7.Genalgo Application

7/30/2019 7.Genalgo Application

1/31

Part II: Applications of GAs

GA and the Internet

Genetic search based on multiple mutation approaches


2/31

GAs are useful and efficient when

The search sapace is large, complex or poorly

understood

Domain knowledge is scarce or expertknowledge is difficult to encode to narrow thesearch space

No mathematical analysis is available

Traditional search methods fail

For problem solving and for modeling


3/31

Applications

GAs are applied to many scientific, engineering problems ,In business and entertainment , including:

1. Optimization: It is used in wide variety of optimization tasks

including numerical optimization such as travelingSalesman Problem, Job Scheduling Problem, video andsound quality optimization.

2. Automatic Programming: It is used to evolve or generatecomputer program for specific task automatically

3. In machine and robot Learning

4. In Models of social systems

5. Interactions between evolution and learning


4/31

Some Applications of Gas

GAInternet search

Data mining

Software guided circuit designControl systems design

Stock prize prediction

Path finding Mobile robotssearch

Optimization

Trend spotting


5/31

Algorithms Phases

Process set of URLs given by user

Select all links from input set

Evaluate fitness function for all genomes

Perform crossover, mutation, and reproduction

Satisfactorysolution

obtained?

The End


6/31

Introduction

GA can be used for intelligent internet search.

GA is used in cases when search spaceis relatively large.

GA is adoptive search.

GA is heuristic search method.


7/31

System for GA Internet

Search Designed at faculty for electrical engineering, university of belgrade

CO

NTROL

PROGRAM

Agent Spider

Input set

Topic

Space

Time

Output set

Current set

Top data

Net data

Generator


8/31

Spider

Spider is software packages,that picks up internet documents

from user supplied input with depth specified by user.

Spider takes one URL, fetches all links,and documents thy contain with predefined depth.

The fetched documents are stored on local hard disk with samestructure as on the original location.

Spiders task is to produce the first generation.

Spider is used during crossover and mutation.


9/31

Agent

Agent takes as an input a set of urls,and calls spider, for every one of them, with depth 1.

Then, agent performs extraction of keywords

from each document, and stores it in local hard disk.


10/31

Generator

Generator generates a set of urls from given keywords,using some conventional search engine.

It takes as input the desired topic, calls yahoo search engine,and submits a query looking for all documentscovering the specific topic.

Generator stores URL and topic of given web pagein database called topdata.


11/31

Topic

It uses topdata DB inorder to insert random urlsfrom database into current set.

Topic performs mutation.


12/31

Space

Space takes as input the current setfrom the agent applicationand injects into it those urlsfrom the database netdata

that appeared with the greatest frequencyin the output set of previous searches.


13/31

Time

Time takes set of urls from agentand inserts ones with greatest frequency into DB netdata.

The netdata DB contains of three fields: URL, topic,and count number.

The DB is updated in each algorithm iteration.


14/31

How Does The System Work?

CONTROL

PR

OGRAM

Agent Spider

Input set

Topic

Space

Time

Output set

Current set

Top data

Net data

Generator

command flow

data flow


15/31

GA and the Internet: Conclusion

GA for internet search, on contrary to other gas,is much faster and more efficient that conventional solutions,such as standard internet search engines.

INTERNET


16/31

Genetic Search Based on

Multiple Mutation Approaches

Concept and its improvements adapted to specificapplications in e-business, and concrete software package

Main problems in finding information on the Internet:

How to find quickly and retrieve efficiently the potentially usefulinformation considering the fact of the fast growth of the quantityand variety of Internet sites

Huge number of documents , many of which are completelyunrelated to what the user originally attempted to find, searchedwith indexing engines

Documents placed on the top of the result list are often lessacceptable then the lower ones

Indexing process may take days, weeks , or even longer, becausethe volume of new information being created daily


17/31

Links Based Approach

The question is:

How to locate and retrieve the needed information before it gets indexed?

