VDBSCAN+: Performance Optimization Based on GPU Parallelism

Author

Valencio, Carlos Roberto ; Priolli Daniel, Guilherme ; Alves de Medeiros, Camila ; Mauro Cansian, Adriano ; Baida, Luiz Carlos ; Ferrari, Federico

Author_Institution

Dept. de Cienc. de Comput. e Estatistica, Sao Paulo State Univ., São José do Rio Preto, Brazil

fYear

2013

fDate

16-18 Dec. 2013

Firstpage

23

Lastpage

28

Abstract

Spatial data mining techniques enable the knowledge extraction from spatial databases. However, the high computational cost and the complexity of algorithms are some of the main problems in this area. This work proposes a new algorithm referred to as VDBSCAN+, which derived from the algorithm VDBSCAN (Varied Density Based Spatial Clustering of Applications with Noise) and focuses on the use of parallelism techniques in GPU (Graphics Processing Unit), obtaining a significant performance improvement, by increasing the runtime by 95% in comparison with VDBSCAN.

Keywords

graphics processing units; knowledge acquisition; parallel processing; pattern clustering; performance evaluation; visual databases; GPU parallelism techniques; VDBSCAN+; graphic processing unit; knowledge extraction; performance improvement; performance optimization; spatial databases; varied density based spatial clustering of application with noise; Algorithm design and analysis; Clustering algorithms; Data mining; Graphics processing units; Kernel; Runtime; Spatial databases; GPU (Graphics Processing Unit); VDBSCAN (Varied Density Based Spatial Clustering of Applications with Noise); spatial clustering; spatial data mining;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel and Distributed Computing, Applications and Technologies (PDCAT), 2013 International Conference on

Conference_Location

Taipei

Print_ISBN

978-1-4799-2418-9

Type

conf

DOI

10.1109/PDCAT.2013.11

Filename

6904228