2010 | OriginalPaper | Chapter
Randomized Approaches for Nearest Neighbor Search in Metric Space When Computing the Pairwise Distance Is Extremely Expensive
Authors : Lusheng Wang, Yong Yang, Guohui Lin
Published in: Algorithmic Aspects in Information and Management
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
Finding the closest object for a query in a database is a classical problem in computer science. For some modern biological applications, computing the similarity between two objects might be very time consuming. For example, it takes a long time to compute the edit distance between two whole chromosomes and the alignment cost of two 3D protein structures. In this paper, we study the nearest neighbor search problem in metric space, where the pair-wise distance between two objects in the database is known and we want to minimize the number of distances computed on-line between the query and objects in the database in order to find the closest object. We have designed two randomized approaches for indexing metric space databases, where objects are purely described by their distances with each other. Analysis and experiments show that our approaches only need to compute
O
(log
n
) objects in order to find the closest object, where
n
is the total number of objects in the database.