Incorporating agent based neural network model for adaptive meta-search

  • Authors:

  • Ying Xie;Dheerendranath Mundluru;Vijay V. Raghavan

  • Affiliations:

  • University of Louisiana at Lafayette, Lafayette, LA;University of Louisiana at Lafayette, Lafayette, LA;University of Louisiana at Lafayette, Lafayette, LA

  • Venue:
  • Proceedings of the 43rd annual Southeast regional conference - Volume 1
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the current information age, the web is increasing at a very rapid pace, while the indexes of the current Search Engines are not scaling up at the same pace resulting in the loss of access to a good fraction of documents on the web. An intriguing alternative is a Meta-Search Engine, which provides a unified access to several Search Engines thereby increasing the coverage of the web. Though using Meta-Search Engines, the coverage of the web is increased, maintaining a good precision can be a problem especially if one or more of the Search Engine's returns irrelevant documents for certain user queries. This paper proposes a novel, intelligent, and adaptive approach to improve the precision of the meta-search results. This approach uses an adaptive agent based neural network model to improve the quality of the search results by incorporating user relevance feedback in to the system.