matlab遗传算法工具箱.rar资源-CSDN文库

共63个文件

m：59个

readme：1个

ps：1个

版权申诉

matlab

198 浏览量 2023-06-06 16:59:51 上传评论收藏 283KB RAR 举报

资源推荐

资源详情

资源评论

收起资源包目录

matlab遗传算法工具箱.rar （63个子文件）

遗传算法工具箱

normGeomSelect.m 2KB

boundaryMutation.m 2KB

nonUnifMutation.m 2KB

calcbits.m 1KB

inversionMutation.m 2KB

gademo2.m 3KB

binaryMutation.m 1KB

enhancederXover.m 2KB

README 1KB

shiftMutation.m 2KB

gaZBGradEval.m 684B

tspEval.m 157B

遗传算法及其MATLAB实现.doc 1.34MB

EER.m 2KB

f2b.m 1KB

simpleXover.m 2KB

initializega.m 1KB

gaDemo1Eval1 (3).m 46B

coranaFeval.m 2KB

b2f.m 1KB

startup.m 50B

delta.m 1KB

linerorderXover.m 2KB

Untitled.m 312B

tournSelect.m 2KB

gademo1eval1.m 1KB

main.m 3KB

modifycircle.m 448B

adjswapMutation.m 1KB

binaryExample.m 2KB

singleptXover.m 2KB

parse.m 1KB

initializeoga.m 2KB

gaotv5.ps 130KB

uniformXover.m 2KB

threeswapMutation.m 1KB

ga.m 11KB

coranaMin.m 1KB

cyclicXover.m 2KB

partmapXover.m 2KB

erXover.m 2KB

orderBasedExample.m 3KB

heuristicXover.m 2KB

orderbasedXover.m 2KB

plotCorana.m 514B

arithXover.m 1KB

multiNonUnifMutation.m 2KB

maxGenTerm.m 1KB

unifMutation.m 2KB

floatGradExample.m 2KB

gaMichEval.m 193B

coranaEval.m 1KB

gaZBGrad.m 174B

gaotv5.pdf 184KB

gademo.m 4KB

gademo3.m 6KB

floatExample.m 2KB

gademo1.m 4KB

roulette.m 861B

dists.m 7KB

swapMutation.m 2KB

optMaxGenTerm.m 2KB

Contents.m 5KB

A Genetic Algorithm forFunction Optimization: A

Matlab Implementation

Christopher R. Houck

North Carolina State University

and

Jeery A. Joines

North Carolina State University

and

Michael G. Kay

North Carolina State University

A genetic algorithm implemented in Matlab is presented. Matlab is used for the following reasons:

it provides many built in auxiliary functions useful for function optimization it is completely

portable and it is ecient for numerical computations. The genetic algorithm toolb oxdevelop ed

is tested on a series of non-linear, multi-modal, non-convex test problems and compared with

results using simulated annealing. The genetic algorithm using a oat representation is found to

be sup erior to b oth a binary genetic algorithm and simulated annealing in terms of eciency and

quality of solution. The use of genetic algorithm to olboxaswell as the code is introduced in the

paper.

Categories and Subject Descriptors: G.1 

Numerical Analysis

]: Optimization|

Unconstrained

Optimization, nonlinear programming, gradient methods

General Terms: Optimization, Algorithms

Additional Key Words and Phrases: genetic algorithms, multimodal nonconvex functions, Matlab

1. INTRODUCTION

Algorithms for function optimization are generally limited to convex regular func-

tions. However, many functions are multi-modal, discontinuous, and nondieren-

Name: Christopher R. Houck

Address: North Carolina State University,Box 7906, Raleigh, NC, 27695-7906,USA,(919) 515-

5188,(919) 515-1543,chouck@eos.ncsu.edu

Aliation: North Carolina State University

Name: Jeery A. Joines

Address: North Carolina State University,Box 7906, Raleigh, NC, 27695-7906,USA,(919) 515-

5188,(919) 515-1543,jjoine@eos.ncsu.edu

Aliation: North Carolina State University

Name: Michael G. Kay

Address: North Carolina State University,Box 7906, Raleigh, NC, 27695-7906,USA,(919) 515-

2008,(919) 515-1543,kay@eos.ncsu.edu

Aliation: North Carolina State University

Sponsor: This researchwas funded in part by the National Science Foundation under grantnum-

ber DMI-9322834.



