RS4002 - Soft Computing Techniques (Syllabus) 2021-regulation Anna University

Soft Computing Techniques

RS4002	SOFT COMPUTING TECHNIQUES	LTPC

3003

OBJECTIVE:

• The objective of the course is to make the students to understand the concepts of Artificial Neural Network, Fuzzy logic and Genetic algorithms and also their application in Geomatic.

UNIT I	ARTIFICIAL NEURAL NETWORKS	9

Introduction - soft computing vs. hard computing - soft computing techniques – applications - ANN : definition - Structure and Function of a single neuron: Biological neuron, artificial neuron, Taxonomy of neural net, Difference between ANN and human brain, characteristics and applications of ANN, single layer network, Perceptron training algorithm, Linear separability, Widrow & Hebbian learning rule/Delta rule, ADALINE, MADALINE - Introduction of MLP – Deep Learning concepts - Geomatic Applications.

UNIT II	FUZZY SYSTEMS	9

Fuzzy Logic: Fuzzy set theory, Fuzzy set versus crisp set, Crisp and fuzzy relations, Fuzzy systems: crisp logic, fuzzy logic, introduction and features of membership functions,Fuzzy rule base system : fuzzy propositions, formation, decomposition & aggregation of fuzzy rules, fuzzy reasoning, fuzzy inference systems, fuzzy decision making and Geomatic Applications

UNIT III	NEURO-FUZZY MODELLING	9

Adaptive Neuro-Fuzzy Inference Systems – Architecture – Hybrid Learning Algorithm – Learning Methods that Cross-fertilize ANFIS and RBFN – Coactive Neuro Fuzzy Modeling – Framework Neuron Functions for Adaptive Networks – Neuro Fuzzy Spectrum.

UNIT IV	GENETIC ALGORITHM	9

Genetic algorithm : Fundamentals, basic concepts, working principle, encoding, fitness function, reproduction, Genetic modeling: Inheritance operator, cross over, inversion & deletion, mutation operator, Bitwise operator, Generational Cycle, Convergence of GA, Applications & advances in GA, Differences & similarities between GA & other traditional method.

UNIT V	APPLICATIONS IN GEOMATICS	9

AI Search algorithm-Predicate calculus –Knowledge acquisition and representation - rules of interface - Semantic networks-frames-objects-Hybrid models – Geomatic applications

TOTAL : 45 PERIODS

OUTCOMES: On completion of the course, the student is expected to be able to

CO1 Understanding the necessity of soft computing techniques and fundamentals of Artificial Neural Networks
CO2 Imparts the concepts of uncertainty and its impacts on artificial intelligence
CO3 Helps to realize the merits of hybrid computing techniques
CO4 Introduces the concepts of heuristic search methods and optimization of solutions
CO5 Gain knowledge on utility of soft computing on multidisciplinary problems

REFERENCES:

1. Introduction to Artificial Neural Systems by Jacek.M Zurada, Jaico Publishing House, 2004.
2. Freeman J.A. and Skapura B.M., "Neural Networks, Algorithms Applications and Programming Techniques", Pearson ,2002.
3. Jang J.S.R.,Sun C.T and Mizutami E - Neuro Fuzzy and Soft computing Pearson, 2015.
4. Timothy J.Ross: Fuzzy Logic with Engineering Applications. McGraw Hill,NewYork, 4th Edition,2016.
5. Laurene Fauseett: Fundamentals of Neural Networks. Prentice Hall India, New Delhi,Pearson, 2004.
6. George J.Klir and Bo Yuan, Fuzzy Sets and Fuzzy Logic, Prentice Hall Inc., New Jersey,1995
7. Nih.J. Ndssen Artificial Intelligence, Harcourt Asia Ltd.,Singapore,1998