SCHEME OF EXAMINATION

B. Tech- 4th Year Semester: 8th

Branch: Computer Science and Engineering
Periods per
Scheme of Exam Credit
Subject week Total
S.N. Subject Name L+
Code Theory/Practical Marks
L T P (T+P)/2
ESE CT TA
Natural Language
1 CS110801 3 1 - 100 20 30 150 4
Processing
2 Professional Elective –IV Refer Table –IV 3 0 - 100 20 30 150 3
3 Open Elective – III Refer Table-III 3 0 - 100 20 30 150 3
4 Computer vision Lab CS110891 - - 2 25 - 25 50 1
Natural Language
5 CS102894 - -- 2 25 - 25 50 1
Processing Lab
6 Capstone Project Phase-II CS102895 - - 16 300 - 150 450 8
Total 8 2 20 650 60 290 1000 20

Professional Elective -IV

Sr. No. Subject Code Name of Subject
1. CS102825 Computer Vision

2. CS102826 Cyber Security Law and Intellectual Property

Open Elective -III

Sr. No. Subject Code Name of Subject
1. CS100842 Data Warehousing and Data Mining

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Natural Language Processing L=3 T=0 P=0 Credits = 3
CS110801
ESE CT TA Total ESE Duration
Examination 100 20 30 150 3 Hours
Scheme
Minimum number of class tests to be
Minimum Assignments=02
conducted=02

Course Objectives Course Outcomes

At the end of the course, the students will be able

to:
CO1: Understand the fundamentals of NLP
The ultimate goal of NLP is to help computers CO2: Process the text data at syntactic and
understand language as well as we do. It is the semantic level.
driving force behind things like virtual CO3: Extract the key information from Text data.
assistants, speech recognition, sentiment CO4: Analyze the text content to provide
analysis, automatic text summarization, predictions related to a specific domain using
machine translation and much more. language models
CO5: Generate the use cases for usage of NLP tools
for real life applications.

UNIT-I Fundamentals of NLP: Natural Language Processing – Linguistic Background -

Mathematical Foundations-Morphological Analysis-Tokenization- Stemming Lemmatization -
Boundary Determination.

UNIT-II Understanding Data: Reading unstructured data - Representing text data - Part of speech
tagging - Syntactic representation - Text similarity - WordNet based similarity- Shallow parsing -
Semantic representation.

UNIT-III Information Retrival: Information retrieval and Information extraction - Named Entity
Recognition - Relation Identification-Template filling. Language model - Probabilistic Models - n-
gram language modelsHidden Markov Model- Topic Modelling - Graph Models -Feature Selection
and classifiers -Rulebased Classifiers - Maximum entropy classifier – Clustering-Word and Phrase-
based Clustering. Detailed description of transformer architecture, use cases and various models for
natural language processing

UNIT-IV-Introduction to Generative AI: What is a Prompt? Elements of a Prompt. Tips for

Designing Prompt, Example prompts for various use cases, Introduction to AI Chatbots, Working of
AI Chatbots, Popular AI Chatbots, ChatGPT and its working, How to use ChatGPT, Usecases of
ChatGPT for various users, Role of AI in Image Generation, Image Sourcing Vs, Image Generation,
Popular AI tools for Image Generation. Midjourney for Image Generation, Working of midjourney,
Advantages and disadvantages of Midjourney, How to use Midjourney, Usecases of Midjourney

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 UNIT-V -Detailed description of GAN architecture, Transformer and Large Language Model
(LLM),its training and variants, Alternative Chatbots, Comparision of ChatGPT, Bard, LLAMA,
Claude, How to get into Generative AI domain, why genAI is special, future of genAI, Next steps.

Text Books:
S. No. Title Author(s) Publisher
Foundations of Statistical Natural Christopher D. Manning
1 MIT Press, 1999
Language Processing and Hinrich Schutze

Reference Books:

S. No. Title Author(s) Publisher

Practical Text Analytics: Interpreting
1 Text and Unstructured Data for Steven Struhl Kogan Page, 2015
Business Intelligence
2 Mining the Social Web Matthew A. Russell O'Reilly Media, 2013
Steven Bird, Ewan
Natural Language Processing with 1 st Edition, O'Reilly
3 Klein and Edward
Python Media, 2009
Loper

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Computer Vision Lab L=3 T=0 P=0 Credits = 3
CS110891
ESE CT TA Total ESE Duration
Examination
25 - 25 50 -
Scheme
Minimum number of Experiments – 10

Course Objectives Course Outcomes

After undergoing the course, students will be able

1. To be able to use Python for Image
handling and processing. to
2. To perform Geometric transformations
1. Apply Python for Image handling and
and computer homo graphy matrix in processing.
Python.
2. Apply Python for Geometric transformations
3. To be able to perform perspective
and computer homography matrix.
transformation, edge detection, line
3. Apply Python for perspective transformation,
detection and corner detection.
edge detection, line detection and corner
4. To be able to implement SIFT, SURF and
detection.
HOG in Python.
4. Apply Python for SIFT, SURF and HOG.

