rabiner, Ronald W. Schafer, Now Publishers, 2015. | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI572 - REINFORCEMENT LEARNING (2023 Batch) | |
Total Teaching Hours for Semester:60 |
No of Lecture Hours/Week:5 |
Max Marks:100 |
Credits:4 |
Course Objectives/Course Description |
|
This course aims at developing an understanding about the fundamental concepts in defining and simulating reinforcement learning, identifying, understanding and implementing various reinforcement learning algorithms. |
|
Learning Outcome |
|
CO1: Basic and deep understanding on reinforcement learning CO2: Illustrate Markov Decision related algorithms. CO3: Implement Monte Carlo methods for prediction CO4: Analyze temporal-difference learning and eligibility traces. |
Unit-1 |
Teaching Hours:12 |
Reinforcement Learning Problem and Multi-arm Bandits
|
|
Definition of a stochastic multi-armed bandit, A k-armed Bandit Problem, Definition of regret, Tracking a Nonstationary Problem, Upper-Confidence-Bound Action Selection, KL-UCB, Gradient Bandits. Lab:
Self-study topics: Basics of probability and linear algebra. | |
Unit-2 |
Teaching Hours:12 |
Finite Markov Decision Processes
|
|
Markov Decision Problem, policy, and value function, Reward models (infinite discounted, total, finite horizon, and average), Episodic & continuing tasks, Bellman's optimality operator, and Value iteration & policy iteration Lab: Implement Markov Decision Process (MDP) Simulation and Value Iteration
Develop a program to perform policy evaluation and improvement for a given MDP | |
Unit-3 |
Teaching Hours:12 |
Monte Carlo Methods
|
|
The Reinforcement Learning problem, prediction and control problems, Model-based algorithm, Monte Carlo methods for prediction, and Online implementation of Monte Carlo policy evaluation Lab: Implement Model-Free Prediction & Control With Monte Carlo (MC).
Extend the reinforcement learning environment to support model-based algorithms for decision-making. | |
Unit-4 |
Teaching Hours:12 |
Temporal-Difference Learning
|
|
Bootstrapping; TD(0) algorithm; Convergence of Monte Carlo and batch TD(0) algorithms; Model-free control: Q-learning, Sarsa, Expected Sarsa Lab: Implement the TD(0) algorithm for temporal-difference learning in a simulated environment, where an agent interacts with states and receives rewards.
Implement Q-learning and SARSA algorithms for action-value estimation and policy improvement. | |
Unit-5 |
Teaching Hours:12 |
Eligibility Traces
|
|
n-step returns; TD(λ) algorithm; Need for generalization in practice; Linear function approximation and geometric view; Linear TD(λ). Tile coding; Control with function approximation; Policy search; Policy gradient methods; Experience replay; Fitted Q Iteration; Case studies. Lab: Implement the TD(λ) algorithm with eligibility traces for temporal-difference learning in a simulated environment.
Implement policy gradient methods for policy search, such as REINFORCE or actor-critic algorithms. | |
Text Books And Reference Books:
| |
Essential Reading / Recommended Reading
2.Sugiyama, Masashi.“Statistical reinforcement learning: modern machine learning approaches,” First Edition, CRC Press,2015 | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI573A - SPATIAL TEMPORAL ANALYSIS (2023 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:5 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
The course is conceptualized to introduce students to both temporal and spatial statistical analysis. It guides students through the use of various tools for the study and interpretation of spatial and temporal data. The objective of the course is to acquaint students with fundamental methods that they might apply to additional study. It will cover the constraints of application as well as the physical interpretation of the data. Through the course, students will be able to analyze environmental data to make better decisions and manage resources more effectively. |
|
Learning Outcome |
|
CO1: Learn to explore and analyze the spatiotemporal data and Models.
CO2: Ability to synthesize and formulate mechanisms that can explain the presence or
absence of clusters and other patterns in spatiotemporal data.
CO3: Attain the comprehensive understanding on the spatiotemporal data.
