R-CHORD: A DISTRIBUTED SIMILARITY RETRIEVAL SYSTEM WITH RPCID

摘要：

In order to achieve the access of massive highdimensional data on P2P network efficiently, we present a distributed similarity retrieval system named R-Chord using modified iDistance based on Relative Position Code (RPCID). RPCID calculates the lower bound distance between the query point and the data point using Relative Position Code (RPC). RPC is a data object encoding method based on spatial location information. A RPC area can be discarded when the lower bound distance is greater than the pruning distance. Experimental results show that RPCID can achieve better time performance and resource consumption than iDistance.

关键词： Range search K-Nearest-Neighbor search Relative Position Code

作者: Wenke Yin Ming Zhu Lan Jiang

作者单位: Joint Laboratory of Network Communication System & Control Key Lab of Anhui, Hefei 230027, China Department of Automation, University of Science and Technology of China, Hefei 230027, China

会议类型: 国际会议

会议名称: 2009 IEEE International Conference on Network Infrastructure and Digital Content(2009年IEEE网络基础设施与数字内容国际会议 IEEE IC-NIDC2009)

会议地点: 北京

会议语种:英文

页码: 393-399

在线出版日期: 2009-11-06（万方平台首次上网日期，不代表论文的发表时间）