C. Houck et al.

tiable. Sto chastic sampling methods have been used to optimize these functions.

Whereas traditional searchtechniques use characteristics of the problem to deter-

mine the next sampling point (e.g., gradients, Hessians, linearity, and continuity),

stochastic search techniques makeno such assumptions. Instead, the next sampled

point(s) is(are) determined based on stochastic sampling/decision rules rather than

a set of deterministic decision rules.

Genetic algorithms have been used to solve dicult problems with objective

functions that do not possess \nice" prop erties suchascontinuity, dierentiability,

satisfaction of the Lipschitz Condition, etc.Davis 1991 Goldberg 1989 Holland

1975 Michalewicz 1994]. These algorithms maintain and manipulate a family,or

population, of solutions and implement a \survival of the ttest" strategy in their

search for b etter solutions. This provides an implicit as well as explicit parallelism

that allows for the exploitation of several promising areas of the solution space at

the same time. The implicit parallelism is due to the schema theory developed by

Holland, while the explicit parallelism arises from the manipulation of a population

of points|the evaluation of the tness of these points is easy to accomplish in

parallel.

Section 2 presents the basic genetic algorithm, and in Section 3 the GA is tested

on several multi-modal functions and shown to be an ecient optimization to ol.

Finally, Section 4 briey describ es the co de and presents the list of parameters of

the Matlab implementation.

2. GENETIC ALGORITHMS

Genetic algorithms search the solution space of a function through the use of sim-

ulated evolution, i.e., the survival of the ttest strategy. In general, the ttest

individuals of any p opulation tend to repro duce and survive to the next genera-

tion, thus improving successive generations. Howev

er, inferior individuals can, by

chance, survive and also repro duce. Genetic algorithms have been shown to solve

linear and nonlinear problems by exploring all regions of the state space and ex-

ponentially exploiting promising areas through mutation, crossover, and selection

operations applied to individuals in the p opulation Michalewicz 1994]. A more

complete discussion of genetic algorithms, including extensions and related topics,

can be found in the bo oks byDavis Davis 1991], Goldb erg Goldberg 1989], Hol-

landHolland 1975], and Michalewicz Michalewicz 1994]. A genetic algorithm (GA)

is summarized in Fig. 1, and each of the ma jor components is discussed in detail

below.

(1) Supply a population

individuals and resp ective function values.

(2)



(3)



selection

f unction

(

;

(4)



repr oduction f unction

(

)

(5)

evaluate

(

)

(6)



(7) Repeat step 3 until termination

(8) Print out b est solution found

Fig. 1. A Simple Genetic Algorithm

AGAfor function optimization



The use of a genetic algorithm requires the determination of six fundamental

issues: chromosome representation, selection function, the genetic operators making

up the reproduction function, the creation of the initial population, termination

criteria, and the evaluation function. The rest of this section describ es eachof

these issues.

2.1 Solution Representation

For any GA, a chromosome representation is needed to describe each individual in

the population of interest. The representation scheme determines how the problem

is structured in the GA and also determines the genetic op erators that are used.

Each individual or chromosome is made up of a sequence of genes from a certain

alphabet. An alphab et could consist of binary digits (0 and 1), oating p ointnum-

bers, integers, symbols (i.e., A, B, C, D), matrices, etc. In Holland's original design,

the alphabet was limited to binary digits. Since then, problem representation has

been the sub ject of muchinvestigation. It has b een shown that more natural repre-

sentations are more ecient and produce better solutionsMichalewicz 1994]. One

useful representation of an individual or chromosome for function optimization in-

volves genes or variables from an alphab et of oating p ointnumbers with values

within the variables upp er and lower b ounds. MichalewiczMichalewicz 1994] has

done extensive exp erimentation comparing real-valued and binary GAs and shows

that the real-valued GA is an order of magnitude more ecient in terms of CPU

time. He also shows that a real-valued representation moves the problem closer

to the problem representation which oers higher precision with more consistent

results across replications. Michalewicz 1994]

2.2 Selection Function

The selection of individuals to pro duce successive generations plays an extremely

important role in a genetic algorithm. A probabilistic selection is performed based

upon the individual's tness such that the better individuals have an increased

chance of being selected.

