SEMESTER VII

Contact

Category
Course Evaluation Scheme

Credits
Hours
Course
Code Code Title Course
L T P CIA ESE Total
Natural Language
C BAI3701 Processing 3 1 0 40 60 100 4
C BAI3702 Fuzzy Logic 3 1 0 40 60 100 4
GE Generic Elective II 3 1 0 40 60 100 4
[Block Chain Technology]

GE Generic Elective III 3 1 0 40 60 100 4

[Internet Of Things]
OE Open Elective I* - - - 40 60 100 4
Natural Language
C BAI3751 Processing Lab 0 0 2 40 60 100 1
C BAI3752 Fuzzy Logic Lab 0 0 2 40 60 100 1
Industrial Training
C BAI3758 Evaluation 0 0 2 100 - 100 1
C BAI3759 Project I# 0 0 4 100 - 100 2
GP3701 General Proficiency - - - 100 - 100 1
Total 12 4 10 580 420 1000 26
*Students will opt any one of the open elective from the list of open electives provided by the university.
#
Students need to submit an abstract for the project, select a guide and will complete the literature review related to the
project.
SEMESTER VIII
Contact
Hours Evaluation Scheme
Category

Credits
Course
Course

Code Code Title Course

L T P CIA ESE
Total
Concepts of Deep
C BAI3801 Learning 3 1 0 40 60 100 4
GE Generic Elective IV 3 1 0 40 60 100 4
GE Generic Elective V 3 1 0 40 60 100 4
OE Open Elective II** - - - 40 60 100 4
C BAI3851 Deep Learning Lab 0 0 2 40 60 100 1
C BAI3859 Project II## 0 0 16 160 240 400 8
GP3801 General Proficiency - - - 100 - 100 1
Total 9 3 18 460 540 1000 26
**The opted subject should be different from the one selected in VII Semester.
##
This is in continuation with the project work started in Semester VII. In this semester the students will
formulate the methodology do experimentation and show the results. Finally all project work will be presented in a
report i.e. Project Report.
Category of Courses:
Legends:
L Number Lecture per week F Foundation Course
T Number of Tutorial Hours per week C Core Course
P Number of Practical Hours per week GE Generic Elective
CIA Continuous Internal Assessment OE Open Elective
ESE End Semester Examination
 List of Open Electives
B. Tech: Computer Science and Engineering
(Artificial Intelligence)
S.N. Course Code Open Elective
1 OE33901 Principles of Industry 4.0
2 OE33902 Nature Inspired Algorithms

List of Generic Electives

Course
Generic Elective I
Code
GE33911 Cyber Law and Security
GE33912 Introduction to Unmanned Aerial Vehicles
GE33913 Computer Vision
GE33914 Recommender Systems
Course
Generic Elective II
Code
GE33921 Block Chain Technology
GE33922 System Modeling & Simulation
GE33923 Embedded System Design
GE33924 Sentiment Analysis
Course
Generic Elective III
Code
GE33931 Evolutionary Multi-objective Optimization
GE33932 Bioinformatics
GE33933 Internet of Things
GE33934 Cloud Computing
Course
Generic Elective IV
Code
GE33941 Data Mining and Ware Housing
GE33942 Introduction to Drones
GE33943 Computer Forensics
GE33944 Augmented & Virtual Reality
Course
Generic Elective V
Code
GE33951 Wireless Sensor Networks
GE33952 Distributed Systems
GE33953 Gaming in Artificial Intelligence
GE33954 Pattern Recognition
 BAI3701 NATURAL LANGUAGE PROCESSING

Course Objective:
1. To tag a given text with basic Language features
2. To design an innovative application using NLP components
3. To learn the fundamentals of natural language processing
4. To understand the use of CFG and PCFG in NLP

Learning Outcome:
After completing the course, the students should be able to:
1. Teach students the leading trends and systems in natural language processing.
2. Make them understand the concepts of morphology, syntax, semantics and
pragmatics of the language and that they are able to give the appropriate examples
that will illustrate the above mentioned concepts.
3. Enable students to be capable to describe the application based on natural
language processing and to show the points of syntactic, semantic and
pragmatic processing.
4. Understand approaches to discourse, generation, dialogue and summarization within NLP.
5. Understand approaches to syntax and semantics in NLP.

Course Contents:

Module Course Topics Total Hours Credits

Introduction to NLP, Need of NLP, History of

NLP, Advantages and Disadvantages of NLP,
Applications of NLP.
How does NLP work, components of NLP,
I Phases of NLP, NLP vs. Machine learning. 1
30 Hours
NLP examples, Future of NLP.

