RankingFor Web Databases Using SVM and K-Means algorithm

Autor:	S. Jayanthi, P. Ayyadurai, M. E-Student
Rok vydání:	2012
Předmět:	Query expansion Web search query Database Data retrieval Web query classification Computer science Ranking SVM k-means clustering Data mining computer.software_genre Query language Cluster analysis computer
Zdroj:	IOSR Journal of Computer Engineering. 8:13-18
ISSN:	2278-0661 2278-8727
DOI:	10.9790/0661-0821318
Popis:	The Usage of internet in now a day is more and it became necessity for the people to do some applications such as searching web data bases in domains like Animation, vehicles, Movie, Real estates, etc. One of the problems in this context is ranking the results of a user query information. Earlier approaches problem have toused frequencies of database value regions, handling query logs, and user profiles information. A common thread in most of these approaches is that ranking is done in a usage page ranking manner. This paper simulates the usage of ranking query results based on user and query Dependent ranks by taking user and query similarities as input including the workload. K- Means algorithm used for cluster and re ranking process, multiple database system used for clustering the data. Among rank learning methods, ranking SVM has been favorably applied to various applications, e.g., optimizing search engine for web information, improving data retrieval quality. We define these similarities formally in discuss their effectiveness analytically and experimentally over four distinct web databases. General Terms -Clustering, Support vector machine, K-means algorithm, Web Databases.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d4e5564aa1e676c793cef01d5e2c53d8 https://doi.org/10.9790/0661-0821318 Zobrazit plný text záznamu