Major Program: Data Science

Conducted By

Department of Computer Engineering

Effective from Academic Year 2022-23
 Credit structure -Major (Data Science)

Course Teaching Scheme

Sem Code Course Name Credits Assigned
(Contact Hours)
Theory Practical Tutorial Theory Practical Tutorial Total

Foundation of
03 - - 03 - - 03
CEMDC501 Data Science
V
CEMDL501 Foundation of - -
Data Science - 02 01 - 01
Lab

CEMDC601 Social -
Network 03 - - 03 - 03
Analysis
CEMDC602 Natural -
Language 03 - - 03 - 03
Processing
VI CEMDL601 Social - - -
Network 02 01 01
Analysis Lab
CEMDL602 Natural - - -
Language
02 01 01
Processing
Lab

Computational - -
03 - - 03 03
CEMDC701 Intelligence
CEMDL701 Computational - - - -
VII Intelligence 02 01 01
Lab
CEMDMP701 Data Science - - - -
04 02 02
Mini Project

Total 12 12 - 12 06 - 18
 Evaluation Scheme: Major (Data Science)

Evaluation Scheme
Course Code Theory
Course Exam
Internal Assessment Mid End Term Pract.
Name Duration Oral Total
Sem. Sem Work
Test1 Test2 Avg. (in Hrs.)
Exam Exam
SEM V
20 20 20 20 60 2 - - - 100
CEMDC501 Foundation
of Data
CEMDL501 Foundation - - - - - - 25 - 25 50
of Data
Science Lab
150
SEM VI
CEMDC601 Social
Network 20 20 20 20 60 2 - - - 100
Analysis
CEMDC602 Natural 20 20 20 20 60 2 - - - 100
Language
Processing
CEMDL601 Social - - - - - - 25 - 25 50
Network
Analysis Lab
CEMDL602 Natural - - - - - - 25 - 25 50
Language
Processing
Lab
300
SEM VII

CEMDC701 Computation 20 20 20 20 60 2 - - - 100

al Intelligence
CEMDL701 Computation - - - - - - 25 - 25 50
al Intelligence
Lab
CEMDMP701 Data Science - - - - - - 25 - 25 50
Mini Project
Total Marks 200
 Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Hrs Hrs Hrs Credit Credit Credits Credits
Foundation
CEMDC501 of Data 03 - - 03 - - 03
Science

Course Code Course Examination Scheme

Name
Theory Marks Term Practical Oral Total
Work

In-Sem Evaluations
End
Mid Sem
IA1 IA2 AVG Sem Exam
Exam

CEMDC501 Foundation 20 20 20 60 - - - 100

of Data 20
Science

Course Objectives:
1. Understand basics of Data Science.
2. Importance of Data Exploration.
3. Understand classification, regression, association and clusteringmethods.
4. Evaluation of models.

Course Outcomes: At the end of the course learner will able to

1. Basic concepts of data science.
2. To do data exploration.
3. Apply various machine learning techniques.
4. Understand and apply deep learning models for data science.
5. Evaluate and compare the models used.
6. Recognize data science applications in real world.

Prerequisites:
1. Data Base Management System, Statistics
 Sr. CO
Module Detailed Content Hours
No. Mapping

AI, Machine learning and Data Science,

what is Data Science, case for DataScience,
1 Introduction 06 CO1
classification and algorithms. Data Science
process, prior knowledge, data preparation,
modelling and applications.
2 Data Objectives, datasets, descriptive statistics, 06 CO2
Exploration data visualization
Linear regression, Logistic regression,
Data Science Decision tree, rule induction, Naïve
3 with Machine Bayesian, support vector machines, 10 CO3
Learning ensemble learners. K means clustering,
DBSCAN clustering, self-organizing maps
Data Science
Introduction, How it works, Regression
4 with Deep 06 CO4
model as NN, RNN, CNN
Learning
Generalization Error , Out-of-Sample ,
Evaluation Metrics, Cross Validation,
Model Overfitting , Under Fitting and Model
5 05 CO5
Evaluation Selection, Prediction by using Ridge
Regression, Testing Multiple Parameters by
using Grid Search.
Time series model, market basket analysis,
6 Data Science
Customer churn analysis, healthcare 06 CO6
applications
applications

