A genetic search strategy based on simulated annealing for web mining

被引：0

作者：

Chen, Hao ^{[1
,2
]}

Bian, Naizheng ^{[2
]}

Zou, Beiji ^{[2
,3
]}

AhHwweYU ^{[4
]}

机构：

[1] Software School, Hunan University, Changsha 410082, China

[2] School of Information Science and Engineering, Central South University, Changsha 410083, China

[3] Dept. of Computer Science and Technology, Huaihua College, Huaihua 418008, China

[4] Nanyang Technological University, 2A-13 Nanyang Avenue, Singapore 639798, Singapore

来源：

Journal of Computational Information Systems | 2008年 / 4卷 / 06期

关键词：

Simulated annealing - Data mining - Search engines - Websites;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

As the web continues to increase in size, the relative coverage of web search engine is decreasing, and search tools that combine the results of multiple search engines are becoming more valuable. We present a genetic search strategy for a search engine by showing that important relation existed between web statistical studies, search engines and optimization techniques. The user query is used to mathematically define a fitness function of Web pages. The simulated annealing genetic algorithm evolves a population of pages and aims at maximizing this fitness function. We define a creation operator which uses the results given by standard search engine. The crossover and mutation operator consist in exploring links. Experimental results have shown that our method leads to pages of qualities that are significantly better than those of the standard search engines. © 2008 Binary Information Press.

引用

页码：2641 / 2650