Write program stopper form following activities:

1. Perform basic Image Handling and Processing operations on the image.
2. Geometric Transformation
3. Compute Homography Matrix
4. Perspective Transformation
5. Camera Calibration
6. Compute Fundamental Matrix
7. Edge Detection, Line Detection and Corner Detection
8. SIFT Feature descriptor
9. SURF and HOG feature descriptor
10. Project based on Computer Vision Applications.

Text Books:
S. No. Title Author(s) Publisher
Programming Computer Vision with
1 Jan Erik Solem O'Reilly Media
Python
Practical Machine Learning for
2 Computer Vision: End-to-End Valliappa Lakshmanan, O'Reilly Media
Machine Learning for Images

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Natural Language Processing
Lab L=3 T=0 P=0 Credits = 3
CS102894
ESE CT TA Total ESE Duration
Examination
25 - 25 50 -
Scheme
Minimum number of Experiments - 10

Course Objectives Course Outcomes

CO1 Use network-based tools for network analysis

CO2 Use techniques for Network scanning
CO3 Identify network vulnerability
To introduce the students with the basics of
CO4 Use tools to simulate intrusion detection
NLP which will empower them for
system
developing advanced NLP tools and
CO5 To understand and install a firewall
solving practical problems in the field.
CO6 Identify the basic steps of ethical hacking and
protecting real-life applications through the
development of countermeasures

Write programs to perform following activities:

1. 1.To study Preprocessing of text (Tokenization, Filtration, Script Validation, Stop Word
Removal, Stemming)
2. 2.To Study Morphological Analysis
3. 3.To study N gram model
4. 4.To study POS tagging
5. 5.To study Chunking
6. 6.To study Named Entity Recognition
7. 7.Virtual Lab on Word Generation
8. N-Grams Smoothing
9. 9.Miniproject based on NLP applications
10. 10.To Study word analysis and word Generation
.

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Capstone Project Phase-II L=3 T=0 P=0 Credits = 3
CS102895
ESE CT TA Total ESE Duration
Examination
300 - 150 450 -
Scheme
Research Paper to be Published - 02

Guideline for Allocation of project:

1. Information regarding broad area must be made available to the students well in advance (may be
during previous semester).
2. Information must cover following parameters.
I. Broad area: Subject or expertise/application area.
II. Required skills: Knowledge of subject(s), software, tools & other characteristics.
III. Type of project: Hardware, software, design, survey, study based etc.
IV. Guide available: Name of Guide (S) from Department & Institute.
V. Other related information depending upon specific branch & institute.
3. It is also recommended to give proper counseling to pick up suitable project.
4. Students must get chance to select projects as per their choice or decided mutually between students
and department faculty (HoD) concern.
5. One project group must contain maximum four students, however students can do project individually
but it should be approved by department.
6. Compiled list of projects must be submitted to the University within 25 days of start of semester.
7. Compiled list may contain following parameters.

Monitoring of project:
1. It is recommended to give projects as per the specializations of existing faculty of the department
instead of outside person/agency.
2. Project must be allocated, developed and monitored by department / institution itself, but not by outside
agencies.
3. Regular review by guide is recommended to ensure development & contribution of students.

Internal Evaluation & Submission of project:

1. Evaluation of project would be as per the examination scheme of the University, which is based on
internal as well as external evaluation.
2. Internal assessment requires submission of project report for getting approved by the concern
authority. However printing and binding would be as per the conventional format.
3. Evaluation will be based on live demonstration / presentation and Viva.
4. Final submission of project is expected as,
• Submission of a copy to the University,
• One copy to the Institution central library,
• One copy to the department.
External Evaluation:
External assessment of project would be like conduction of practical exams of University, and must be executed
as per the norms of practical exams.
NOTE: Completion of Project outside the department/Institution should not be encouraged.

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Computer Vision L=3 T=0 P=0 Credits = 3
CS102825
ESE CT TA Total ESE Duration
Examination 100 20 30 150 3 Hours
Scheme
Minimum number of class tests to be
Minimum Assignments=02
conducted=02

Course Objectives Course Outcomes

1. To learn fundamentals of computer vision

After completion of this course the students will be
and its applications.
able to
2. To understand the basic image processing
1. To Know the fundamental video, audio
operations to enhance, segment the images
,image, text processing techniques
3. To Understand the analyzing and extraction
2. Acquire the basic skill of designing video
of relevant features of the concerned domain
compression, audio compression, image
problem.
compression, text compression.
4. To Understand and apply the motion
3. To Know the basic techniques in designing
concepts and its relevance in real time
video transmission systems : error control and rate
applications
control
5. To Apply the knowledge in solving high
4. To Identify basic concepts, terminology,
level vision problems like object
theories, models and methods in the field of
recognition, image classification etc.
computer vision.

