NAME OF COURSE/MODULE: NEURAL NETWORK AND FUZZY LOGIC
COURSE CODE: KEK4743
NAME(S) OF ACADEMIC STAFF: Ir. Dr. Abu Bakar Hasan
RATIONALE FOR THE INCLUSION OF THE COURSE/MODULE IN THE PROGRAMME: This course presents an overview of the theory and applications of artificial neural network and fuzzy systems to electronic engineering applications. The objective of this course is on the understanding of various neural network and fuzzy systems models and the applications of these models to solve engineering problems.
SEMESTER AND YEAR OFFERED: SEM 7 / YEAR 4
TOTAL STUDENT LEARNING TIME (SLT) FACE TO FACE TOTAL GUIDED AND INDEPENDENT LEARNING
L = Lecture

T = Tutorial

P = Practical

O= Others

L

 

42

T

 

0

P

 

12

O

 

0

Guided: 54 hours

Independent Learning: 66 hours

Total: 120 hours

CREDIT VALUE: 3
PREREQUISITE (IF ANY): NONE
OBJECTIVES: To provide an introduction to basic concept and applications of neural network and fuzzy logic methods, allowing students to solve real-world problems with these intelligent methods and provide programming experience implementing these methods.
LEARNING OUTCOMES: Upon successful completion of this course, students should have the ability to:

CLO1: Analyse and solve the problems using related essential concepts, principles and theories (C4 – PO1)

CLO2: Display the ability to solve the problems related to neural networks and fuzzy logic (P4)

CLO3: Demonstrate the ability to communicate and explain on concepts of neural networks and fuzzy logic (A3)

TRANSFERABLE SKILLS: Students should be able to develop problem solving skills through a process of lectures and tutorials.
TEACHING-LEARNING AND ASSESSMENT STRATEGY: Teaching-learning strategy:

The course will be taught through a combination of formal lectures, assignments, group work, blended learning using authentic materials, informal activities and various textbooks.

Assessment strategy:

i.Formative

ii.Summative

SYNOPSIS:

 

Soft computing methods such as neural network and fuzzy logic and their extended systems genetic algorithm are introduced in this course. The course will provide an overview on neural network and fuzzy logic. The applications of the methods will also be discussed and the evolving trend towards the genetic algorithm, shall also be covered. The application using MATLAB software for implementing the solution for real-world problems using these methods will also be introduced.
MODE OF DELIVERY: Lectures, Labs
ASSESSMENT METHODS AND TYPES:
A. Continuous Assessment (50%)
Category Percentage
·    Test

·    Lab

25%

25%

B. FINAL EXAMINATION (50%)
i.          Examination 50% ·    Structured and essay type questions
MAIN REFERENCES SUPPORTING THE COURSE
  1. Neural Networks: A Comprehensive Foundation, Simon Haykin, Prentice Hall, Upper Saddle River, NJ, SECOND EDITION, 1999
ADDITIONAL REFERENCES SUPPORTING THE COURSE
  1. Fuzzy System Theory and Its Applications, T. Terano, K. Asai, and M. Sugeno, Academic Press, San Diego, CA, 1992.
  2. Understanding neural networks and fuzzy logic: basic concepts and applications, Stamatous.V.Kartapolous, IEEE
  3. Fundamental of Artificial Neural Network and Fuzzy Logic, Rajesh Kumar, Laxmi Publications ltd.