CO4: Apply the models to solve the real-world spatiotemporal applications. |
Unit-1 |
Teaching Hours:15 |
INTRODUCTION TO SPATIOTEMPORAL DATA
|
|
Introduction: Types of data, Time Series data, Types of spatial data, collection of temporal and spatial data, preparation of data, Geographic Information Systems (GIS)-GIS components, functionalities of GIS. Analysis for trend detection and slope estimation: Parametric and Non-Parametric approach. Lab Exercise 1: Exploratory data analysis on Time Series data. Lab Exercise 2: Exploratory data analysis on Spatiotemporal data. | |
Unit-2 |
Teaching Hours:15 |
TIME SERIES ANALYSIS AND VISUALIZATION
|
|
Spatiotemporal Prediction, classification and clustering, components of spatiotemporal data, concept of stationarity, decomposition of time series. Geo-Python. Visualization of Spatial data (Graphs using Latitude and longitude, 3D Maps, Choropleth, Cartogram, Stream and area graph, Tree map, ArcGIS and QGIS) Lab Exercise 3: Implement the spatiotemporal prediction and visualize the insights using the spatiotemporal visualization methods. Lab Exercise 4: Implement Classification of Time Series dataset and visualize the insights. Lab Exercise 5: Implement Clustering of Time Series dataset and visualize the insights using the spatiotemporal visualization methods. | |
Unit-3 |
Teaching Hours:15 |
SPATIAL DATA ANALYSIS
|
|
Spatial data analysis, Descriptive and exploratory analysis, Point processes, Geostatistics: Spatial continuity, Kriging, Anisotropy, directional tolerance, variogram and types of variogram - relative variogram, correlogram, cross-variogram. Spatial interpolation- Inverse Distance Weighting (IDW) and Triangulated Irregular Networks (TIN), geographic regional data. Generalized Additive Models: - Estimation, Cross validation. Lab Exercise 6: Implementation of Geostatistics using Generalized Additive Models. Lab Exercise 7: Implement the Spatial Interpolation using temperature map. | |
Unit-4 |
Teaching Hours:15 |
MULTIVARIATE AND SPATIOTEMPORAL DATA
|
|
Multivariate and spatiotemporal data- Univariate and Multivariate data analysis, Spatiotemporal data. Spatial autocorrelation measures- Global and Local measures. Autocorrelation analysis: Estimation of Autocorrelation coefficient, Correlogram, Moving Average process, Autoregressive Process and Integrated Moving Average Process. Lab Exercise 8: Implement Spatiotemporal Traffic Flow Prediction. Lab Exercise 9: Autocorrelation analysis on Spatiotemporal data. | |
Unit-5 |
Teaching Hours:15 |
SPATIOTEMPORAL MODELS
|
|
Spatiotemporal models and its applications: Empirical Orthogonal Function, Canonical Correlation Analysis, Cross correlation analysis, Singular Spectrum Analysis, Contextual Mann-Kendall, Seasonal Trend Analysis. Lab Exercise 10: Implement the Canonical Correlation Analysis on Spatiotemporal Data. | |
Text Books And Reference Books: [1] Spatiotemporal Data Analysis, Gidon Eshel, Princeton University Press, 2011 [2] R. P. Haining and G. Li, Regression Modelling with Spatial and Spatial-Temporal Data, CRC Press, 2020. [3] R. P. Haining and G. Li, Modelling, Spatial and Spatial-Temporal Data: A Bayesian Approach, CRC Press, 2020. [4] Environmental Statistics, Methods and Applications, Barnett V, John Wiley & Sons, 2004 [5] Time Series Analysis Forecasting and Control, Box G.E.P., Jenkins G.M. and Reinsel G.C., Pearson Education, Third Edition, 2007 [6] Applied Geostatistics, Isaaks E.H. and Srivastava R.M., Oxford University Press, 1989 | |
Essential Reading / Recommended Reading [1] N. Cressie and C. K. Wikle, Statistics for Spatio-Temporal Data, John Wiley & Sons, 2015. [2] C. K. Wikle, A. Zammit-Mangion, and N. Cressie, Spatio-Temporal Statistics with R, CRC Press, 2019 [3] R. Bivand et al., Applied Spatial Data Analysis With R, New York: Springer, 2008. [4] G. W. Peters and T. Matsui, Modern Methodology and Applications in Spatial-Temporal Modeling, Springer, 2015. [5] N. Andrienko and G. Andrienko, Exploratory Analysis of Spatial and Temporal Data, Springer Science & Business Media, 2006. [6] J. F. Roddick and K. Hornsby, Temporal, Spatial, and Spatio-Temporal Data Mining, Springer, 2003 | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI573B - QUANTUM COMPUTING (2023 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:5 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
This course covers the basics of quantum computing, including complex numbers, linear algebra, and quantum mechanics postulates, along with practical skills in designing quantum gates, circuits, and error correction. Students will learn about quantum algorithms like Deutsch's and Grover's, explore quantum information theory, and understand pragmatic applications such as cryptography and Quantum Key Distribution for secure communication. |
|
Learning Outcome |
|
CO1: Understand foundational knowledge of quantum computing, including its fundamental principles, algorithms, and potential applications.
CO2: Develop proficiency in modelling quantum circuits using various quantum computation environments and frameworks, enabling the implementation and simulation of quantum algorithms. CO3: Acquire a deep understanding of quantum operations, including noise and error- correction techniques, and their significance in mitigating errors and enhancing the reliability of quantum computations.
