Format no.

: LP01
Issue No. : 01
Issue Date: 05.05.06
EASWARI ENGINEERING COLLEGE
DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGG
Course plan
Regulation -2017

Course/Branch : B.E./ECE Total no. of hours given in

syllabus:
Subject Code : CS8086 Lecture : 45
Subject Title : Soft Computing Tutorials : -
Year/Semester : IV/V III Practical : Nil
Faculty Name : Mrs. Bindu Babu TOTAL : 45

COURSE OBJECTIVES :

1. Classify the various soft computing frame works

2. Be familiar with the design of neural networks, fuzzy logic and fuzzy systems
3. Learn mathematical background for optimized genetic programming
4. Be exposed to neuro-fuzzy hybrid systems and its applications

Books Page. Teaching

S.No Topics Hours
Referred No Methodology
UNIT I: INTRODUCTION TO SOFT COMPUTING
OBJECTIVES:
1. Scope and Components of Soft Computing.
2. Description on ANN with advantages and applications.
3. Overview of Fuzzy logic and Genetic Algorithm.

1. Soft Computing Constituents-From 1 T1 1-4 Chalk and

Conventional AI to Computational Board
Intelligence
2. Artificial neural network: Introduction, 1 T1 7-12 Chalk and
characteristics- learning methods – Board
taxonomy
3. Fuzzy Systems 1 T1 13-18 Chalk and
Board
4. Genetic Algorithm and Evolutionary 1 T1 19-22 Chalk and
Programming Board
5. Swarm Intelligent Systems 1 T1 23-27 Chalk and
Board
6. Classification of ANNs, McCulloch and 1 T1 74-80,80-83 Chalk and
Pitts Neuron Model Board
7. Learning Rules: Hebbian and Delta, 1 T1 85-99 Chalk and
Perceptron Network Board
8. Adaline Network- 1 T1 101 PPT,
 Chart*
9. Madaline Network. 1 T1 104 PPT

Total hours -9
UNIT II: ARTIFICIAL NEURAL NETWORKS
OBJECTIVES:
1. Description of various learning.
2. Architecture, flowchart, training and testing algorithm of various networks.
3. Comparison of salient features and differences of various networks.

10. Back propagation Neural Networks 1 T1 118-142 Chalk and

Board
11. Kohonen Neural Network 1 T1 153-159 PPT,
Handouts
12. Learning Vector Quantization 1 T1 164-172 PPT, Handouts
13. Hamming Neural Network 1 T1 175-181 PPT,
Handouts,
Chalk and
Board
14. Hopfield Neural Network 1 T1 186-191 PPT,
Handouts
15. Bi-directional Associative Memory 1 T1 197-204 PPT,
Handouts,
Chalk and
Board
16. Adaptive Resonance Theory 1 T1 208 PPT,
Handouts
17. Support Vector Machines 1 T1 222 PPT,
Handouts
18. Spike Neuron Models 1 T1 259-263 PPT,
Handouts,
Chalk and
Board
Total Hours –9
UNIT III- FUZZY LOGIC
OBJECTIVES:
1. Need and types of Fuzzification and Defuzzificaton process.
2. Concept of Fuzzy arithmetic, measures and reasoning
3. Overview of Fuzzy inference, expert system and decision making.
1. Introduction to Fuzzy Logic 1 T2 313-315 PPT,
Chalk and
Board
2. Classical Sets and Fuzzy Sets 1 T2 315-322
3. Classical Relations and Fuzzy Relations, 1 T2 339-349,
Membership function 369-379
4. Defuzzification, lambda cuts – methods, 2 T2 389-398 PPT,
 Problems Chalk and
Board
5. Fuzzy arithmetic and fuzzy measures, 1 T2 415-430 PPT,
Fuzzy arithmetic - extension principle - Chalk and
fuzzy measures - measures of fuzziness - Board
fuzzy integrals, Problems
6. Fuzzy rule base and approximate reasoning : 1 T2 437-445 PPT
truth values and tables, fuzzy propositions,
formation of rules-decomposition of rules,
aggregation of fuzzy rules, fuzzy reasoning
7. Fuzzy inference systems- Overview of fuzzy 1 T2 445-449 PPT
expert system
8. Fuzzy decision making. 1 T2 453-458 PPT
Total hours -9
UNIT-IV: GENETIC ALGORITHM
OBJECTIVES:
1. Comparison of Traditional algorithm with Genetic Algorithm.
2. Operators and classifications of Genetic Algorithm.
3. Features and operational properties of Genetic Programming.
1. 1 Genetic algorithm- Introduction - biological 1 T2 455-462 PPT
background traditional optimization
2. Search techniques Genetic basic concepts 1 T2 462-471 PPT
3. 2 Operators – Encoding scheme 1 T2 471-473 PPT
4. Fitness evaluation 1 T2 473-476 PPT
5. 3 Reproduction, Crossover 1 T2 476-480 PPT
6. 4 Inversion and Deletion, , 2 T2 480-483, PPT
Problems 483-487
7. Mutation, Bitwise operators 1 T2 511-522 PPT
8. 5 Convergence of Genetic Algorithm. 1 T2 Notes PPT
from
Internet
Total hours–9
UNIT-V: HYBRID SOFT COMPUTING TECHNIQUES
OBJECTIVES:
1. Properties, characteristics and advantages of various hybrid systems
2. Knowledge to develop hybrid fuzzy controllers using Soft computing
techniques.
1. 1 Hybrid Systems -Neural Networks, Fuzzy 1 T3 297-300 Chalk and
Logic and Genetic Board
2. GA Based Weight Determination 2 T3 306-313 Chalk and
Board
3. 2 LR-Type Fuzzy Numbers 1 T3 320-330 Chalk and
Board
4. Fuzzy Neuron 1 T3 330 NPTEL
5. 4 Fuzzy BP Architecture, Learning in Fuzzy 1 T3 331-339 Chalk and
BP- Inference by Fuzzy BP Board
6. 5 Fuzzy ArtMap: 1 T3 358-361 Chalk and
Board
7. Soft Computing Tools - GA in Fuzzy Logic 1 T3 417-418 PPT
Controller Design
8. Fuzzy Logic Controller 1 T3 425-426 PPT

