Title: Research on adaptive classification algorithm based on non-segment and classified-centre-vector

Authors: Kai Gao; Xiang Wang; Wei Wang

Addresses: School of Information Science and Engineering, Hebei University of Science and Technology, No. 70 Yuhua East Street, Shijiazhuang Hebei, 050000, China ' School of Information Science and Engineering, Hebei University of Science and Technology, No. 70 Yuhua East Street, Shijiazhuang Hebei, 050000, China ' School of Information Science and Engineering, Hebei University of Science and Technology, No. 70 Yuhua East Street, Shijiazhuang Hebei, 050000, China

Abstract: Classification is essential to many web applications such as focused crawling, search engine, recommendation, content filter, knowledge discovery, etc. Although traditional classification algorithms have many virtues, the unstructured and big web data application presents challenges to these traditional algorithms. Moreover, the traditional segmentation processing usually needs more time and a complete lexicon. This work focuses on an interesting and promising approach that may enhance the classification performance of web and big data applications. Based on the non-segment and the classified-centre-vector, the proposed algorithm can meet the request on big data classifications. By using positive and negative modification, it can revise the potential data bias. The experimental results and the analysis show the feasibility of this approach.

Keywords: adaptive classification; classified centre vector; non-segment; bias revising; web applications; big data classification.

DOI: 10.1504/IJIIDS.2013.057424

International Journal of Intelligent Information and Database Systems, 2013 Vol.7 No.6, pp.550 - 566

Received: 30 Jan 2013
Accepted: 26 Jul 2013

Published online: 31 Mar 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article