Analyze the wild birds' migration tracks by MPI-based parallel clustering algorithm

Authors:
HaiMing Zhang;YuanChun Zhou;JianHui Li;XueZhi Wang;BaoPing Yan
Affiliations:
Computer Network Information Center, Chinese Academy of Sciences, Beijing;Computer Network Information Center, Chinese Academy of Sciences, Beijing;Computer Network Information Center, Chinese Academy of Sciences, Beijing;Computer Network Information Center, Chinese Academy of Sciences, Beijing;Computer Network Information Center, Chinese Academy of Sciences, Beijing
Venue:
ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications: Part I
Year:
2010

Citing 3
Cited 0

STING: A Statistical Information Grid Approach to Spatial Data Mining

VLDB '97 Proceedings of the 23rd International Conference on Very Large Data Bases
STING+: An Approach to Active Spatial Data Mining

ICDE '99 Proceedings of the 15th International Conference on Data Engineering
Discovery of Migration Habitats and Routes of Wild Bird Species by Clustering and Association Analysis

ADMA '09 Proceedings of the 5th International Conference on Advanced Data Mining and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Aiming at the avian influenza outbreak in Qinghai Lake area, the satellite tracking of migratory birds in Qinghai Lake is studied to analyze the relationship between bird migration, virus spread and ecological environment. These biological problems have been converted into computational studies in previous studies in which spatial clustering is the key factor. A bird migration data analysis system based on DBSCAN algorithm was designed in previous work, by which data can be systematically analyzed, and knowledge patterns are subsequently available for deep biological studies. As the GPS (Global Positioning System) raw data grows rapidly which is large scale with high complexity, DBSCAN takes long time (several minutes) to get the result. In this paper, parallel STING (statistical information grid) algorithm is designed and implemented based on MPI (message passing interface) for spatial clustering. By using parallel STING algorithm, it only takes several seconds to get the result.