Text Books:
1. Vijay Kotu ,Bala Deshpande , “Data Science: Concepts and Practice “, Morgan and
Kaufmann publisher (Elseveir)

Reference Books:
1. Cathy O’Neil and Rachel Schutt, “Doing Data Science”, O'Reilly, 2015. 3
2. David Dietrich, Barry Heller, Beibei Yang, “Data Science and Big data Analytics”,
EMC 2013

Evaluation Scheme:
1. In-Semester Assessment:
 • Assessment consists of two Internal Assessments (IA1, IA2) out of which; one
should be compulsory class test (on minimum 02 Modules) and the other is a class
test / assignment on case studies / course project.
• Mid Semester Examination (MSE) will be based on 40-50% of thesyllabus.

2. End-Semester Examination:
• Question paper will comprise of full syllabus.
• In the question paper, weightage of marks will be proportional to the total number
of lecture hours as mentioned in the syllabus.
 Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Hrs Hrs Hrs Credit Credit Credits Credits
CEMDL501 Foundatio - 02 - - 01 - 01
n of Data
Science
Lab

Subject Subject Examination Scheme

Code Name
Theory Marks Term Practical Oral Total
Work & Oral

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid Exam
Sem
Exam

CEMDL501 Foundation - - - - - 25 25 - 50
of Data
ScienceLab

Lab Objectives:
1. To understand the basic concepts for building the data science project
2. To apply appropriate model for particular data science application.
3. To evaluate the model selected for the project

Lab Outcomes: At the end of the course, the students will be able to
7. Use Rapid Miner for visualizing the data set.
8. Implement and evaluate machine learning techniques for regression.
9. Implement and evaluate classification methods for real world problems.
10. Implement and evaluate clustering methods for real world problems.
11. Implement and evaluate deep learning models.
12. Analyze real world case study.

Prerequisite: Discrete Mathematics, Data Structure

Suggested List of Experiments (programming in Rapid Miner)

Experiment Experiments Name CO Mapping

No.
1 Getting Started with Rapid Miner to visualize the CO1
real time dataset.
2 Implement and evaluate multivariate regression CO2
using real time data set.
3 Implement and evaluate Logistic Regression using CO2
real time data set.
4 Implement and evaluate Support Vector Machine CO3
using real time data set.
5 Implement and evaluate Decision Tree using real CO3
time data set.
6 Implement and evaluate Random Forest method CO3
using real time data set.
7 Implement and evaluate k means clustering CO4
algorithm using real time data set.
8 Implement and evaluate DBSCAN algorithm using CO4
real time data set.
9 Implement CNN for image classification. CO5
10 Case Study CO6

Text Books:
4. Vijay Kotu ,Bala Deshpande , “Data Science: Concepts and Practice “, Morgan and
Kaufmann publisher (Elseveir).
5. http://www.rapidminer.com

Term Work:
The Term work Marks are based on the weekly experimental performance of the students,
Oral performance and regularity in the lab.

Students are expected to be prepared for the lab ahead of time by referring the manual and
perform the experiment under the guidance and discussion. Next week the experiment write-
up to be corrected along with oral examination.

End Semester Examination:

End of the semester, there will be Oral evaluation based on the laboratory work and the
corresponding theory syllabus.
 Subject Subject Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Code Name Hrs Hrs Hrs Credit Credit Credits Credits
CEMDC601 Social 03 - - 03 - - 03
Network
Analysis

Subject Subject Examination Scheme

Code Name
Theory Marks Term Practical Oral Total
Work

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid Exam
Sem
Exam

Social
Network 20 20 20 20 60 - - - 100
CEMDC601
Analysis

Course objectives:

1. To familiarize the learners with the concept of social network.

2. To enable the learners to develop skills required for analysing the effectiveness of social
network.
3. To familiarize the learner with different visualization techniques for social network
analytics.
4. To examine the ethical and legal implications of leveraging social mediadata.

