AL Baath University
Faculty of Informatics Engineering
5th year, 2015-2016
Bioinformatics
Practical Lab8: Genetic Algorithms
Eng. Nawwar AlMakhlouf
1
In this lecture
Genetic Algorithm Projects:
Scheduling.
Monalisa.
JGAP Examples.
Any Other Accepted Exa

) (Chromosomes
0 p X i p 1; i cfw_1,2,3
A, B, C, D
X X1 X2 X3
A 0.22 0.28 0.35
B 0.53 0.67 0.48
C 0.44 0.55 0.39
D 0.11 0.33 0.25
) (fitness :
:
f (X ) = X1 X 2 X 3
.1 ) (fitness
) (
Chromosome
Rank
f(X) = X1 . X2 . X3
) X = ( X1, X2

) (Chromosomes :
X= a b c d e f g h
) (Gene cfw_1,2,3,4,5,6,7,8
:
X1= 65413532 , X2= 87126611 , X3= 45218736 , X4= 58127634
) (fitness :
)f ( x ) = ( a + b ) (c + d ) + ( e + f ) ( g + h
:
.1 ) ( )
(.

GA : Reminder
Coding or Representation
Victor of parameters (characteristics)
Permutation between stats
Fitness function
Parent selection
Reproduction (dumb process )
Crossover
Mutation
Convergence
106
When to stop
Genetic Algorithms
,
December 1, 2015
Ca

Simple Genetic Algorithm
Begin
Initialize
population
Evaluate Solutions
T =0
Optimum
Solution?
T=T+1
N
Y
Selectio
n
Stop
Crossover
Mutation
79
Genetic Algorithms
,
November 17, 2015
Fitness function
Purpose
Parent selection
Measure for convergence
Should

Case study : Decision making
Prisoners Dilemma
Classic problem of conflict and cooperation
Studied by Axelrod, 1985
Drawn from political science and game theory
Moves towards machine learning
Iterated Prisoners Dilemma
Prisoners Dilemma played repeatedly

Simple Genetic Algorithm
Begin
Initialize
population
Evaluate Solutions
T =0
Optimum
Solution?
T=T+1
N
Y
Selectio
n
Stop
Crossover
Mutation
19
Genetic Algorithms
,
November 10, 2015
Simple Genetic Algorithm
Simple_Genetic_Algorithm()
cfw_
Initialize the P

Simple Genetic Algorithm
Begin
Initialize
population
Evaluate Solutions
T =0
Optimum
Solution?
T=T+1
N
Y
Selectio
n
Stop
Crossover
Mutation
49
Genetic Algorithms
,
November 10, 2015
Traveling Salesman Problem (TSP)
We are given a set of cities and a symme

Faculty of informatics engineering
Genetic Algorithms
Dr. Husam ALUSTWANI
November 12
1
Genetic Algorithms
,
November 10, 2015
Course conventions
Slide color code
Green for examples
Blue for definitions
Red for important things
Orange for titles
Lecture c

Parallel Genetic Algorithms : PGA
GA : Powerful tool for optimization problems
Can succeed where other techniques fail
GAs require many calculations
We want to improve performance
Parallel Computing
How to parallelize GAs ?
At fitness level
At population

Fourier Transform
Lecture 6
Outlines
Homomorphic filtering
Basic idea:
f ( x, y ) i ( x, y ) r ( x, y )
Illumination
(low freq.)
reflectance
(high freq.)
ln f ( x, y ) ln i ( x, y ) ln r ( x, y )
freq. domain enhancement
H (u, v) (H L )[1 e
c ( D 2 ( u ,

Computer Vision & Robotic
Yosser ATASSI
Lecture1
2012-2013
Vision
`to know what is where, by looking.
Where?
What?
Vision is
Deceptive
Computationally demanding
Critical to many applications
Visual Fields

Morphological Image
Processing
Introduction
Morphology: a branch of biology that deals with
the form and structure of animals and plants
Morphological image processing is used to extract
image components for representation and
description of region shape,

Point Processing - Histogram
&
Local Operations
Lecture 3
2011-2012
Dr. Yosser ATASSI
Main ideas
Point Processing
Histogram
Local Operations
Convolution
smoothing
Point Processing of Images
* In a digital image, point = pixel.
Point processing transf

Local Processing Filter
Lecture 4
2010-2011
Image Noise and Gradients
Image Noise and Gradients
First and Second Derivations
Laplacian Operators
Gradient operator: first-order derivative
sensitive to abrupt change, but not slow change
2
2
f
f
2
second-or

Fourier Transform 1
Lecture 5
OUTLINES
The Two-Dimensional Fourier
Transform
Primary Uses of the FT in Image Processing:
Explains why down-sampling can add distortion to an image
and shows how to avoid it.
Useful for certain types of noise reduction, debl

Lab2
1
Lab2
Types of operations
The types of operations that can be applied to digital images
to transform an input image a[m,n] into an output image
b[m,n] can be classified into three categories
Arithmetic operations
Adding a constant will lighten

1
Lab5
eng.Heba
Lab5
Filtering: Frequency Domain
In theory any frequency domain filtering can be accomplished as convolution in
the spatial domain. If there exists a simple mask for the desired filter effect, it
may be computationally less expensive t

Introduction to Matlab (Code)
%
% Introduction to Matlab
%
%
% (1) Basics
% The symbol "%" is used to indicate a comment (for the remainder of
% the line).
% When writing a long Matlab statement that becomes to long for a
% single line use "." at the end

Lab3
1
Lab3
Spatial domain filtering
Previously, in histogram modification for example, we considered
enhancement techniques where the change at any point in the
image was calculated using only the gray level at that point and
the transformation func

1
Lab4
eng.Heba
Lab4
Digital Convolution
To convolve an image M with a spatial filter S:
o Place S over each pixel of M in turn
o Calculate the product of all corresponding grey values of M and
elements of S, and add the results
The result is calle