An individual in the population can be selected more

than once with all individuals in the population having a chance of being selected

to repro duce into the next generation. There are several schemes for the selection

process: roulette wheel selection and its extensions, scaling techniques, tournament,

elitist mo dels, and ranking methods Goldb erg 1989 Michalewicz 1994].

A common selection approach assigns a probability of selection,

,toeach indi-

vidual,

based on its tness value. A series of

random numbers is generated and

compared against the cumulative probability,

, of the population.

The appropriate individual,

, is selected and copied into the new population if

;





.Various methods exist to assign probabilities to individuals:

roulette wheel, linear ranking and geometric ranking.

Roulette wheel, developed by Holland Holland 1975], was the rst selection

method. The probability,

, for each individual is dened by:

 Individual

is chosen ] =

P opS ize



(1)

where

equals the tness of individual

. The use of roulette wheel selection limits



C. Houck et al.

the genetic algorithm to maximization since the evaluation function must map the

solutions to a fully ordered set of values on

. Extensions, such as windowing and

scaling, have b een proposed to allow for minimization and negativity.

Ranking methods only require the evaluation function to map the solutions to

a partially ordered set, thus allowing for minimization and negativity. Ranking

methods assign

based on the rank of solution

when all solutions are sorted.

Normalized geometric ranking, Joines and Houck 1994], denes

for each indi-

vidual by:

 Selecting the

th individual ] =

;

)

;

 (2)

where:

= the probability of selecting the best individual



= the rank of the individual, where 1 is the best

= the population size

;

)

Tournament selection, like ranking metho ds, only requires the evaluation function

to map solutions to a partially ordered set, however, it do es not assign probabilities.

Tournament selection works by selecting

individuals randomly, with replacement,

from the p opulation, and inserts the best of the

into the new population. This

procedure is rep eated until

individuals have been selected.

2.3 Genetic Operators

Genetic Operators provide the basic searchmechanism of the GA. The operators are

used to create new solutions based on existing solutions in the p opulation. There

are two basic types of operators: crossover and mutation. Crossover takes two

individuals and produces two new individuals while mutation alters one individual

to produce a single new solution. The application of these two basic types of

operators and their derivatives dep ends on the chromosome representation used.

Let



and



be two

-dimensional rowvectors denoting individuals (parents)

from the population. For



and



binary, the following op erators are dened:

binary mutation and simple crossover.

Binary mutation ips eachbitinevery individual in the p opulation with proba-

bility

according to equation 3.



;



otherwise

(3)

Simple crossover generates a random number

from a uniform distribution from

1to

and creates two new individuals (



and



) according to equations 4 and 5.





i<r



otherwise

(4)





i<r



otherwise

(5)

Operators for real-valued representations, i.e., an alphabet of oats, were de-

veloped by Michalewicz Michalewicz 1994]. For real



and



, the following op-

AGAfor function optimization



erators are dened: uniform mutation, non-uniform mutation, multi-non-uniform

mutation, boundary mutation, simple crossover, arithmetic crossover, and heuris-

tic crossover. Let

and

be the lower and upper b ound, respectively, for each

variable

Uniform mutation randomly selects one variable,

, and sets it equal to an uniform

random number

(

b



(

b

)



otherwise

(6)

Boundary mutation randomly selects one variable,

, and sets it equal to either

its lower or upper b ound, where



1):



j r <



j r





otherwise

(7)

Non-uniform mutation randomly selects one variable,

, and sets it equal to an

non-uniform random number:

;

)

(

)if

;

(

)

(

)if





otherwise

(8)

where

(

)=(

;

max

))



(9)

r

= a uniform random number between (0,1),

= the current generation,

max

= the maximum number of generations,

= a shape parameter.

