Presentation is loading. Please wait.

Presentation is loading. Please wait.

EVOLUTIONARY SYSTEMS AND GENETIC ALGORITHMS NAME: AKSHITKUMAR PATEL STUDENT ID: 0577498 GRAD POSITION PAPER.

Similar presentations


Presentation on theme: "EVOLUTIONARY SYSTEMS AND GENETIC ALGORITHMS NAME: AKSHITKUMAR PATEL STUDENT ID: 0577498 GRAD POSITION PAPER."— Presentation transcript:

1 EVOLUTIONARY SYSTEMS AND GENETIC ALGORITHMS NAME: AKSHITKUMAR PATEL STUDENT ID: 0577498 GRAD POSITION PAPER

2 OUTLINE  Introduction  Evolutionary System  Genetic Algorithm  Crossover techniques  Applications  Conclusion  References

3 INTRODUCTION  Evolutionary system uses iterative progress, such as growth or development in a population.  This population is use random search using parallel processing to accomplish the desired end.  Genetic Algorithms have the advantage of finding novel solutions or variations for a specific situation without the programmer having to explicitly provide an analytic solution.

4 EVOLUTIONARY SYSTEM  An Evolutionary System depend on computational models of natural selection and genetics.  It encouraged by biological evolution such as, reproduction, mutation, recombination, and survival of the fitness.  Population based EAs, i.e., they process a whole collection of candidate solutions concurrently,  EAs mostly use recombination to mix information of more candidate solution into a new one,

5 FLOW CHART OF EVOLUTIONARY ALGORITHM

6 INITIALIZATION  Initialization is usually random or sometimes used, it is particularly used in complex or high-dimensional search spaces.  It noticed experimentally that initialization has a big influence on variance of the results and speed of convergence.

7 POPULATION  The population is use to hold possible solution.  It is a multi-set of genotypes.  In some EAs a population has an additional spatial structure, with a distance measure or a neighborhood relation.  Almost every EA applications have the population size is constant, it is not changing during the evolutionary search.  one genotype mention only one phenotype and fitness value.

8 PARENT SELECTION  It classify among individuals based on their quality, in particular, to allow the better discrete to become parents of the next generation.  High quality individuals access a higher chance to become parents than those with low quality.  Low quality individuals are often given a small, but positive chance, otherwise the whole search could become too greedy and get stuck in a local optimum.

9 MUTATION  That operator which applies to one object as input.  It is applied to one genotype and delivers a modified mutant, the child or offspring of it.  In Genetic Algorithms the mutation work as a background operator to fill the gene while in Evolutionary Programming it is the one and only variation operator doing the whole search work.

10 RECOMBINATION  A binary variation operator which applies to two objects as input is called Recombination.  It is used to merges information from two parent genotypes into one or two offspring genotypes.  Recombination operators are easy to implement with mathematically functions, but have no biological equivalent.  Evolutionary Algorithms create a number of offspring by random recombination, accept that some will have undesirable combinations of traits, most may be no better or worse than their parents, and hope that some have improved characteristics.

11 SURVIVOR SELECTION (REPLACEMENT)  It classify as individuals based on their quality.  It is similar to parent selection, but it is used in a different stage of the evolutionary cycle.

12 TERMINATION  Stopping the evolution process at the right moment is crucial from a practical viewpoint; but if little or no information is available about the value of the searched optimum, it is difficult to know when to stop.  A good control of the stopping criterion obviously influences the efficiency of the algorithm, and is as important as a good setting of evolution parameters.

