2005 | OriginalPaper | Chapter
Distributed and Scalable Similarity Searching in Metric Spaces
Author : Michal Batko
Published in: Current Trends in Database Technology - EDBT 2004 Workshops
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
In this paper, we address the problem of scalable distributed similarity searching. Our work is based on single-site metric space indexing algorithms. They provide efficient way to perform range and nearest neighbor queries on arbitrary data in general metric spaces. The metric spaces are excellent abstraction that allows comparison of very complex objects (such as audio files, DNA sequences, texts). We have exploited the SDDS (Scalable and Distributed Data Structures) paradigms and P2P (Peer to Peer) systems to form a metric space similarity searching structure in distributed environment. Our proposed method is fully scalable without any centralized part and it allows performing similarity queries on stored data.