UNIT-I: Introduction To Computer Vision

Overview, computer imagingsystems,lenses,Imageformationandsensing,Imageanalysis,pre-
processingand Binary image analysis, feature detection, image classification: Image Formation and
Representation: Imaging geometry, radiometry, digitization, cameras and Projections, rigid and affine
transformation Image Processing: Pixel transforms, color transforms, histogram processing, histogram
equalization, filtering, convolution, Fourier transformation and its applications in sharpening, blurring
and noise removal.

UNIT-II Feature detection: edge detection, corner detection, line and curve detection, active contours,
SIFT and HOG descriptors, shape context descriptors, Morphological operations Segmentation:
Active contours, split & merge, watershed, region splitting, region merging, graph-based
segmentation, mean shift and model finding, Normalized cut Camera calibration: camera models;
intrinsic and extrinsic parameters; radial lens distortion; direct parameter calibration; camera
parameters from projection matrices; orthographic, weak perspective, affine, and perspective camera
models.

UNIT-III-Motion representation: the motion field of rigid objects; motion parallax; optical flow, the
image brightness constancy equation, affine flow; differential techniques; feature-based techniques;
regularization and robust estimation Motion tracking: statistical filtering; iterated estimation;
observability and linear systems; the Kalman filter Object recognition and shape representation:

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 alignment, appearance-based methods, invariants, image eigenspaces

UNIT-IV: Data Compression Coding requirement, Source, entropy, hybrid coding, JPEG, MPEG,
Text compression using static Huffmann technique, Dynamic Huffmann Technique, Statistical coding
techniques.

UNIT-V: Optical Storage Media Video disk and other WORMS, Compact Disk digital audio,
Advantage of CD-DA Frames tracks blocks of CD-DA, CD-ROM, and Further CD-ROM based
developments, Principles of CDWO, Prospects of CD technologies.

Text Books:
S. No. Title Author(s) Publisher
Computer Vision Algorithms and
1 R. Szeliski Springer
Applications
Computer Vision : A modern
2 Forsyth & Ponce Pearson2011
approach
Introductory techniques for 3D
3 E. Trucco and A. Verri Prentice Hall, 1998
computer vision

Reference Books:

S. No. Title Author(s) Publisher

Multimedia Computing
1 Steinmetz Pearson Edn
Communication and Application
Fundamentals of Computer Graphics
2 D. P. Mukherjee PHI
and Multimedia

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Cyber Security Law and
Intellectual Property L=3 T=0 P=0 Credits = 3
CS102826
ESE CT TA Total ESE Duration
Examination 100 20 30 150 3 Hours
Scheme
Minimum number of class tests to be
Minimum Assignments=02
conducted=02

Course Objectives Course Outcomes

After undergoing the course, students will be able

to
1. To make attentive to students about 1. Understand the cyber security threat
different cybercrimes landscape.
2. To understand key terms and concept in 2. Understand Cybercrimes and cyber laws.
cybercrimes and cyberlaw 3. Understand various privacy and security
3. To make attentive to students about concerns on online Social media its legal
security privacy and challenges aspects and best practices.
4. To make attentive to students about 4. Understand the importance and applications
copyright and Patents of IPR it regulations.
Understand the application process of patent file
and other related aspects such as search,
registration and grant
UNIT–I : Introduction to cybercrimes Definition, cybercrime and information security, classes of
cyber crime and categories, cyber offences, cyber crimes with mobile and wireless devices, cyber
crime against women and children, financial frauds, social engineering attacks.

UNIT–II: Cybercrime and Cyber law Malware and ransom ware attacks, zero day and zero click
attacks, Legal perspective of cybercrime, IT Act 2000 and its amendments, Cyber crime and offences,
Organizations dealing with Cyber crime and Cyber studies security in India

UNIT–III: Social Media Overview and Security Introduction to Social networks. Types of Social
media, Social media platforms, Social media monitoring, Hashtag, Viral content, Social media
marketing, Social media privacy, Challenges, opportunities and pitfalls in online social network,
Security issues related to social media, Flagging and reporting of inappropriate content, Laws
regarding Posting of inappropriate content, Best practices for the use of Social media, Case studies.

UNIT–IV: Introduction to Intellectual Property Rights(IPR) Introduction to IPR, International

Instruments and IPR, WIPO – TRIPS – WTO -Laws Relating to IPR , IPR Tool Kit : Protection and
Regulation, Copyrights and Neighboring Rights, Agencies for IPR Registration, Emerging Areas of
IPR, Use and Misuse of Intellectual Property Rights.

