Parallel execution of distributed SVM using MPI (CoDLib)

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

Support Vector Machine (SVM) is an efficient data mining approach for data classification. However, SVM algorithm requires very large memory requirement and computational time to deal with very large dataset. To reduce the computational time during the process of training the SVM, a combination of distributed and parallel computing method, CoDLib have been proposed. Instead of using a single machine for parallel computing, multiple machines in a cluster are used. Message Passing Interface (MPI) is used in the communication between machines in the cluster. The original dataset is split and distributed to the respective machines. Experiments results shows a great speed up on the training of the MNIST dataset where training time has been significantly reduced compared with standard LIBSVM without affecting the quality of the SVM.

Original languageEnglish
Title of host publication2011 International Conference on Information Technology and Multimedia
Subtitle of host publication"Ubiquitous ICT for Sustainable and Green Living", ICIM 2011
DOIs
Publication statusPublished - 01 Dec 2011
Event2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011 - Kajang, Malaysia
Duration: 14 Nov 201116 Nov 2011

Publication series

Name2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011

Other

Other2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011
CountryMalaysia
CityKajang
Period14/11/1116/11/11

Fingerprint

Message passing
Support vector machines
Parallel processing systems
Distributed computer systems
Data mining
Data storage equipment
Communication
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Information Systems
  • Software

Cite this

Md Salleh, N. S., Suliman, A., & Ahmad, A. R. (2011). Parallel execution of distributed SVM using MPI (CoDLib). In 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011 [6122723] (2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011). https://doi.org/10.1109/ICIMU.2011.6122723
Md Salleh, Nur Shakirah ; Suliman, Azizah ; Ahmad, Abd Rahim. / Parallel execution of distributed SVM using MPI (CoDLib). 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011. 2011. (2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011).
@inproceedings{35e69a6a00e64fe287e1e5683c1e181a,
title = "Parallel execution of distributed SVM using MPI (CoDLib)",
abstract = "Support Vector Machine (SVM) is an efficient data mining approach for data classification. However, SVM algorithm requires very large memory requirement and computational time to deal with very large dataset. To reduce the computational time during the process of training the SVM, a combination of distributed and parallel computing method, CoDLib have been proposed. Instead of using a single machine for parallel computing, multiple machines in a cluster are used. Message Passing Interface (MPI) is used in the communication between machines in the cluster. The original dataset is split and distributed to the respective machines. Experiments results shows a great speed up on the training of the MNIST dataset where training time has been significantly reduced compared with standard LIBSVM without affecting the quality of the SVM.",
author = "{Md Salleh}, {Nur Shakirah} and Azizah Suliman and Ahmad, {Abd Rahim}",
year = "2011",
month = "12",
day = "1",
doi = "10.1109/ICIMU.2011.6122723",
language = "English",
isbn = "9781457709890",
series = "2011 International Conference on Information Technology and Multimedia: {"}Ubiquitous ICT for Sustainable and Green Living{"}, ICIM 2011",
booktitle = "2011 International Conference on Information Technology and Multimedia",

}

Md Salleh, NS, Suliman, A & Ahmad, AR 2011, Parallel execution of distributed SVM using MPI (CoDLib). in 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011., 6122723, 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011, 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011, Kajang, Malaysia, 14/11/11. https://doi.org/10.1109/ICIMU.2011.6122723

Parallel execution of distributed SVM using MPI (CoDLib). / Md Salleh, Nur Shakirah; Suliman, Azizah; Ahmad, Abd Rahim.

2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011. 2011. 6122723 (2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Parallel execution of distributed SVM using MPI (CoDLib)

AU - Md Salleh, Nur Shakirah

AU - Suliman, Azizah

AU - Ahmad, Abd Rahim

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Support Vector Machine (SVM) is an efficient data mining approach for data classification. However, SVM algorithm requires very large memory requirement and computational time to deal with very large dataset. To reduce the computational time during the process of training the SVM, a combination of distributed and parallel computing method, CoDLib have been proposed. Instead of using a single machine for parallel computing, multiple machines in a cluster are used. Message Passing Interface (MPI) is used in the communication between machines in the cluster. The original dataset is split and distributed to the respective machines. Experiments results shows a great speed up on the training of the MNIST dataset where training time has been significantly reduced compared with standard LIBSVM without affecting the quality of the SVM.

AB - Support Vector Machine (SVM) is an efficient data mining approach for data classification. However, SVM algorithm requires very large memory requirement and computational time to deal with very large dataset. To reduce the computational time during the process of training the SVM, a combination of distributed and parallel computing method, CoDLib have been proposed. Instead of using a single machine for parallel computing, multiple machines in a cluster are used. Message Passing Interface (MPI) is used in the communication between machines in the cluster. The original dataset is split and distributed to the respective machines. Experiments results shows a great speed up on the training of the MNIST dataset where training time has been significantly reduced compared with standard LIBSVM without affecting the quality of the SVM.

UR - http://www.scopus.com/inward/record.url?scp=84856509269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856509269&partnerID=8YFLogxK

U2 - 10.1109/ICIMU.2011.6122723

DO - 10.1109/ICIMU.2011.6122723

M3 - Conference contribution

SN - 9781457709890

T3 - 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011

BT - 2011 International Conference on Information Technology and Multimedia

ER -

Md Salleh NS, Suliman A, Ahmad AR. Parallel execution of distributed SVM using MPI (CoDLib). In 2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011. 2011. 6122723. (2011 International Conference on Information Technology and Multimedia: "Ubiquitous ICT for Sustainable and Green Living", ICIM 2011). https://doi.org/10.1109/ICIMU.2011.6122723