By Topic

Efficient K-Nearest Neighbors query based on MR-tree

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Zhang Hengfei ; Digital Eng. & Simulation Res. Center, Huazhong Univ. of Sci. & Tech., Wuhan, China ; Zeng Zhiyuan ; Tan Xiaojun ; Chen Jixiong

We present an approach based on novel structure called Multi-approximate R-tree (MR-tree) to performing the K-Nearest Neighbors (KNN) query efficiently and accurately in this paper. Maximal Enclosed Circle (MEC) is introduced to express an object approximately with Minimum Bound Rectangle (MBR). The introducing of the MEC improves the accuracy of the approximate expression of the spatial objects. We also discussed the implementation of the branch-and-bound MR-Tree traversal algorithm derived from R-Tree traversal algorithm. The metrics used in the traversal algorithm are the emphases in our discussion. Factors of the spatial dataset impact the performance of the KNN query and are considered separately in our designing of the experiments. We give some guide lines for the using of our approach with these factors. Finally, we presented the results of several experiments conducted using different structures to demonstrate the effectiveness and proved the efficiency enhancement of the MR-Tree over other structures.

Published in:

Advanced Computer Control (ICACC), 2010 2nd International Conference on  (Volume:5 )

Date of Conference:

27-29 March 2010