Course outcomes: On successful completion of course, learner will be able to:

1. Understand the concept of social network.

2. Understand the concept of social network analytics and itssignificance.
3. Learners will be able to analyse the effectiveness of social media.
4. Learners will be able to use different social network analytics tools effectively and
efficiently
5. Learners will be able to use different effective Visualization techniques to represent
social network analytics
 6. Acquire the fundamental perspectives and hands-on skills needed to work with social
media data.

Prerequisites:

1. Data Mining

Sr. Detailed Content CO

Module Hours
No. Mapping

Introduction, History of social

network, need to study social
Social network: network, Applications of social
1 6 CO1
An Overview network, Three levels of social
network analysis, Graph
visualization Tool.

Basics of Social Network Structure

- Nodes, Edges & Tie. Network
Social Network Visualization - Graph Layout,
Structure, Visualizing Network features,
2
Scale Issues. Social Media 6 CO2
Measures &
Visualization Network Analytics - Common
Network Terms, Common Social
Media Network Types.

Social Media Text Analytics -

Types of social media text, Purpose
of Text Analytics, Steps in Text
Analytics, Social Media Text
Social Media Analysis Tools Social Media
3 Text, Action Action Analytics - Common Social 8 CO3
& Hyperlink Media Actions, Actions Analytics
Analytics Tools. Social Media Hyperlink
Analytics - Types of Hyperlinks,
Types of Hyperlink Analytics,
Hyperlink Analytics Tools
 Location Analytics - Sources of
Location Data, Categories of
Location Analytics, Location
Analytics and Privacy Concerns,
4 Search Engine
Location Analytics Tools Search 6 CO4
Analytics
Engine Analytics - Types of Search
Engines, Search Engine Analytics,
Search Engine Analytics Tools

Social Information Filtering -

Social Sharing and filtering ,
Automated Recommendation
systems, Traditional Vs social
Social Recommendation System
5
Information Understanding Social Media and 6 CO5
Filtering Business Alignment, Social Media
KPI, Formulating a Social Media
Strategy, Managing Social Media
Risks

Social media in public sector -

Analyzing public sector social
media, analyzing individual users,
Social network case study. Business use of social
6 Analytics media - Measuring success, 7 CO6
Applications Interaction and monitoring, case
and Privacy study. Privacy - Privacy policies,
data ownership and maintaining
privacy online.

Text Books:

1. Gohar F. Khan, “Seven Layers of Social Media Analytics_ Mining Business Insights
from Social Media Text, Actions, Networks, Hyperlinks, Apps, Search Engine, and
Location Data”,(ISBN-10: 1507823207).
2. Jennifer Golbeck, “Analyzing the Social Web”, 1st Edition.
3. Matthew A Russell, “ Mining the Social Web_ Analyzing Data from Facebook, Twitter,
LinkedIn, and Other Social Media Sites”, O’Reilly

Reference Books:
 1. Matthew Ganis, Avinash Kohirkar, “Social Media Analytics [2015], Techniques and
Insights for Extracting Business Value Out of Social Media”, IBMPress.
2. Alex Gonçalves, “Social Media Analytics Strategy_ Using Data to Optimize Business
Performance”, APress Business Team.
3. Szabo, G., G. Polatkan, O. Boykin & A. Chalkiopoulus, “Social Media Data Mining
and Analytics”, Wiley, 2019, ISBN 978-1-118-82485-6

Evaluation Scheme:
1. In-Semester Assessment:
• Assessment consists of two Internal Assessments (IA1, IA2) out of which; one
should be compulsory class test (on minimum 02 Modules) and the other is a class
test / assignment on case studies / course project.
• Mid Semester Examination (MSE) will be based on 40-50% of thesyllabus.