The efficient way to locate the new not-yet-indexed information:

Using links-based approaches genetic search

simulated annealing

Best result:

indexing - based approaches

+

links - based approaches


18/31

Genetic Search Algorithm

GENETIC ALGORITHM OF ZERO ORDER, with no mutation

Start:

Model Web presentation that contains all the needed types of

information (fitness function is evaluated).

It is assumes that it includes URL pointers to other similar Webpresentations, and these are downloaded.

The Web presentations that survived the fitness function areassumed to include additional URL pointers, and their related Webpresentations are downloaded next.

After the end-of-search condition is met, the Web presentations areranked according to their fitness value.


19/31

Genetic Search Algorithm

Type of mutation:

Topic-oriented database mutation

Semantic mutations

- based on the principles of spatial locality

- based on the principles of temporal locality

Logical reasoning and semantics consideration is involve inpicking out URLs for mutation.


20/31

Innovations Required by Domain Area

APPLICATION LEVEL

LEVEL OF THE GENERAL PROJECT APPROACHAND PRODUCT ARCHITECTURE

ALGORITHMIC LEVEL

IMPLEMENTATION LEVEL


21/31

Application Level

Statistical analysis and data mining has to be performed,

in order to figure out the common and typical patterns ofbehavior and need

The state-of-the-art of mutual referencing has to be determined

The trends and asymptotic situations foreseen for the time ofproject finalization has to be determined


22/31

Level of the General Project

Approach and Product ArchitectureDecisions have to be made about the most important goals to beachieved:

Maximizing the speed of search

Maximizing the sophistication of search

Maximizing specific effects of interest for a given institution or acustomer

Maximizing a combination of the above

Decision on this level affect the applicability of the final product /tool.


23/31

Algorithmic Level

Develop an efficient mutation algorithm of interest for the application

in the direction of database architecture and design

in introducing the elements of semantic-based mutation

Semantics-based mutations are especially of interest for chaoticmarkets, typical of new markets in developed countries ortraditional markets in under-developed countries.


24/31

Semantics-based Mutation

Mutation based on spatial localities

After a fruitful Web presentation is reached (using a tradicional

algorithm with mutation), the site of the same Internet service provideris searched for other presentations on the same or similar topic

Explanation :

In chaotic markets, it is very unlikely that service/product offers fromthe same small geographic area each other on their Web presentations

After a successful side trip based on spatial mutation, one continue

with the traditional database mutation.


25/31

Semantics-based Mutation

Mutation based on temporal localities

One comes back periodically to a Web presentation which wasfruitful in the past

One comes back periodically to other Web presentationsdeveloped by the author who created some fruitful Web

presentations in the past

Temporal mutation can use direct revisits or a number of indirectforms or revisit.


26/31

Implementation Level

Utilization of novel technologies, for maximal performance andminimal implementation complexity

Important for:

- good flexibility

- extendibility

- reliability

- availability

Utilization of mobile platforms and mobile agents


27/31

Implementation Level

Static agents

- one has to download megabytes of information

- treat that information with a decision-making code of sizemeasured in kilobytes

- derive the final business related decision, which is binary in size(one bit: yes or no)

A huge amount of data is transferred through the network invain, because only a small percent of fetched documents will turnout to be useful

Mobile agents

- they would browse through the network and perform the searchlocally, on the remote servers, transferring only the neededdocuments and data

- they load the network only with kilobytes and a single bit


28/31

Simulation Result

Links-based approach in the static domain

How various mutation strategies can affect the search efficiency

Set of software packages have developed , that would performInternet search using genetic algorithms (by Veljko Milutinovic,Dragana Cvetkovic, and Jelena Mirkovic)

As the fitness function they have measured average Jaccards

score for the output documents, while changing the type and rateof mutation


29/31

Simulation Result

The simulation result for topicmutation

The simulation result fortemporal and spatial mutationcombined with topic mutation


30/31

Simulation Result

The simulation result for topic,spatial and temporal mutationcombined.

Constant increase in the qualityof pages found.


31/31

Conclusion: Evolution

Tutorial download: galeb.etf.bg.ac.yu/~vm Option:Tutorials

Date post:	04-Apr-2018
Category:	Documents
Upload:	srikar-chintala
View:	213 times
Download:	0 times