CO4: Explore various quantum algorithms such as Deutsch's algorithm, the Deutsch' Jozsa
algorithm, the Quantum Fourier transform, Grover's Algorithm, and understand their
applications in solving computational problems exponentially faster than classical algorithms |
Unit-1 |
Teaching Hours:18 |
QUANTUM COMPUTING BASIC CONCEPTS
|
|
Complex Numbers - Linear Algebra - Matrices and Operators - Global Perspectives Postulates of Quantum Mechanics – Quantum Bits - Representations of Qubits - Superpositions Lab Exercise : Implementation of basic quantum operations using matrices and operators, simulating quantum gates and their effects | |
Unit-2 |
Teaching Hours:15 |
QUANTUM GATES AND CIRCUITS
|
|
Universal logic gates - Basic single qubit gates - Multiple qubit gates - Circuit development - Quantum error correction Lab Exercise: Development of quantum circuits to perform specific tasks or algorithms, with a focus on understanding gate composition and circuit optimization | |
Unit-3 |
Teaching Hours:15 |
QUANTUM ALGORITHMS
|
|
Quantum parallelism - Deutsch’s algorithm - The Deutsch–Jozsa algorithm - Quantum Fourier transform and its applications - Quantum Search Algorithms: Grover’s Algorithm Lab Exercise: Implementation and testing of quantum parallelism concepts through programming exercises, demonstrating the parallel processing capabilities of quantum algorithms | |
Unit-4 |
Teaching Hours:15 |
QUANTUM INFORMATION THEORY
|
|
Data compression - Shannon’s noiseless channel coding theorem - Schumacher’s quantum noiseless channel coding theorem - Classical information over noisy quantum channels Lab Exercise: simulating various error scenarios and evaluating error-correction techniques | |
Unit-5 |
Teaching Hours:12 |
PRAGMATICS AND MACHINE TRANSLATION
|
|
Classical cryptography basic concepts - Private key cryptography - Shor’s Factoring Algorithm - Quantum Key Distribution - BB84 - Ekart 91 Lab Exercise: implementing encryption algorithms, simulating Shor's Factoring Algorithm, and testing Quantum Key Distribution protocols for secure communication. | |
Text Books And Reference Books: [1] Parag K Lala, Mc Graw Hill Education, “Quantum Computing, A Beginners Introduction”, First edition,2020. [2] Michael A. Nielsen, Issac L. Chuang, “Quantum Computation and Quantum Information”, Tenth Edition, Cambridge University Press, 2010. | |
Essential Reading / Recommended Reading [1] Scott Aaronson, “Quantum Computing Since Democritus”, Cambridge University Press, 2013. [2] N. David Mermin, “Quantum Computer Science: An Introduction”, Cambridge University Press, 2007. | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI573C - PREDICTIVE ANALYTICS(CASE STUDY BASED APPROACH) (2023 Batch) | |
Total Teaching Hours for Semester:75 |
No of Lecture Hours/Week:5 |
Max Marks:150 |
Credits:5 |
Course Objectives/Course Description |
|
Predictive analytics is a field that leverages statistical algorithms and machine learning techniques to analyze historical data and make predictions about future events or outcomes. This course provides students with a comprehensive understanding of the principles, methodologies, and applications of predictive analytics across various domains such as business, finance, healthcare, and marketing. This course helps to provide comprehensive understanding of predictive analytics techniques through real-world case studies. students can learn the principles, theories, and practical applications of various evolutionary algorithms |
|
Learning Outcome |
|
CO1: Understanding of various evaluation metrics for predictive analytics.