Lexical analysis, Unsmoothed N grams,

evaluating N grams, Morphology and Finite
state Transducers,
Interpolation and Back off
– word classes, Part of Speech Tagging –
30 Hours 1
II Markov Models, Hidden Markov Models.
Transformation based Models – Maximum
Entropy Models.
Syntax Parsing:-

Concept of Parser, Types of Parsing, Concept of

Derivation, Types of Derivation, Concept of
Grammar CFG, Definition of CFG. Grammar rules
III for English Treebank’s, Normal forms for 30 Hours 1
grammar – Dependency Grammar, Syntactic
 Parsing, Ambiguity, Dynamic
Programming Parsing- Shallow
Parsing.
Semantic Analysis and
Disclosure Pragmatic:-

Elements of Semantics Analysis, Difference

between Polysems and Homonymy. Meaning 30 Hours 1
IV
Representatives, Need of Meaning
Representative, Disclosure Pragmatic- Concept
of Coherence, Disclosure structure, Text
coherence, Building Hierarchical Disclosure
structure. Reference Resolution, Terminology
used in Reference Resolution.

Text/Reference Books:

1. Daniel Jurafsky, James H. Martin: "Speech and Language Processing", 2/E, Prentice
Hall, 2008.
2. James Allen, "Natural Language Understanding", 2/E, Addison-Wesley,
199Christopher D. Manning, Hinrich Schutze: "Foundations of Statistical Natural
Language Processing", MIT Press, 1999
3. Steven Bird, Natural Language Processing with Python, 1st Edition, O'Reilly, 2009.
4. Jacob Perkins, Python Text Processing with NLTK 2.0 Cookbook, Packt Publishing, 2010
 BAI3702 FUZZY LOGIC COURSE
Objectives:
1. To teach about the concept of fuzziness involved in various systems. To
provide adequate knowledge about fuzzy set theory.
2. To provide adequate knowledge of application of fuzzy logic control to
real time systems.
3. Comprehend the fuzzy logic control and to design the fuzzy control
using genetic algorithms.
4. Apply basic fuzzy system modelling methods.
5. Make applications on Fuzzy logic membership function and fuzzy
inference systems.

Learning Outcomes:
After completing the course, the students should be able to:

1. Recognize fuzzy logic membership function.

2. Make applications on Fuzzy logic membership function and
fuzzy inference systems.
3. Use the fuzzy set theory on the statistical method which is given.
4. Analyse statistical data by using fuzzy logic methods.
5. Recognize fuzzy logic fuzzy inference systems

Course Content:

Total
Module Course Topics Credits
Hour
s
Introduction, Classical Sets and Fuzzy Sets:-

Background, Uncertainty and Imprecision,

I 1
Statistics and Random Processes, Uncertainty in 12 Hours
Information Fuzz Sets and
Membership, Chance versus
Ambiguity Classical Sets - Operations on
Classical Sets Properties o Classical (Crisp)
Sets, Mapping of Classica Sets to
Functions Fuzzy Sets - Fuzzy Set operations, Properties of
Fuzz Sets. Sets as Points in Hypercubes
Classical Relations and Fuzzy Relations :-
II
Cartesian Product, Crisp Relations- Cardinality of
9 Hours 1
Crisp Relations, Operations on
Crisp
 III
,
11 Hours 1
Ge

IV 8 Hours 1

Text/ReferenceBooks:

1. Fuzzy Logic with Engineering Applications By Timothy J. Ross · 2016.

2. Kosko, B, “Neural Networks and Fuzzy Systems: A Dynamical
Approach to Machine Intelligence”, PrenticeHall, NewDelhi,2004.
 GE33921 BLOCK CHAIN TECHNOLOGY
[ Generic Elective II ]
Objective:
By the end of the course, students will be able to

1. Understand how block chain systems (mainly Bitcoin and Ethereum) work,
2. To securely interact with them,
3. Design, build, and deploy smart contracts and distributed applications,
4. Integrate ideas from block chain technology into their own projects,
5. Evaluate security, privacy, and efficiency of a given block chain system.

Learning Outcome:
After completing the course, the students should be able to:

1. Explain design principles of Bitcoin and Ethereum.

2. Explain Nakamoto consensus.
3. Explain the Simplified Payment Verification protocol.
4. List and describe differences between proof-of-work and proof-of-stake consensus.
5. Interact with a block chain system by sending and reading transactions.
6. Design, build, and deploy a distributed application.
7. Evaluate security, privacy, and efficiency of a given block chain system.