2. End-Semester Examination:
• Question paper will comprise of full syllabus.
• In the question paper, weightage of marks will be proportional to the total number
of lecture hours as mentioned in the syllabus.
 Subject Subject Theor Practical Tutorial Theory Practical/Oral Tutorial Total
Code Name y Hrs Hrs Credit Credit Credits Credits
Natural
Language 03 – – 03 – – 03
CEMDC602 Processin
g

Subject Code Subject Name Examination Scheme

Theory Marks Term Practical Oral Total

ork

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid xam
Sem
xam

Natural
CEMDC602 Language 20 20 20 20 60 – – -- 100
Processing

Course Objectives:

1. To understand natural language processing and to learn how to apply basic algorithms
in this field.
2. To get acquainted with the basic concepts and algorithmic description of the main
language levels: morphology, syntax, semantics, and pragmatics.
3. To design and implement applications based on natural languageprocessing

Course Outcomes: After completion of this course learner will be able to

1. Understand the capabilities and limitations of natural languageprocessing

2. Model linguistic phenomena with formal grammars
3. Design and implement algorithms for syntax analysis
4. Identify and resolve references between sentences from thediscourse
5. Use the mathematical and linguistic foundations for semantic analysis
6. Apply NLP techniques to design real world NLP applications

Prerequisites:
1. Basic Linguistics
2. Machine Learning

Sr. Detailed Content CO

No. Module Hours Mapping

Introduction to Why NLP? Generic NLP system, Stages of

1 Natural Language NLP, Challenges in NLP, Applications of 04 CO1
Processing (NLP) NLP
Morphology, Types of morphology, Role
of Regular expression and finite automata
Morphological in morphology, Stemming vs
2 07 CO2
Analysis Lemmatization, Porter stemmeralgorithm,
Language model- Ngram
Part-Of-Speech tagging( POS), POS tag
ambiguity, Rule based tagging, Stochastic
POS tagging, Parsing with CFG, Sequence
3 Syntactic analysis 08 CO3
labelling: Hidden Markov Model (HMM),
Maximum Entropy
Lexical Semantics, Attachment for
fragment of English language, Semantic
relations among lexemes & their senses,
4 Semantic Analysis Wordnet, Word Sense Disambiguation- 08 CO4
Dictionary based, Machine Learning based
approach
Introduction to Pragmatics and Discourse
analysis, reference phenomenon, reference
Pragmatics and resolution problem, Syntactic & semantic
5 06 CO5
Discourse constraints on co reference, Lappin and
Leass' Algorithm for Pronoun Resolution

Machine translation, Informationretrieval,

Information extraction (Question-
6 Applications AnswerSystem), Summarization, 06 CO6
Sentiment Analysis, Named Entity
Recognition Applications in Indian
regional languages
Text Books:

1. Daniel Jurafsky, James H. Martin, “Speech and Language Processing”, Second Edition,
Prentice Hall, 2008.
2. Christopher D. Manning and Hinrich Schutze, “Foundations of Statistical Natural
Language Processing” MIT Press, 1999.

Reference Books:

1. Siddiqui and Tiwary U.S., “Natural Language Processing and Information Retrieval”,
Oxford University Press (2008).
2. Daniel M Bikel and Imed Zitouni, “Multilingual natural language processing
applications”, Pearson, 2013.

Evaluation Scheme:

1. In-Semester Assessment:
• Assessment consists of two Internal Assessments (IA1, IA2) out of which; one
should be compulsory class test (on minimum 02 Modules) and the other is a
class test / assignment on case studies / course project.
• Mid Semester Examination (MSE) will be based on 40-50% of thesyllabus.

2. End-Semester Examination:
• Question paper will comprise of full syllabus.
• In the question paper, weightage of marks will be proportional to the total
number of lecture hours as mentioned in the syllabus.
 Subject Subject Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Code Name Hrs Hrs Hrs Credit Credit Credits Credits
Social
Networ
CEMDL601 - 02 -- - 01 - 01
k
Analysis

Subject Code Subject Examination Scheme

Name
Theory Marks Term Practical Oral Total
Work & Oral

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid Exam
Sem
Exam

Social
Networ
CEMDL601 - - - - - 25 - 25 50
k
Analysis

Course Objectives:
1. To understand the fundamental concepts of social media networks.
2. To learn various social media analytics tools and evaluationmatrices.
3. To collect and store social media data.
4. To analyze and visualize social media data
5. To design and develop social media analytics models.

