On member search engine selection using artificial neural network in meta search engine

Meta search engine is an effective tool for searching information online. In comparison with independent search engine like Google, Bing, and etc., meta search engine has a wider coverage and can meet the requirement of information retrieval in a better manner. In particular, when a query is received from the user, the meta search engine sends it to some proper candidate member engines, collects results from them, and then replies to the user. An important issue here is how to better select the underlying member search engines. In this paper, we focus on the engine selection in meta search engine. We propose a selection design based on the combination of weighted round robin algorithm and artificial neural network. The experimental results show that our design can indeed improve the relevancy between the query and member search engine, and thus the effectivity of member selection.