Download Soft computing is an association of computing

Course
Year
: T0423-Current Popular IT III
: 2013
Introduction to Artificial Intelligence and
Soft Computing
Session 1
Lecture Outline
•
•
•
•
Introduction to Artificial Intelligence
Introduction to Hard and Soft Computing
The utility of Fuzzy systems
Introduction to Fuzzy Logic
Bina Nusantara University
3
Lecturer
• Dr. Widodo Budiharto D2637
Email : [email protected]
HP :08569887384
• Quiz 3x
• TM 3x
• Final Project presentation(Group) at session 13
• Reference book:
http://ruangbacafmipa.staff.ub.ac.id/files/2012/02/ebooksclub.org__Fuzzy_Logi
c_with_Engineering_Applications__Third_Edition.pdf
Bina Nusantara University
4
Intro What is Fuzzy Logic
• Demo Video
Bina Nusantara University
5
Artificial Intelligence
• Definition :
(1) a branch of computer science dealing with the
simulation of intelligent behavior in computers
(2) the capability of a machine to imitate intelligent human
behavior (merriam-webster.com)
• The branch of computer science concerned with making
computers behave like humans. (John McCarty)
Bina Nusantara University
6
Artificial Intelligence
Domain Area
Bina Nusantara University
7
Soft Computing
• Soft computing is an association of computing
methodologies that includes fuzzy logic, neurocomputing, evolutionary computing, and probabilistic
computing. (P. Bonissone, 2000).
Bina Nusantara University
8
Soft Computing
• Hard Computing (conventional) requires a precisely
stated analytical model and often a lot of computation
time. Many analytical models are valid for ideal cases.
Real world problems exist in a non-ideal environment.
• Soft computing was introduced by Prof. Lotfi Zadeh in
1992. It is a collection of some biologically-inspired
methodologies such as Fuzzy Logic, Neural Network,
Genetic Algorithm, and combined forms such as GA-FL,
GA-NN, NN-FL.
Bina Nusantara University
9
Hard Vs Soft
Computing
• Hard computing based on binary logic, crisp systems,
numerical analysis and crisp software (exp. PID
Controller) but soft computing based on fuzzy logic,
neural nets and probabilistic reasoning.
• Soft computing is tolerant of imprecision, uncertainty,
partial truth, and approximation.
• Hard computing requires exact input data; soft
computing can deal with ambiguous and noisy dat
Bina Nusantara University
10
Demo Hard computing
• Demo Video
Bina Nusantara University
11
A review of Soft Computing
components
Bina Nusantara University
12
Methods of
Soft Computing
•
•
•
•
•
Fuzzy Logic
Neural Network Theory
Probabilistic Reasoning
Evolutionary Computing
Genetic Algorithm
Bina Nusantara University
13
Evolutionary computing
• Is a subfield of artificial intelligence (computational
intelligence) that involves continuous optimization and
combinatorial optimization problems.
• Evolutionary computing uses iterative progress, such as
growth or development in a population. This population
is then selected in a guided random search using parallel
processing to achieve the desired end.
• Such processes are often inspired by biological
mechanisms of evolution.
• Evolutionary programming was introduced by Lawrence
J. Fogel in the US, while John Henry Holland called his
method a genetic algorithm
Bina Nusantara University
14
The Utility of
Fuzzy Systems
• Several sources have shown and proven that fuzzy
systems are universal approximators. Hence, fuzzy
systems are very useful in two general contexts:
(1) in situations involving highly complex systems whose
behaviors are not well understood, and
(2) In situations where an approximate, but fast, solution is
warranted.
Bina Nusantara University
15
Fuzzy Logic
• Fuzzy logic is a form of many-valued logic or
probabilistic logic; it deals with reasoning that is
approximate rather than fixed and exact. In contrast with
traditional logic they can have varying values, where
binary sets have two-valued logic, true or false, fuzzy
logic variables may have a truth value that ranges in
degree between 0 and 1.
• Fuzzy logic has been extended to handle the concept of
partial truth, where the truth value may range between
completely true and completely false
Bina Nusantara University
16
Traditional logic
Slow
Speed = 0
Fast
Speed = 1
bool speed;
get the speed
if ( speed == 0) {
// speed is slow
}
else {
// speed is fast
}
Bina Nusantara University
17
Fuzzy Logic
representation
Slowest


For every problem
must represent in
terms of fuzzy sets.
What are fuzzy sets?
[ 0.0 – 0.25 ]
Slow
[ 0.25 – 0.50 ]
Fast
[ 0.50 – 0.75 ]
Fastest
[ 0.75 – 1.00 ]
Bina Nusantara University
18
Why using Fuzzy Logic
• Fuzzy logic allows for approximate values
and inferences as well as incomplete or
ambiguous data (fuzzy data) as opposed
to only relying on crisp data (binary
yes/no choices).