Total Hours-9
Total hours required to complete all the 5 units---45

 Methodology followed: Chalk & Board/Chart/ Handouts/Power point presentation

CONTENTS BEYOND THE SYLLABUS

SL.NO. TOPIC PO PSO

1 Third Generation NN PO3, PO6 PSO3
2 Catheterization Laboratory PO3,PO6,PO8 PSO2,PSO3
instrumentation
3 MATLAB implementation PO3,PO5,PO8 PSO2,PSO3
of Fuzzy Logic Applications
4 Genetic Algorithm based PO6,PO12,PO5, PSO2,PSO3
Machine learning classifier
system
5 Neuro fuzzy system PO3,PO5,PO6 PSO3

TEXT BOOKS:
1. N.P.Padhy, S.P.Simon, "Soft Computing with MATLAB Programming", Oxford
University Press, 2015.
2. S.N.Sivanandam , S.N.Deepa, "Principles of Soft Computing", Wiley India Pvt.Ltd.,
2nd Edition, 2011.
3. S.Rajasekaran, G.A.Vijayalakshmi Pai, "Neural Networks, Fuzzy Logic and Genetic
Algorithm, Synthesis and Applications ", PHI Learning Pvt.Ltd., 2017.

REFERENCES
1. Jyh-Shing Roger Jang, Chuen-Tsai Sun, Eiji Mizutani, ―Neuro-Fuzzy and Soft
Computing‖, Prentice-Hall of India, 2002.
2. Kwang H.Lee, ―First course on Fuzzy Theory and Applications‖, Springer, 2005.
3. George J. Klir and Bo Yuan, ―Fuzzy Sets and Fuzzy Logic-Theory and Applications‖,
Prentice Hall, 1996.
4. James A. Freeman and David M. Skapura, ―Neural Networks Algorithms,
Applications, and Programming Techniques‖, Addison Wesley, 2003.

ASSIGNMENTS:
1. Problem on various Neural Networks.
2. Multilevel optimization and Real life problem- advances in GA.
3. Problems on Traveling salesman problem using Genetic Algorithm.

Course Outcomes:
Students must be able to
CO1: Examine the soft computing techniques for finding the optimal solutions.
CO2: Analyze various neural network architectures for classification and
clustering
applications.
CO3: Develop decision making and expert system using fuzzy logic control.
CO4: Solve optimization problems using genetic algorithms.
CO5: Apply hybrid soft computing techniques in real time problems.