Course Outcomes: Student will able to

1. Understand characteristics and types of social media networks.

2. Use social media analytics tools for business.
3. Collect, monitor, store and track social mediadata.
4. Analyze and visualize social media data from multiple platforms.
5. Design and develop content and structure based social media analyticsmodels.
6. Design and implement social media analytics applications forbusiness.

Prerequisites:

1. Python
Sr Title CO
No. Mapped

1 Study various - CO1

i) Social Media platforms ( Facebook, twitter, YouTubeetc)

ii) Social Media analytics tools ( Facebook insights, googleanalytics

net lyticetc)

iii) Social Media Analytics techniques and engagement metrics (page

level, post level, member level)

iv) Applications of Social media analytics forbusiness.

e.g. Google Analytics

https://marketingplatform.google.com/about/analytics/

https://netlytic.org/

2 Data Collection-Select the social media platforms of your choice (Twitter, CO2
Facebook, LinkedIn, YouTube, Web blogs etc) ,connect to and capture
social media data for business ( scraping, crawling, parsing).

3 Data Cleaning and Storage- Preprocess, filter and store social media data CO3
for business (Using Python, MongoDB, R, etc).

4 Exploratory Data Analysis and visualizationof Social Media Data for CO4
business.

5 Develop Content (text, emoticons, image, audio, video) based social CO5
media analytics model for business.

(e.g. Content Based Analysis :Topic , Issue ,Trend, sentiment/opinion

analysis, audio, video, image analytics)
 6 Develop Structure based social media analytics model for any business. CO6

( e.g. Structure Based Models -community detection, influence analysis)

7 Mini Project -

Text Books:

1. Siddhartha Chatterjee , Michal Krystyanczuk, “Python Social Media Analytics:

Analyze and visualize data from Twitter, YouTube, GitHub, and more”, Kindle Edition.
2. Matthew A. Russell, “Mining the Social Web: Data Mining Facebook, Twitter,
Linkedin, Google+, Github, and More”, 2nd Edition, O'Reilly Media, 2013.

Term Work:

The Term work Marks are based on the weekly experimental performance of the
students, Oral performance and regularity in the lab.
Students are expected to be prepared for the lab ahead of time by referring the manual
and perform the experiment under the guidance and discussion. Next week the
experiment write-up to be corrected along with oral examination.

End Semester Examination:

End of the semester, there will be Oral examination based on the laboratory work and
the corresponding theory syllabus.
 Subject Subject Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Code Name Hrs Hrs Hrs Credit Credit Credits Credits

Natural
Language -- 02 -- -- 01 -- 01
CEMDL602
Processing
Lab

Subject Code Subject Examination Scheme

Name
Theory Marks Term Practical Oral Total
Work & Oral

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid Exam
Sem
Exam

Natural
Language
CEMDL602 - - - - - 25 - 25 50
Processing
Lab

Course Objectives:

1. To design and implement various algorithms in different stages of natural

language processing.
2. To explore various machine learning tools and techniques.
3. To use appropriate natural technique for real world applications.

Course Outcomes: At the end of the course learner will able to

1. Understand fundamentals of natural language text processing and implement basic

commands of text processing tool
2. Apply morphological analysis on natural language text
3. Analyze syntactic structure of a language using syntax analysistechniques
4. Identify semantic relationships between words using semanticanalysis
5. Apply the discourse analysis techniques to resolve thereferences
6. Apply NLP techniques to solve real world problems

Prerequisites:

1. Basic Linguistics
 2. Statistics

Suggested Experiments:

Experiment Experiments Name CO

No. Mapping

1 Study of R tool and basic commands to access text data. CO1

2 Perform Preprocessing (Tokenization, Scrip Validation, CO2

Stop word removal and stemming) of Text.

3 Implement N-Gram (Bigram) model for next word CO3

prediction.

4 Implement Rule-based Part-of-Speech (POS) Tagging. CO3

5 Implement Lesk Algorithm for Word Sense Disambiguation CO4

using Wordnet dictionary.

6 Implement the Lappin and Leass' algorithms for pronoun CO4

resolution.

