An SMO Approach to fast SVM for classification of large scale data

Juanxi Lin, Mengnan Song, Takayuki Furuzuki

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

Abstract

In this paper, a novel approach is proposed as a new fast Support Vector Machines (SVM) basing on sequential minimal optimization(SMO), minimum enclosing ball(MEB) approach and active set strategy. The combination with these 3 techniques largely accelerates the training process of SVM, attains fewer support vectors(SVs) as well as obtains a acceptable accuracy comparing to original SVM. From simulation results, it is stated that the proposed method will be a good alternative for classification of large scale data.

Original languageEnglish
Title of host publication2014 International Conference on IT Convergence and Security, ICITCS 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479965410
DOIs
Publication statusPublished - 2014 Jan 23
Event4th 2014 International Conference on IT Convergence and Security, ICITCS 2014 - Beijing, China
Duration: 2014 Oct 282014 Oct 30

Other

Other4th 2014 International Conference on IT Convergence and Security, ICITCS 2014
CountryChina
CityBeijing
Period14/10/2814/10/30

Keywords

  • active set
  • minimum enclosing ball
  • sequential minimal optimization
  • Support Vector Machine

ASJC Scopus subject areas

  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'An SMO Approach to fast SVM for classification of large scale data'. Together they form a unique fingerprint.

  • Cite this

    Lin, J., Song, M., & Furuzuki, T. (2014). An SMO Approach to fast SVM for classification of large scale data. In 2014 International Conference on IT Convergence and Security, ICITCS 2014 [7021735] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICITCS.2014.7021735