Vous êtes sur la page 1sur 18

FUZZY LOGIC

ENGR. ARGEL A. BANDALA, MSECE


argel.bandala@dlsu.edu.ph
argel_bandala@yahoo.com
argel_bandala@ieee.org
OUTLINE OF DISCUSSION

 Introductory Concepts
 Artificial Intelligence
 Computational Intelligence
 Knowledge Representation
 Fuzzy Logic
 Introduction to Fuzzy Logic
 Researches in Fuzzy Logic
 Samples
Artificial Intelligence

 Is the intelligence of machines


and the branch of computer
science that aims to create it.
 The study and design of intelligent
agents
An agent is a system that perceives its
environment and takes actions that
maximize its chances of success
Computational Intelligence

 Is a set of nature-inspired computational


methodologies and approaches to
address complex real-world problems to
which traditional approaches, i.e., first
principles modeling or explicit statistical
modeling, are ineffective or infeasible.
Knowledge Representation

 Is an area of artificial
intelligence research aimed at
representing knowledge in symbols to
facilitate inferencing from those
knowledge elements, creating new
elements of knowledge
What is Fuzzy Logic?

 SMALL
 MEDIUM
 LARGE

 10
 40
 100
What is Fuzzy Logic?

 SMALL
 MEDIUM
 LARGE

 100
 400
 1000
Lofti Zadeh
 February 4,1921
 Father of Fuzzy Logic
 IEEE Medal of Honor
 ACM Fellow
Fuzzy Logic
 A fuzzy logic system is a system design that is
based on how the human brain thinks.
 Fuzzy logic looks at the world in imprecise terms
in much the same way that our own brain takes
in information.
 The information is described in terms of fuzzy
linguistic terms.
 These fuzzy linguistic terms are called fuzzy sets
and can be regarded as sets of singletons, the
grades of which are not only 1 but also ranging
from 0 to 1.
 Each singleton is an element of fuzzy sets.
Membership Functions

 Trapezoidal MF’s specified by four parameters {a,b,c,d}


which determine the x coordinate as follows:
trapezoid(x ; a,b,c,d) = max{min{(x -a)/(b -a),1,
(d -x)/(d -c)},0}

 Triangular MF’s specified by three parameters {a,b,c}


which determine the x coordinate as follows:
triangle(x ; a,b,c) = max{min{(x -a)/(b -a),
(c -x)/(c-b)},0}
Membership Functions
Fuzzy Associative
Matrix
 The technique used to store and represent
fuzzy rules is the fuzzy associative memory
matrix.
 This matrix may have dimensions higher than
two.
 Usually the number of inputs, or antecedents,
to the fuzzy rules determines the dimension
of the matrix.
Weight Value of FAM
Matrix
w1 = min{FZE{(0.8),FN(-0.7)}
= min {0.7, 0.13} = 0.13
w2 = min{FZE(0.S),FZE(-0.1)}
= min {0.7,0.8} = 0.7
w3 = min{FP(0.8),FN(-0.7)}
= min {0.2,0.13} = 0.13
w4 = min{FP(0.8),FZE(-0.1)}
= min {0.2,0.8} = 0.2
Defuzzification

Center of gravity formula


𝑛
𝑖=1 𝑜𝑖 𝑤𝑖
 𝑛 𝑤
𝑖=1 𝑖
THANK YOU!
ENGR. ARGEL A. BANDALA, MSECE
argel.bandala@dlsu.edu.ph
argel_bandala@yahoo.com
argel_bandala@ieee.org

Vous aimerez peut-être aussi