Abstract
Support vector machines (SVMs) possess good accuracy in big data classification. However, the computational cost in both training and testing stages is a critical issue. In this study, we speed up the training speed through an integrated working set selection which is based on a modification of the selection pool of the working set of SVMs. In the testing stage, a lost-min strategy is proposed to accelerate the voting algorithm used in multi-SVMs. The number of the used binary classifiers is reduced from an order of to
(nearly to
or
). The proposed methods were tested with DNA dataset (bioinformatics), Usps datasets (handwritten digits), Letter dataset (English alphabet) and Satimage dataset (satellite imagery of Earth). We further theoretically derive the time complexity of the proposed method approaches to
algorithm in the case of high accuracy. This result is demonstrated through the experimental results for these datasets.
Acknowledgments
This research was supported by grant number MOST 107-2221-E-212-013 from the Ministry of Science and Technology of Taiwan, R.O.C.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Additional information
Funding
Notes on contributors
![](/cms/asset/1cb1784a-896e-43a6-a7da-db827195062a/tjca_a_1779978_ilg0003.gif)
Shinq-Jen Wu
Shinq-Jen Wu received the B.S. degree in chemical engineering from National Taiwan University, Taipei, Taiwan, the M.S. degree in chemical engineering from National Tsing-Hua University, Hsinchu, Taiwan, the M.S. degree in electrical engineering from the University of California, Los Angeles, USA, and the Ph.D. degree in electrical and control engineering from National Chiao-Tung University, Hsinchu, Taiwan. From September 1989 to July 1990, she was with the Laboratory for Simulation and Control Technology, Chemical Engineering Division, Industrial Technology Research Institute, Hsinchu. She then joined the Chemical Engineering Department, Kao-Yuan Junior College of Technology and Commerce, Kaohsiung, Taiwan. From 1995 to 1996, she was an engineer with the Integration Engineering Department, Macronix International Co., Ltd, Hsinchu. She is currently with the Department of Electrical Engineering, Da-Yeh University, Chang-Hwa, Taiwan. She is a member of PHI-TAU-PHI Scholastic Honor Society. Her name is included in Asian Admirable Achievers, in Asia/American Who's Who, in Asia/Pacifica Who's Who, and in Marquis Who's Who in Science and Engineering/in the World/in America/in Asia. She is a Life Fellow of the International Biographical Association. She is a Scientific Adviser to the IBC Director General. She got 21st Century Award for Achievement from IBC and The Albert Einstein Award of Excellent from ABI. She was the Editor-in-Chief of Anatomy & Physiology: Current Research (2014-2017), and is the editor of journal Advances in Fuzzy Sets and Systems, International Journal of Advanced Robotic Systems, Global Journal of Cancer Therapy and Journal of Food Science and Nutrition Therapy. Her research interests include ergonomics-based smart cars, advanced vehicle control and safety systems, Petri-net modeling for cancer mechanisms, soft-computational-based inference of biological systems, soft sensor for online tuning, very-large-scale integration process technology, optimal fuzzy control/tracking/estimation, and nature- and bio-inspired intelligent techniques.
![](/cms/asset/fb1d6bbf-fb66-4a95-967a-d837f59d3441/tjca_a_1779978_ilg0004.gif)
Van-hung Pham
Van-hung Pham was a faculty in Institute information of technology, Vietnam Academy of Science. He received the Ph.D. degree in electrical engineering on Jan. 2018 from Da-Yeh University, Chang-Hwa, Taiwan. During his PhD program, he focused on modifications of support vector machines and feature selection, which had been embedded in an automatic data entry system (VnHandwritten 1.0), the first commercial application of recognizing Vietnamese handwriting technology in Vietnam. After struggling with Cancer, he passed away on Nov. 18, 2019.