Course Contents:

Total
Module Course Topics Credits
Hour
s

Basics: Distributed Database, Two General Problem,

Byzantine General problem and Fault Tolerance,
I Hadoop Distributed File System, Distributed Hash
Table, ASIC resistance, Turing 30 1
Complete.Cryptography: Hash function, Digital
Signature - ECDSA, Memory Hard Algorithm, Zero
Knowledge Proof.
Blockchain: Introduction, Advantage over
conventional distributed database, Blockchain
Network, Mining Mechanism, Distributed Consensus
1
Merkle Patricia Tree Gas Limit, Transactions and Fee 30
II
Anonymity, Reward Chain Policy, Life of Blockchain
application, Soft & Hard Fork, Private and Public
blockchain.
 Distributed Consensus: Nakamoto consensus, Proof of
Work, Proof of Stake, Proof of Burn, Difficulty Leve
III 30 1
Sybil Attack, Energy utilization and alternate.
Cryptocurrency: History, Distributed Ledger, Bitcoin
protocols - Mining strategy and rewards, Ethereum -
Construction, DAO, Smart Contract, GHOST
Vulnerability, Attacks, Sidechain, Namecoin
IV
Cryptocurrency Regulation: Stakeholders, Roots of 30 1
Bit coin, Legal Aspects- Crypto currency Exchange
Black Market and Global Economy. Applications
Internet of Things, Medical Record Managemen
System, Domain Name Service and future of
Blockchain.

Text Books:

1. Arvind Narayanan, Joseph Bonneau, Edward Felten, Andrew Miller and Steven Goldfeder,
Bitcoin and Cryptocurrency Technologies: A Comprehensive Introduction, Princeton
University Press (July 19, 2016).

Reference Books

1. Andreas M. Antonopoulos, Mastering Bitcoin: Unlocking Digital Cryptocurrencies,

"O'Reilly Media, Inc.", 03-Dec-2014 - Business & Economics.
2. Dr. Gavin Wood, “ETHEREUM: A Secure Decentralized Transaction
Ledger,”Yellow paper.2014.
3. Antony Lewis, The Basics of Bitcoins and Blockchains: An Introduction to
Cryptocurrencies and the Technology that Powers Them(Cryptography, Crypto
Trading, Digital Assets, NFT) Paperback – April 13,2021
4. Joseph J. Bambara, Paul R. Allen, Block Chain: A Practical Guide to Developing
Business, Law And Technology.
 GE33933 INTERNET OF THINGS
[ Generic Elective III ]
Objective:
1. Describe the IoT and Cloud architectures
2. Determine the right sensors and communication protocols to use in a
particular IoT system.
3. Deploy Cloud Services using different cloud technologies.
4. Implement cloud computing elements such virtual machines, web
apps, mobile services, etc
5. Establish data migration techniques from IoT devices to the cloud.
Learning Outcome:
After completing the course, the students should be able to:
1. Understand general concepts of Internet of Things (IoT) (Understand)
2. Recognize various devices, sensors and applications (Knowledge)
3. Apply design concept to IoT solutions (Apply)
4. Analyze various M2M and IoT architectures (Analyze)
5. Evaluate design issues in IoT applications (Evaluate)
6. Create IoT solutions using sensors, actuators and Devices (Create)
Course Contents:

Total
Module Course Topics Credits
Hours

Introduction to IoT: Sensing, Actuation,

Networking basics, Communication Protocols,
I Sensor Networks, Machine-to- 30 Hours 1
Machine Communications, IoT
Definition, Characteristics. IoT
Functional Blocks, Physical design of
IoT, Logical design of
IoT, Communication models & APIs.
M2M to IoT-The Vision-Introduction, From
II M2M to IoT, M2M towards IoT-the global 30 Hours 1
context, A
use case example,
Differing Characteristics.
Definitions, M2M Value Chains, IoT Value
Chains, An emerging industrial structure for
IoT.
M2M vs IoT An Architectural Overview–
Building architecture, Main design principles 30 Hours 1
III
and needed capabilities, An IoT architecture
outline, standards considerations. Reference
Architecture and Reference Model of IoT.
 IoT Reference Architecture- Getting Familiar
IV with IoT Architecture, Various architectural
views of IoT such as Functional, Information, 30 Hours 1
Operational and Deployment. Constraints
affecting design in the IoT world- Introduction,
Technical design Constraints.

Domain specific applications of IoT: Home

automation, Industry applications, Surveillance
applications, Other IoT applications, developing
IoT solutions.

Text/Reference Books:

1. Vijay Madisetti and Arshdeep Bahga, “Internet of Things

(A Hands- onApproach)”, 1st Edition, VPT, 2014
2. Francis daCosta, “Rethinking the Internet of Things: A Scalable
Approach to Connecting Everything”, 1st Edition, Apress
Publications, 2013
3. Cuno Pfister, Getting Started with the Internet of Things, O‟Reilly Media,
2011, ISBN: 978-1-4493- 9357-1
 QUALITY MANAGEMENT (OE33501)
Course Objective:
1. To have knowledge of Quality concept & Quality Management.
2. To be aware about the importance Quality Management.
3. To have knowledge about Control charts.
4. To have knowledge of ISO9000series.
Learning Outcome:
At the end of the course student should be able to:
1. Know the importance of Quality Management Tools and their applications.
2. Increase the productivity and efficiency of organization with the help of
Quality Management Tools.
3. Can develop new types Quality Management Techniques.
4. Apply Taguchi method & JIT method for various applications.
Course Contents:

