Feature Selection for Network Intrusion Detection System Using Mutual Correlation

Abstract

A large and growing number of web pages display contextual knowledge based on keywords automatically extracted from the text of the page and this is a substantial source of revenue supporting the web today. In addition, geography keywords are also useful to the research of the information retrieval, text clustering and topic research. Manually indexing keywords will highly cost. Thus, automatically indexing keyword from text is of great interests. Web search users (physical geographers, spatial analyzers, student and teachers) extract the desirable information over the World Wide Web by browsing web directories. This system proposes a topic detection method that exploits the topical information of the geography terms for improving the performance of automatic extraction processing. Thus, this method applies the searching for the suitable resource of geography conditions. Moreover, this system checks to confirm the Geographical web page based on defined geography keywords.