7 Perform Name Entity Recognition (NER) on given text. CO6

8 Case study on Indian Regional Language. CO6

Text Books:

1. Daniel Jurafsky, James H. Martin, “Speech and Language Processing”, Second Edition,
Prentice Hall, 2008.
2. Niel J le Roux, Sugnet Lubbe, “A step by step tutorial: An introduction into R
application and programming”.

Reference Books:

1. Siddiqui and Tiwary U.S., “Natural Language Processing and Information Retrieval”,
Oxford University Press (2008)
2. Steven Bird, Ewan Klein, “Natural Language Processing with Python”,O‘Reilly.

Term Work:

The Term work Marks are based on the weekly experimental performance of the
students, Oral performance and regularity in the lab.
 Students are expected to be prepared for the lab ahead of time by referring the manual
and perform the experiment under the guidance and discussion. Next week the
experiment write-up to be corrected along with oral examination.

End Semester Examination:

End of the semester, there will be Oral examination based on the laboratory work and
the corresponding theory syllabus.
 Subject Subject Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Code Name Hrs Hrs Hrs Credit Credit Credits Credits

Computati
CEMDC701 onal 03 - - 03 - - 03
Intelligence

Subject Code Subject Examination Scheme

Name
Theory Marks Term Practical Oral Total
Work & Oral

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid Exam
Sem
Exam

Computation
CEMDC701 al 20 20 20 20 60 - - - 100
Intelligence

Course Objectives:
1. To familiarize the students with basics of ANN, optimization and deep Learning.
2. To understand the various steps followed in solving Prediction problems and to choose the right prediction
method to develop a model.
3. To learn the modern heuristic optimization techniques and apply them for problem solving.
4. To learn MLP BP Neural Network and deep learning methods and to design and develop ANN
Classification systems.
5. To learn the underlying theory of building hybrid systems for better decision making.

Course Outcomes: At the end of the course learner will able to

1. Understand the basics of various CI techniques and to find a suitable classifier based on the given problem.
2. Differentiate various Prediction methods and choose the right prediction method to develop a model.
3. Analyse and apply the various optimization techniques to solving complex problems which cannot be
solved using traditional methods.
4. Differentiate the various supervised and unsupervised ANN techniques and to choose a suitable technique
to design and develop classification and regression problems.
5. To select, configure and to use the CNN and RNN deep learning networks.
6. To build a hybrid model for better accuracy in decision making.

Prerequisites:

Artificial Intelligence, Machine Learning, Soft Computing, Image Processing, Computer Vision
Sr. Detailed Content CO
Module Hours
No. Mapping

Introduction
Differentiate Hard and Soft Computing,
1 Soft Computing 04 CO1
Soft Computing Constituents and
characteristics, Foundation of Prediction,

Data Preparation, Different Prediction

2 Prediction Methods, Mathematical Methods, 08 CO2
Distance based Methods, Logic Methods,

Annealing, Tabu Search, Evolutionary

3 Optimization Algorithms - Genetic Optimization, 08 CO3
Particle Swarm Optimization, Ant Colony
Optimization

Supervised ANN
Single layer Feed forward networks, Multi
layer feed forward net, learning algorithms,
back-propagation
4 Neural Networks 08 CO4
Unsupervised ANN
Self Organizing Maps, Learning Vector
Quantization
Convolution Neural Network
Convolutional Neural Networks, LeNet,
AlexNet, VGGNet
5 Deep Networks Recurrent and Recursive Nets 7 CO%
Bidirectional RNNs, Bidirectional RNNs,
The Long Short-Term Memory and Other

6 Hybrid Systems Hybrid Systems for Prediction, Hybrid 4 CO6

Systems for Optimization
Text Books:

1. Andries P. Engelbrecht, “Computational Intelligence An Introduction, Second Edition, Wiley Publication

2. Samir Roy and Chakraborty, “Introduction to soft computing”, Pearson Edition.
3. Zbigniew Michalewicz, Martin Schmidt, Matthew Michalewicz, Constantin Chiriac, "Adaptive Business
Intelligence", Springer Publication 2006
4. Ian Goodfellow and Yoshua Bengio and Aaron, Deep Learning, An MIT Press book.
5. S.N.Sivanandam, S.N.Deepa "Principles of Soft Computing" Second Edition, Wiley Publication

Reference Books:

1. J.S.R.Jang "Neuro-Fuzzy and Soft Computing", PHI 2003.

2. S. Rajasekaran and G.A. Vijaylakshmi Pai., “Neural Networks Fuzzy Logic, and Genetic
Algorithms”, Prentice Hall of India.
3. Satish Kumar, "Neural Networks A Classroom Approach" Tata McGrawHill.