Module Course Topics Total Credits

Hours

Quality Concepts:
Evolution of Quality control, Concept change, TQM
Modern concept, Quality concept in design, Review
off design, Evolution of prototype.
Control on Purchased Product:
Procurement of various products, Evaluation of
I 30 1
supplies, Capacity verification, Development of
sources, Procurement procedure.
Manufacturing Quality:
Methods and Techniques for manufacture, Inspection
and control of product, Quality in sales and services,
Guarantee, analysis of claims.
Quality Management:
Organization structure and design, Quality function,
II Decentralization, Designing and fitting organization 30 1
for different types products, Economics of quality
value and contribution, Quality cost, Optimizing
quality cost.
 Human Factor in Quality:
Attitude of top management, Co-operation, of
groups,
Operators attitude, responsibility, Causes of o
error and corrective methods.
Control Charts:
Theory of control charts, Measurement range,
Construction and analysis of R charts, Process
capability study, Use of control charts.
III 30 1
Attributes of Control Charts:
Defects, Construction and analysis off-chart,
Improvement by control chart, Variable sample size,
Construction and analysis of C-chart.
Defects Diagnosis and Prevention:
Defect study, Identification and analysis of defects,
Corrective measure, Factors affecting reliability,
MTTF, Calculation of reliability, Building reliability
IV in the product, Evaluation of reliability, Interpretation 1
30
of test results, Reliability control, Maintainability,
Zero defects, quality circle.
IS0-9000anditsconceptofQualityManagement:
ISO9000series, Taguchi method, JIT in some details

Reference Books:
1. Concurrent Engineering Kusiak John Wiley.
2. Concurrent Engineering Menon Chapman & hall.
 BAI3751 NATURAL LANGUAGE PROCESSING LAB

List of Experiments
1. Word Analysis
The objective of the experiment is to learn about morphological features of a word by
analysing it.

2. Word Generation
The objective of the experiment is to generate word forms from root and suffix information.

3. Morphology
Understanding the morphology of a word by the use of Add-Delete table

4. N-Grams
The objective of this experiment is to learn to calculate bigrams from a given corpus and
calculate probability of a sentence.

5. N-Grams Smoothing
The objective of this experiment is to learn how to apply add-one smoothing on sparse
bigram table.

6. POS Tagging - Hidden Markov Model

The objective of the experiment is to calculate emission and transition matrix which will be
helpful for tagging Parts of Speech using Hidden Markov Model.

7. POS Tagging - Viterbi Decoding

The objective of this experiment is to find POS tags of words in a sentence using Viterbi
decoding.

8. Building POS Tagger

The objective of the experiment is to know the importance of context and size of training
corpus in learning Parts of Speech

BAI3752 FUZZY LOGIC LAB

List of Experiments
1. Implementation of Fuzzy Operations.
2. Implementation of Fuzzy Relations (Max-min Composition).
3. Implementation of Fuzzy Controller (Washing Machine).
4. Implementation of Simple Neural Network (McCulloh-Pitts model).
5. Implementation of Perceptron Learning Algorithm.
6. Implementation of Unsupervised Learning Algorithm.
7. Implementation of Simple Genetic Application.
8. Study of ANFIS Architecture.
9. Study of Derivative-free Optimization.
10. Study of research paper on Soft Computing.
 Babu Banarasi Das University, Lucknow
School of Engineering
Bachelor of Technology: Computer Science and Engineering
(Artificial Intelligence)
Branch Code: 39

Credit Summary Chart

Semester Total
Course Category I II III IV V VI VII VIII Credits %age
F 16/11 11/16 0 0 0 0 0 0 27/27 12.80
C 10/16 16/10 25 25 25 21 13 13 148/148 70.14
GE 0 0 0 0 0 4 8 8 20 9.48
OE 0 0 0 0 0 0 4 4 8 3.79
GP 1 1 1 1 1 1 1 1 8 3.79
Total 27/28 28/27 26 26 26 26 26 26 211 100
Discipline wise Credit Summary Chart
Semester Total
Course Category I II III IV V VI VII VIII Credits %age
Basic Sciences 10/12 12/10 4 3 29 10.43
Humanities and
Socials Sciences 0/4 4/0 2 2 3 3 14 9.95
Engg. Sciences 16/11 11/16 27 12.79
Professional
Subject Core 19 20 22 17 10 5 93 44.07
Professional
Subject-General
4 8 8 20 9.48
Elective
Professional
Subject -Open
4 4 8 3.80
Elective
GP + Project Work,
Seminar and / or
Internship in Industry
or 1 1 1 1 1 2 4 9 20 9.48
elsewhere.
Total 27/28 28/27 26 26 26 26 26 26 211 100