UNIT–V : Patents Introduction to Patents, Laws Relating to Patents in India, Patent Requirements
,Product Patent and Process Patent, Patent Search, Patent Registration and Granting of Patent,

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Exclusive Rights and Limitations, Ownership and Transfer, Revocation of Patent, Patent Appellate
Board, Infringement Of Patent, Compulsory Licensing, Patent Cooperation Treaty, New developments
in Patents, Software Protection and Computer related Innovations.

Text Books:
S. No. Title Author(s) Publisher
Intellectual Property Rights (Patents & Oxford University Press,
1 Dr. A. Srinivas
Cyber Law) New Delhi
Cyber Laws: Intellectual property & E
2 Kumar K Dominant Publisher
Commerce Security
Cyber Security Understanding Cyber
Sumit Belapureand
3. Crimes, Computer Forensics and Wiley India Pvt.Ltd
Nina Godbole
Legal Perspectives

Reference Books:

S. No. Title Author(s) Publisher

Gerald R. Ferrera, CENGAGE LEARNING
1 Cyber Law Text & Cases
Margo E. K. Reder Publication
Intellectual Property (Trade Marks
2 and the Emerging concepts of Cyber P. Narayanan Universal Book Traders
property rights (HB)

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Subject Code Data Warehousing and Data
Mining L=3 T=0 P=0 Credits = 3
CS100842
ESE CT TA Total ESE Duration
Examination 100 20 30 150 3 Hours
Scheme
Minimum number of class tests to be
Minimum Assignments=02
conducted=02

Course Objectives Course Outcomes

 To understand the principles of Data

warehousing and Data Mining.
 To be familiar with the Data warehouse
architecture and its Implementation.
 To know the Architecture of a Data Technical knowhow of the Data Mining principles
Mining system. and techniques for real time applications.
 To understand the various Data
preprocessing Methods.
 To perform classification and prediction
of data.

UNIT I : Data Warehousing and Business Analysis: - Data warehousing Components –Building a
Data warehouse –Data Warehouse Architecture – DBMS Schemas for Decision Support – Data
Extraction, Cleanup, and Transformation Tools –Metadata – reporting – Query tools and Applications
– Online Analytical Processing (OLAP) – OLAP and Multidimensional Data Analysis.

UNIT II : Data Mining: - Data Mining Functionalities – Data Preprocessing – Data Cleaning – Data
Integration and Transformation – Data Reduction – Data Discretization and Concept Hierarchy
Generation- Architecture Of A Typical Data Mining Systems- Classification Of Data Mining Systems.
Association Rule Mining: - Efficient and Scalable Frequent Item set Mining Methods – Mining
Various Kinds of Association Rules – Association Mining to Correlation Analysis – Constraint-Based
Association Mining.

UNIT III : Classification and Prediction: - Issues Regarding Classification and Prediction –
Classification by Decision Tree Introduction – Bayesian Classification – Rule Based Classification –
Classification by Back propagation – Support Vector Machines – Associative Classification – Lazy
Learners – Other Classification Methods – Prediction – Accuracy and Error Measures – Evaluating the
Accuracy of a Classifier or Predictor – Ensemble Methods – Model Section.

UNIT IV : Cluster Analysis: - Types of Data in Cluster Analysis – A Categorization of Major

Clustering Methods – Partitioning Methods – Hierarchical methods – Density-Based Methods – Grid-

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards
 Based Methods – Model-Based Clustering Methods – Clustering High-Dimensional Data –
Constraint-Based Cluster Analysis – Outlier Analysis.

UNIT V : Mining Object, Spatial, Multimedia, Text and Web Data: Multidimensional Analysis and
Descriptive Mining of Complex Data Objects – Spatial Data Mining – Multimedia Data Mining –
Text Mining – Mining the World Wide Web.

Text Books:
S. No. Title Author(s) Publisher
Data Mining Concepts and Jiawei Han, Micheline Third Edition, Elsevier,
1
Techniques Kamber and Jian Pei 2011
Pang-Ning Tan,
2 Introduction to Data Mining Michael Steinbach and Pearson Education, 2007
Vipin Kumar

Reference Books:

S. No. Title Author(s) Publisher

Data Warehousing, Data Mining & Alex Berson and Tata McGraw – Hill
1
OLAP Stephen J. Smith Edition
Insight into Data mining Theory and K.P. Soman, Shyam Easter Economy Edition,
2
Practice Diwakar and V. Ajay Prentice Hall of India
Introduction to Data Mining with Easter Economy Edition,
3 G. K. Gupta
Case Studies Prentice Hall of India

1.00 Applicable for

Chairman (AC) Chairman (BoS) Date of Release Version AY 2021-22 Onwards