13 GENETIC ALGORITHMS  Genetic Algorithms referred to a generation and it is execute according to the problem.  Genetic Algorithms are executed by using arrays of bits or characters that represent the chromosomes.  [Start] Generate random population of n chromosomes (suitable solutions for the problem)  [Fitness] Evaluate the fitness f(x) of each chromosome x in the population  [New population] Create a new population by repeating following steps until the new population is complete  [Selection] Select two parent chromosomes from a population according to their fitness (the better fitness, the bigger chance to be selected)  [Crossover] With a crossover probability cross over the parents to form a new offspring (children). If no crossover was performed, offspring is an exact copy of parents.  [Mutation] With a mutation probability mutate new offspring at each locus (position in chromosome).  [Accepting] Place new offspring in a new population  [Replace] Use new generated population for a further run of algorithm  [Test] If the end condition is satisfied, stop, and return the best solution in current population  [Loop] Go to step 2

14 CHROMOSOMES  Solution to the problem to be solved and this is represented by a list of parameters it is called chromosome.  It is typically represented as simple strings of data and instructions, it also used to wide variety of other data structures for storing chromosomes.  Every artificial chromosome consists of a number of “genes”, and each gene is classified as being on or off (0 or 1, respectively).

15 TRAVELLING SALESMAN PROBLEM  There are cities and given distances between them. Travelling salesman has to visit all of them, but he does not to travel very much. Task is to find a sequence of cities to minimize travelled distance.  Here I define cities 1 2 3 4 5 6 and its shortest path is 6 1 5 2 4 3. 1 6 5 3 4 2

16 CROSSOVER TECHNIQUES  Single-point crossover: one crossover point is selected, binary string from beginning of chromosome to the crossover point is copied from one parent, the rest is copied from the second parent.  Two-point crossover: two crossover point are selected, binary string from beginning of chromosome to the first crossover point is copied from one parent, the part from the first to the second crossover point is copied from the second parent and the rest is copied from the first parent.  Uniform crossover: bits are randomly copied from the first or from the second parent.

17 APPLICATIONS  Evolutionary Computing methods GA and ES have applied to solve wide range of engineering problems, such as manufacturing scheduling, image processing, robotics, power electronics, VLSI design, CAD design, chemistry, signal processing and physics.  Application of ES:  Image processing and Computer Vision system  Task scheduling  Mobile manipulator path planning  Car automation  Application of GA:  Job-Shop Scheduling problem  Real-time system task managements  Robot Path planning with give map  Image Processing  Sensor-based Robot Path Planning

18 CONCLUSION  the methods of ES and GA are similar, and they have different techniques for implementation.  For example, in ES we can use real vector data for our population for example, we use initialization, parent selection, mutation, replacement, and recombination;  However, in GA we need to encode and decode our population (solution candidate) for example we use crossover technique and mutation.  Finally, both methods are applied to a variety of engineering problems from chemistry to robotics.

19 REFERENCES  http://www.obitko.com/tutorials/genetic-algorithms/tsp-example.php http://www.obitko.com/tutorials/genetic-algorithms/tsp-example.php  http://www.obitko.com/tutorials/genetic-algorithms/crossover-mutation.php  A.E. Eiben. Evolutionary computing: the most powerful problem solver in the universe. Dutch Mathematical Archive, 5/3(2):126-131, 2002. A gentle introduction to evolutionary computing with details over GAs and ES.  http://www.liacs.nl/~emmerich/dinati00ga-es.pdfhttp://www.liacs.nl/~emmerich/dinati00ga-es.pdf  http://www.4c.ucc.ie/~aholland/udg/Girona_Lec8.pdf http://www.4c.ucc.ie/~aholland/udg/Girona_Lec8.pdf  http://www.softcomputing.net/gpsystems.pdf http://www.softcomputing.net/gpsystems.pdf  Vose, M. D., and Liepins, G. E. “Punctuated equilibria in genetic search”. Complex Systems. 5:31-44, 1991.  Whitley, D., “A Genetic Algorithm Tutorial”, Computer Science Department, Colorado State University, whiteky@cs.colostate.edu whiteky@cs.colostate.edu  http://www.academia.edu/500843/Genetic_and_Evolutionary_Computation_for_Image_Processing_and_Analysis. http://www.academia.edu/500843/Genetic_and_Evolutionary_Computation_for_Image_Processing_and_Analysis

20 THANK YOU


Download ppt "EVOLUTIONARY SYSTEMS AND GENETIC ALGORITHMS NAME: AKSHITKUMAR PATEL STUDENT ID: 0577498 GRAD POSITION PAPER."

Similar presentations


Ads by Google