Research on Neural Network Based MultiAgent Semantic Web Content Mining

ABSTRACT As with the rapid increase of the huge amount of online information, there is a strong demand for Information retrieving from the web which helps to discover some useful knowledge from Web documents. Agents are often developed not in isolation but as part of a multi-agent system. Single agent is unable to retrieve the information from multiple searching tools. Single agent requires more time to retrieve information than multi-agent. Multi-agent neural network system is an effective solution to large scale Web mining. This work proposes Multi-agent neural network based framework for mining contents of semantic web, which would provide query relevant knowledge using STC (Suffix Tree Cluster) clustering technique. Clustering helps to provide user with query relevant cluster of web contents, which better satisfy user requirement and provides optimal utilization of web surfing time. It uses fuzzy neural network to classify the relevancy of search results on a multi-agents. The fuzzy neural network is used by us to enable multi-agent to match a query terms which create a clusters and return search result with high accuracy in a reasonably short time.