Evaluation Scheme:

• Assessment consists of two Internal Assessments (IA1, IA2) out of which; one should be compulsory
class test (on minimum 02 Modules) and the other is a class test / assignment on case studies / course
project.
• Mid Semester Examination (MSE) will be based on 40-50% of the syllabus.

End-Semester Examination:
• Question paper will comprise of full syllabus.
• In the question paper, weightage of marks will be proportional to the total number of lecture hours as
mentioned in the syllabus
 Subject Subject Theory Practical Tutorial Theory Practical/Oral Tutorial Total
Code Name Hrs Hrs Hrs Credit Credit Credits Credits

Computatio
nal
CEMDL701 Intelligence 02 01 01
Lab

Subject Code Subject Examination Scheme

Name
Theory Marks Term Practical Oral Total
Work & Oral

In-Sem Evaluations End

Sem
IA1 IA2 AVG Mid Exam
Sem
Exam

Computational
CEMDL701 Intelligence 25 25 50
Lab

Course Objectives:

1. To familiarize the students with basics of modern Computational Intelligence techniques.

2. Enable the student to analyse the problem, identify the soft computing techniques to address the
problem, analyse and design solutions to solve the problem.
3. To learn the tools and techniques of Computational Intelligence and apply them to solve the problem
Course Outcomes: At the end of the course learner will able to

1. Analyse a given problem, identify the soft computing techniques to address the problem.
2. Perform pre-processing, design and Implement a Prediction model for the above application.
3. Analyse the problem, identify the Optimization techniques to address the problem, design and
implement the optimization model.
4. Analyse the problem, identify the suitable NN techniques to address the problem, design and implement
the NN model
5. Analyse the problem, identify the suitable Deep Learning techniques to address the problem, design and
implement the model
6. Analyse the problem, identify the suitable models to build a hybrid module that can perform better than
the individual models.

Prerequisites:

Machine Learning, Soft Computing, Image Processing, Computer Vision

 Suggested Experiments:

Sr. CO
Module Detailed Content Hours
No. Mapping
Choose an application, analyse the problem, identify the
1 1 4 LO1
soft computing techniques to address the problem
Perform pre-processing, design and Implement a
2 2 2 LO2
Prediction model for the above application
Choose an application, analyse the problem, identify the
3 3 4 LO2
Optimization techniques to address the problem
3 Design and Implement an Optimization model for the
4 2 LO2
above application
Choose an application, analyse the problem, identify the
5 4 4 LO3
NN technique to address the problem
Design and Implement an NN model for the above
6 4 2 LO4
application
Choose an application, analyse the problem, identify the
7 5 4 LO4
Deep learning technique to address the problem
Design and Implement an Deep learning NN model for
8 5 2 LO4
the above application
Choose an application, analyse the problem, identify the
9 6 4 LO5
need for Hybrid technique to address the problem
Design and Implement an Hybrid model for the above
10 6 2 LO6
application

Text Books:
1. Jake VanderPlas, Python Data Science Handbook: Essential Tools for Working with Data, O’reilly
Publication
2. Wes McKinney , Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython,
O’reilly Publication
3. Jason Test, PYTHON FOR DATA SCIENCE
4. Jason Test, Python Programming: 3 BOOKS IN 1

Term Work:

The Term work Marks are based on the weekly experimental performance of the students, Oral
performance and regularity in the lab.
Students are expected to be prepared for the lab ahead of time by referring the manual and perform
the experiment under the guidance and discussion. Next week the experiment write-up to be
corrected along with oral examination.

End Semester Examination:

End of the semester, there will be Oral examination based on the laboratory work and the
corresponding theory syllabus.