• Fuzzy Logic provides a more efficient and
resourceful way to solve Control
Systems.
• On 2000, Fuzzy Logic Becomes a
Standard Technology and Is Also Applied
in Data and Sensor Signal Analysis.
Bina Nusantara University
19
Application of
Fuzzy Logic
• Sendai Subway system in Sendai, Japan. This control of
the Nanboku line, developed by Hitachi, used a fuzzy
controller to run the train all day long.
• The most tangible applications of fuzzy logic control
have appeared commercial appliances. Specifically, but
not limited to heating ventillation and air conditioning
(HVAC) systems.
• Fuzzy logic also finds applications in many other
systems. For example, the MASSIVE 3D animation
system for generating crowds uses fuzzy logic for
artificial intelligence.
Bina Nusantara University
20
History (1965 by Zadeh)
Bina Nusantara University
21
Fuzzy Sets and
Membership
• Classical sets contain objects that satisfy precise
properties of membership; fuzzy sets contain objects that
satisfy imprecise properties of membership, i.e.,
membership of an object in a fuzzy set can be
approximate.
• For example, the set of heights from 5 to 7 feet is precise
(crisp); the set of heights in the region around 6 feet is
imprecise, or fuzzy.
Bina Nusantara University
22
Fuzzy Sets and
Membership (2)
• For crisp sets (Himpunan klasik) an element x in the
universe X is either a member of some crisp set A or not.
This binary issue of membership can be represented
mathematically with the indicator function,
Nilai keanggotaan
Fungsi keanggotaan
Bina Nusantara University
23
Fuzzy Sets Theory
• Classical Set vs Fuzzy set
Membership value
Membership value
1
1
0
0
175
Height(cm)
175
Height(cm)
Universe of discourse
24
Fuzzy Sets and
Membership (4)
• The membership function embodies the mathematical
representation of membership in a set, and the notation
used throughout this text for a fuzzy set is a set symbol
with a tilde underscore, where the functional mapping is
given by :
• And the symbol
is the degree of membership of
element x in fuzzy set A.
Bina Nusantara University
25
example
• the meanings of the expressions cold, warm, and hot are
represented by functions mapping a temperature scale.
Bina Nusantara University
26
Example
http://petro.tanrei.ca/fuzzylogic/fuzzy_negnevistky.html
• The problem is to estimate the level of risk involved in a
software engineering project. For the sake of simplicity
we will arrive at our conclusion based on two inputs:
project funding and project staffing.
Bina Nusantara University
27
Project Funding
• Suppose our our inputs are project_funding = 35% and
project_staffing = 60%.
Bina Nusantara University
28
Project Staffing
Bina Nusantara University
29
The rules
• If project_funding is adequate or project_staffing is small
then risk is low.
• If project_funding is marginal and project_staffing is
large then risk is normal.
• If project_funding is inadequate then risk is high.
Bina Nusantara University
30
Rule Evaluation results
Bina Nusantara University
31
Rule Evaluation results
Bina Nusantara University
32
Rule Evaluation results
Bina Nusantara University
33
calculation
• We perform a union on all of the scaled functions to
obtain the final result
Bina Nusantara University
34
Result
• The defuzzification can be performed in several different
ways. The most popular method is the centroid method.
Bina Nusantara University
35
Result
• We chose the centroid method to find the final non-fuzzy
risk value associated with our project. This is shown
below.
• The result is that this project has 67.4% risk associated
with it given the definitions above.
Bina Nusantara University
36
Fuzzy Logic Type 2
To handle uncertainty better than Fuzzy Logic
37
Homework
• Develop simple Fuzzy logic program using example in C:
http://www.chebucto.ns.ca/Science/AIMET/archive/ddj/fuzz
y_logic_in_C/
Bina Nusantara University
38
References
• Fuzzy Logic with Engineering Applications, chapter 1.
• Artificial Inteligence : A Modern Approach, chapter 1.
• http://www.seattlerobotics.org/encoder/mar98/fuz/flindex.
html
• http://www.soft-computing.de/def.html
Bina Nusantara
Projects paper (Group)
• Create a paper and Discuss at session 10 and 13
(submission)
• Example topics :
•
•
•
•
Games using fuzzy logic
Decision system using fuzzy
Interval type 2 FLC
Obstacle avoidance for mobile robot using fuzzy
Example paper :
Octavia George, Maria Gorethi, Syerra Riswandi and Widodo Budiharto,
The Development of an Expert Mood Identifier System using Fuzzy Logic
on BlackBerry Platform, Journal of Computer Science, vol 9(6), pp. 733739, USA, 2013. Indexed by SCOPUS
Bina Nusantara University
40