DMCA
Quantile-Based KNN Over Multi-Valued Objects
Cached
Download Links
| Citations: | 9 - 5 self |
BibTeX
@MISC{Zhang_quantile-basedknn,
author = {Wenjie Zhang and Xuemin Lin and Muhammad Aamir Cheema and Ying Zhang and Wei Wang and Query Player A Player B},
title = {Quantile-Based KNN Over Multi-Valued Objects},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract — K Nearest Neighbor search has many applications including data mining, multi-media, image processing, and monitoring moving objects. In this paper, we study the problem of KNN over multi-valued objects. We aim to provide effective and efficient techniques to identify KNN sensitive to relative distributions of objects. We propose to use quantiles to summarize relative-distribution-sensitive K nearest neighbors. Given a query Q and a quantile φ ∈ (0, 1], we firstly study the problem of efficiently computing K nearest objects based on a φ-quantile distance (e.g. median distance) from each object to Q. The second problem is to retrieve the K nearest objects to Q basedonoverall distances in the “best population ” (with a given size specified by φ-quantile) for each object. While the first problem can be solved in polynomial time, we show that the 2nd problem is NP-hard. A set of efficient, novel algorithms have been proposed to give an exact solution for the first problem and an approximate solution for the second problem with the approximation ratio 2. Extensive experiment demonstrates that our techniques are very efficient and effective. results insensitive to relative distributions of instances of objects.
Keyphrases
multi-valued object quantile-based knn second problem first problem relative distribution exact solution median distance many application extensive experiment approximate solution quantile distance abstract nearest neighbor search efficient technique data mining basedonoverall distance polynomial time image processing novel algorithm approximation ratio
