الفهرس 
INTRODUCTIONOnly 14 pages are availabe for public view
 |  | from | 107 |  |  |
| | | from | 107 | | |
Abstract
With the rapid development of the Internet, the process of finding useful information rapidly has become more important. Search engines somewhat satisfy user’s search needs. However, they do not consider user’s interest or background. Thus lead to retrieving a lot of irrelevant web pages to the user query. The usefulness of a search engine depends on the relevance of the result set it gives back. While there may be millions of web pages that include a particular word or phrase, some pages may be more relevant, popular, or authoritative than others. Most of search engines use methods to rank the results of web pages to provide the most relevant results. It varies from search engine to another: how a search engine decides which pages are the best matches, and which order of these web pages are displayed to the user. These methods also change over time as Internet usage changes and new techniques evolve. In this thesis, the artificial intelligence (AI) techniques in optimization are proposed improving the returned results of search engine. They can be able to optimize and return the results that user is most interested. Page clustering is proposed to group all similar pages together into groups then genetic algorithm is applied to pick up the most relevant pages from each group. A short final list of the best pages is displayed to the user; so that the required information could be found easily and quickly. In addition; query recommendation approach is applied to help the user in typing the search query. The query recommendation algorithm suggests a list of previous related queries to the query submitted by the user. The problem of retrieving relevant web pages is not because of the search engines methodologies, but it strongly depends on the query. The more accurate search queries the user use, the more relative results will be obtained. Finally the proposed methods for optimizing search results have been implemented and the experimental results have been analyzed to evaluate the performance of these methods.