PSO-based DBSCAN with obstacle constraints.

Xiaoning Feng; Guisheng Yin; Ying Wang; Zhuo Wang

No Detail Found!

PSO-based DBSCAN with obstacle constraints.

Author(s)

Xiaoning Feng College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China

Guisheng Yin College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China

Ying Wang College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China

Zhuo Wang National Key Laboratory of Science and Technology On Autonomous Underwater Vehicle, Harbin Engineering University, Harbin 150001, China

Abstract

This paper presents a new PSO-based optimization DBSCAN space clustering algorithm with obstacle constraints. The algorithm introduces obstacle model and simplifies two-dimensional coordinates of the cluster object coding to one-dimensional, then uses the PSO algorithm to obtain the shortest path and minimum obstacle distance. At the last stage, this paper fulfills spatial clustering based on obstacle distance. Theoretical analysis and experimental results show that the algorithm can get high-quality clustering result of space constraints with more reasonable and accurate quality.

Publication Details

Page(s) 377-383

DOI DOI not available

Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 46, Issue: 1, Year: 2012

Request the full text from PASTIC

Citations

Downloads

Views