Program Outcomes:
PO1: Engineering Knowledge
PO2: Problem Analysis
PO3: Design/Development of Solutions
PO4: Conduct investigations of complex problems
PO5: Modern Tool Usage
PO6: The Engineer and Society
PO7: Environment and Sustainability
PO8: Ethics
PO9: Individual and Team Work
PO10: Communication
PO11: Project Management and Finance
PO12: Life Long Learning

MAPPING OF COURSE OUTCOMES WITH THE PROGRAM OBJECTIVES:

CO/PO P PO PO PO PO PO PO PO PO PO1 PO1 PO1

O1 2 3 4 5 6 7 8 9 0 1 2
CO1 3 3 3 3 3 3 1 1 1 1 1 3
CO2 3 3 3 3 3 3 1 1 1 1 1 3
CO3 3 3 3 3 3 3 1 1 1 1 1 3
CO4 3 3 3 3 3 3 1 1 1 1 1 3
CO5 3 3 3 3 3 3 1 1 1 1 1 3
CS8086 3 3 3 3 3 3 1 1 1 1 1 3

Justification of the mapping:

CO1 An moderate knowledge of mathematics is required to apply (PO1) ,
Analyze(PO2), design and develop solutions (PO3) for complex real time
problems(PO4) by the usage of modern tools(PO5) to meet the requirement of
engineer and society(PO6).With proper discussion (PO10) along with team-
 mates(PO9) modify (PO7) / gain knowledge to meet the recent developments
(PO12).
CO2 Fundamental knowledge of mathematics (PO1) is necessary to investigate
(PO4), formulate(PO2) and develop solutions(PO3) for problems(PO4) in
society(PO12) by engineer(PO6) with tools(PO5) on neural networks.
CO3 Adequate mathematical knowledge (PO1) is essential to assimilate (PO2) the
if-then-rule of fuzzy to design and provide solutions (PO3) by the usage of
tools (PO5) for complicated problems (PO4) to the societal needs (PO6) by
usage of latest expert system (PO12).
CO4 Various possible permutation and combination (PO1) of solutions for the
societal problems using genetic algorithm by observing, analyzing (PO2), apply
the natures evolution technique to solve complex problems (PO3 & PO4) of
society (PO6) with ease using modern tools (PO5) by usage of appropriate
optimization techniques (PO12).
CO5 Application(PO2) of mathematics and the engineering concepts learnt (PO1) to
select design(PO3), integrate and hybrid soft computing techniques of
appropriate applications(PO4) for real time-applications (PO6) with the
usage of latest modern tools (PO5)by analyzing problems(PO4) and provide
design solutions(PO3). Conclusions(PO10) derived through experiments (PO8)
for real time communication problems(PO7)

PROGRAM SPECIFIC OUTCOMES:

PSO1: Design and construct Electronic circuits and to Simulate the circuits with software
tools which lead to the development of Electronic gadgets.
PSO2: Design and analyze various signal processing blocks for Image and Signal
processing systems
PSO3: Analyze various Networking and Communication areas and its impact in real time
applications
PSO4: Implement their professional skills and techniques in the integrated circuit design
which are applicable to industrial and societal needs.

MAPPING OF PROGRAMMME OUTCOMES WITH THE PROGRAM SPECIFIC

OUTCOMES:

Program Programme Outcomes

Specific PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
Objectives
1 3 3 3 3 3 3 3 3 2 2 1 3
2 3 3 3 3 3 3 3 3 2 2 1 3
3 3 3 3 3 3 3 3 3 2 2 1 3
4 3 3 3 3 3 3 3 3 2 2 1 3
MAPPING OF COURSE OUTCOMES WITH THE PROGRAM SPECIFIC
OUTCOMES:

CO PSO1 PSO2 PSO3 PSO4

CO1 3 2 2 3
CO2 3 2 2 3
CO3 3 2 2 3
CO4 3 2 2 3
CO5 3 2 2 3
CS8086 3 2 2 3

Justification of the mapping:

CO1 Knowledge of hardware (PSO1) and analysis of software (PSO2) is required
for understanding the Computational capabilities (PSO3) for the
technological growth (PSO4).
CO2 Understanding of architecture (PSO1) and analysis of algorithm (PSO2) is
required for implementing the concepts (PSO3) for the societal needs and
real time applications (PSO4).
CO3 An insight into hardware and software (PSO1) helps in design and
development of expert system for society (PSO3) for performing day-to-day
work by modifying the systems with innovative ideas.
CO4 An overall understanding of programming concepts(PSO2) for the genetic
algorithm to optimize the search procedure to reach target, thereby reducing
the computational complexity(PSO3) and hardware requirements(PSO1) to
to satisfy the target requirement (PSO4)
CO5 To utilize the concept (PSO1, PSO2) of various systems integrated to form
hybrid soft computing techniques with less computational capabilities
(PSO3) with innovative ideas for real time applications and research areas
(PSO4).

Prepared by: Reviewed by: HOD/ECE

Mrs.Bindu Babu