The multi-non-uniform mutation op erator applies the non-uniform operator to

all of the variables in the parent



Real-valued simple crossover is identical to the binary version presented above

in equations 4 and 5. Arithmetic crossover produces two complimentary linear

combinations of the parents, where



1):



+ (1

;

)



(10)



=(1

;

)



(11)

Heuristic crossover pro duces an linear extrap olation of the two individuals. This

is the only operator that utilizes tness information. A new individual,



,is

created using equation 12, where



1) and



is b etter than



in terms of

tness. If



is infeasible, i.e.,

f easibility

equals 0 as given by equation 14, then

generate a new random number

and create a new solution using equation 12,

otherwise stop. To ensure halting, after

failures, let the children equal the parents

and stop.

评论收藏

内容反馈

版权申诉

Matlab科研辅导帮

粉丝: 2w+
资源: 7757

matlab遗传算法工具箱.rar

遗传算法的MATLAB代码遗传算法工具箱-matlab遗传算法工具箱.rar

MATLAB工具箱-Sheffield大学Matlab遗传算法工具箱.rar

Sheffield--Matlab遗传算法工具箱.rar

MATLAB工具箱-遗传算法工具箱.rar

Matlab遗传算法工具箱.rar_遗传 工具箱_遗传 matlab_遗传算法matlab_遗传算法实例_遗传算法工具

关于雷英杰编著《Matlab遗传算法工具箱及应用》 中的工具箱遗传算法工具箱.rar

chapter1 谢菲尔德大学的matlab遗传算法工具箱.rar_LKC_遗传算法

matlab智能算法——chapter1 谢菲尔德大学的matlab遗传算法工具箱.rar

MATLAB遗传算法工具箱与应用雷英杰清晰版-复件 MATLAB遗传算法工具箱与应用[雷英杰].part01.rar

遗传算法的MATLAB代码遗传算法工具箱-一些用matlab编写的经典遗传算法算例.rar

Matlab遗传算法工具箱以及应用源码-Matlab遗传算法工具箱及应用》源码.rar

遗传算法工具箱.rar_matlab 遗传算法工具箱_mostlygu3

MATLAB遗传算法工具箱及应用教材-MATLAB遗传算法工具箱及应用.part2.rar

MATLAB遗传算法工具箱及应用 雷英杰编 2005年.rar

MATLAB遗传算法工具箱与应用雷英杰清晰版-MATLAB遗传算法工具箱与应用[雷英杰].part34.rar

Matlab遗传算法工具箱.zip

MATLAB遗传算法工具箱及应用教材-MATLAB遗传算法工具箱及应用.part7.rar

【MATLAB工具箱集锦】-遗传算法工具箱.rar

MATLAB遗传算法工具箱及应用教材-MATLAB遗传算法工具箱及应用.part6.rar

MATLAB遗传算法工具箱与应用雷英杰清晰版-MATLAB遗传算法工具箱与应用[雷英杰].part23.rar

MATLAB遗传算法工具箱与应用雷英杰清晰版-MATLAB遗传算法工具箱与应用[雷英杰].part24.rar

MATLAB遗传算法工具箱与应用雷英杰清晰版-MATLAB遗传算法工具箱与应用[雷英杰].part17.rar

遗传算法的MATLAB代码遗传算法工具箱-遗传算法的MATLAB代码常用代码.rar

《Matlab遗传算法工具箱及应用》源码.rar

遗传算法工具箱.rar

MATLAB遗传算法 数学建模算法 灰色算法 蒙特卡洛神经网络图论算法资料集合.zip

MATLAB遗传算法工具箱与应用雷英杰清晰版-MATLAB遗传算法工具箱与应用[雷英杰].part20.rar

MATLAB遗传算法工具箱及应用

2022年精选数学建模算法教程文档合集第16期：遗传算法（100份）.zip

最新资源

Matlab遗传算法工具箱.rar_遗传工具箱_遗传 matlab_遗传算法matlab_遗传算法实例_遗传算法工具

关于雷英杰编著《Matlab遗传算法工具箱及应用》中的工具箱遗传算法工具箱.rar

MATLAB遗传算法工具箱及应用雷英杰编 2005年.rar

MATLAB遗传算法数学建模算法灰色算法蒙特卡洛神经网络图论算法资料集合.zip