CO2: Analyze and Design the various prediction models
CO3: Understanding and develop time series and forecasting models
CO4: Understanding and design predictive models using evolutionary approaches. |
Unit-1 |
Teaching Hours:15 |
Statistical Storytelling
|
|
Statistical Storytelling The Path from Multivariate Data to the Modeling Process -- Predictive Analytics - A Framework for Predictive Analytics Techniques-The Goal, Tasks, and Phases of Predictive Analytics- Ethical issues in predictive analytics -Privacy concerns and data protection regulations- Data Preprocessing - Model building (regression, classification and ensemble models) a) Case study: Exploratory analysis of a real-world dataset b) Case study: Ethical implications of using predictive models in healthcare c) Case study: Predicting sales using regression analysis LAB Exercises: 1. Exploratory Analysis of a Real world application 2. Building Predicting model using regression/classifier/ensemble approach | |
Unit-2 |
Teaching Hours:15 |
Statistical Metrics for Predictive Analytics
|
|
Statistical Metrics for Predictive Analytics Model Evaluation metrics(MAE,MSE, RMSE, RMSLE, R2, adjusted R2, for Regression model, Overfitting and Model tuning- Cross-validation and resampling methods - Hyperparameter tuning for model optimization- Model Evaluation Metrics ( Accuracy, confusion matrix, precision, recall, f1 score, AUC, logistic loss) for classifier models- Model Evaluation metrics ( extrinsic Measures: Rand Index, Mutual Information, V-measure, Fowlkes-Mallows Scores, Intrinsic Measures: Silhouette Coefficient, Calinski-Harabasz Index, Davies-Bouldin Index) for clusters d)Case study: Customer churn prediction (classification) e) Case study: Credit risk assessment using ensemble methods f) Case study: Market segmentation analysis (clustering) Lab Exercises: 3. Hyper parameter tuning and Evaluation metrics for Regression model 4. Hyper parameter tuning and Evaluation metrics for Classifier model | |
Unit-3 |
Teaching Hours:15 |
Time Series Analysis
|
|
Time Series Analysis Basic concepts in time series modeling- Times Series Visualization and Descriptive Statistics- Plotting time series data: line plots, scatter plots, and histograms -Calculating descriptive statistics: mean, variance, autocorrelation, and partial autocorrelation - Identifying patterns and trends in time series data- Time Series Decomposition- Trend estimation techniques: moving averages, exponential smoothing - Autoregressive Integrated Moving Average (ARIMA) Models- Model selection and diagnostics: ACF, PACF, Box-Jenkins methodology- Model fitting and diagnostics for seasonal time series data - Double and triple exponential smoothing (Holt-Winters method) g) Case study: Stock market analysis h) Case studies from various domains (e.g., healthcare, finance, marketing) Lab Exercises: 5. Time Series Visualization for any real time dataset 6. Design time series model and Evaluate the model using different metrics | |
Unit-4 |
Teaching Hours:15 |
Forecasting
|
|
Forecasting Simple forecasting methods - Average method - Naïve method - Seasonal naïve method - Drift method - Neural network models for forecasting - RNN - LSTM - Transformations and adjustments - calendar adjustments, population adjustments, inflation adjustments and mathematical transformations - Residual diagnostics - Evaluation metrics for forecasting - MAE, RMSE, MAPE, MASE , forecast bias - prediction intervals in forecasting i ) Case study: Forecasting the daily usage of electricity in any state / country j ) Case studies from various domains (e.g., healthcare, finance, marketing, economics, and business ) Lab Exercises: 7. Design simple forecasting model 8. Design RNN / LSTM forecasting model for any real time application | |
Unit-5 |
Teaching Hours:15 |
Genetic and Evolutionary Algorithms for Predictive Analytics
|
|
Genetic and Evolutionary Algorithms for Predictive Analytics Introduction to genetic algorithms - Overview of evolutionary computation - Principles of natural selection and evolution - Historical development of genetic algorithms - Genetic Representation and Operators - Crossover operators - Mutation operators - Selection Operators and Fitness Evaluation - Fitness scaling and normalization techniques - Constraint handling in genetic algorithms - Genetic Model Optimization - Time Series Forecasting with Genetic Algorithms k) Case study: Genetic algorithms in engineering design and optimization l) Case Study: Genetic algorithms in scheduling, resource allocation problems, bioinformatics and computational biology Lab Exercises: 9. Implement Genetic representation and operators 10. Implement time series forecasting model using genetic algorithms | |
Text Books And Reference Books: [1] Fundamentals of Predictive Analytics with JMP, Second Edition,Ron Klimberg, B. D. McCullough, SAS Institute, 2016 (unit 1,2) [2] Data Mining and Predictive Analytics, 2nd Edition, Daniel T. Larose, Wiley, 2021. (unit 3,5) [3] Forecasting: Principles and Practice, Rob J Hyndman and George Athanasopoulos Monash University, Australia, Third edition (unit 4) | |
Essential Reading / Recommended Reading [1] Hands-On Predictive Analytics with Python: Master the complete predictive analytics process, from problem definition to model deployment, Kindle Edition, Alvaro Fuentes, 2021. [2] Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie, or Die, Revised and Updated, Eric Siegel, Wiley, 2016. | |
Evaluation Pattern CIA-50% ETE-50% | |
MAI681 - INDUSTRY PROJECT (2023 Batch) | |
Total Teaching Hours for Semester:180 |
No of Lecture Hours/Week:18 |
Max Marks:300 |
Credits:12 |
Course Objectives/Course Description |
|
NA |
|
Learning Outcome |
|
CO1: Students will be able to develop and implement a functional system or application by applying learned coding skills and development methodologies. CO2: Students will be able to evaluate the performance of their project, identify potential areas for optimization, and troubleshoot any errors or inefficiencies within the system. |
Unit-1 |
Teaching Hours:180 |
Specialisation Project
|
|
NA | |
Text Books And Reference Books: NA | |
Essential Reading / Recommended Reading NA | |
Evaluation Pattern CIA-50% ETE-50% |