A GPGPU Approach to Accelerate Ant Swarm Optimization Rough Reducts (ASORR) Algorithm

Udayanti, Erika Devi and Choo, Yun Huoy and Draman @ Muda, Azah Kamilah and Nugroho, Fajar Agung (2012) A GPGPU Approach to Accelerate Ant Swarm Optimization Rough Reducts (ASORR) Algorithm. In: The International Conference on Information Technology and Electrical Engineering (CITEE) 2012, 12 July 2012, Yogyakarta, Indonesia.

[img] Text
citee2012_submission_91.pdf
Restricted to Registered users only

Download (463kB) | Request a copy

Abstract

Reducts can be used to discern all discernible objects from the original information system. In order to find a reducts, a such applications of rough set uses a discernibility matrix. Ant Swarm Optimization Rough Reducts (ASORR) algorithm is used in rough reducts calculation for identifying significant attribute set optimally. For the complex matrix calculation in a single cpu, it will take a long computing time to build the discernibility matrix whereas the execution time of an algorithm is needed to be considered. This paper proposed an parallel approach to accelerate the execution time of ASORR algorithm which is utilizing GPGPU that supports high speed parallel computing. It will be implemented with CUDA from NVIDIA. The experiment results indicate that parallel ASORR achieve the acceleration on GPGPU.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Rough reducts, Ant swarm optimization, Parallel approach, GPGPU, CUDA
Subjects: T Technology > T Technology (General)
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Information and Communication Technology > Department of Industrial Computing
Depositing User: Dr. Yun-Huoy Choo
Date Deposited: 06 Jan 2013 01:46
Last Modified: 17 Aug 2023 12:28
URI: http://eprints.utem.edu.my/id/eprint/6466
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item