An efficient search model using k-means clustering analysis is proposed to improve the low efficiency of resource retrieval technology in peer-to-peer net with mass information. The metadata described by RDF framework is used to perform cluster analysis of resources and the search range of resources is narrowed from global to local so that the model can enhance the efficiency of resource retrieval effectively
a dynamic optimization technique is adopted to significantly improve the inquiry speed. Moreover
the use of the subnet division algorithm and the node backup algorithm enhances the scalability
safety and reliability of the model. Simulation results and comparisons with traditional retrieval models show that the proposed model is convenient and has higher resources searching efficiency in search delay and average path.
关键词
Keywords
references
EDITH C, SCOTT S. Replication strategies in unstructured peer-to-peer networks[C]∥Proceedings of the 2002 SIGCOMM Conference. New York, USA: ACM Press, 2002:177-190.
XIAO Bo, NIE Xiaowen, HOU Mengshu. Quantitative analysis and design of an estimating algorithm on DHT network size [J]. Journal of University of Electronic Science and Technology, 2011, 40(2):261-266.
QIU Dingxi. A comparative study of the k-means algorithm and the normal mixture model for clustering: bivariate homoscedastic case[J].Journal of Statistical Planning and Inference, 2010, 140(7):1701-1711.
TSAI C W, YANG C S, CHIANG M C. A time-efficient pattern reduction algorithm for k-means based clustering [C]∥IEEE International Conference on Systems, Man and Cybernetics. Piscataway, NJ, USA: IEEE, 2007:504-509.
BLOEHDORN S, CIMIANO P, HOTHO A. Learning ontologies to improve text clustering and classification[C]∥Proceedings of the 29th Annual Conference of the From Data and Information Analysis to Knowledge Engineering. Berlin, Germany: Springer, 2006:334-341.
ZHOU Bo, LIU Yiqun, ZHANG Min, et al. A document relevance based search result re-ranking[J]. Journal of Chinese Information Processing, 2010,24(3):19-36.