Intelligent Internet Search Technology Using a Novel Genetic Algorithm and a Service-Oriented Architecture
Naser El-Bathy, Clay Gloster, Ghassan M. Azar · American Journal of Intelligent Systems · 2013
Internet search technology, used to find informat ion, is only two decades old. However, it has become a cornerstone of the Internet economy. In 2012, the number of Internet users in the United States exceeded 245 million with the average user performing about 1,500 searches last year. Accordingly, the industry is wo rth more than $780 billion worldwide. Queries returned using current search technology can produce results containing conflicting info rmation, redundant and irrelevant data, and even data that arises erroneous. This is a result of search technologies that typically do not attempt to integrate results of a query. This research directly addresses these problems by introducing Intelligent Internet Search Technology using a Novel Genetic Algorith m and A Service-Oriented Architecture. The proposed research project defines three specific goals. First, develop ment of an Internet search technology system that presents an innovative solution that significantly reduces contradiction and irrelevancy of search results. The four (4) major co mponents of the system are: a search engine system, an informat ion ext raction sub-system, an informat ion retrieval sub-system, and genetic algorith m for data clustering. Second, development of a novel genetic algorithm (GA ) that optimizes document-query similarity. Th is algorith m eliminates irrelevant information and redundancy for data clustering as it improves search performance. Third, incorporation of the results of this study into undergraduate and graduate information technology (IT) degree programs.