Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2011, Vol. 12 Issue (2): 83-87    DOI: 10.1631/jzus.C1000022
    
Binary tree of posterior probability support vector machines
Dong-li Wang1,2, Jian-guo Zheng1, Yan Zhou*,2
1 Glorious Sun School of Business and Management, Donghua University, Shanghai 200051, China 2 College of Information Engineering, Xiangtan University, Xiangtan 411105, China
Download:   PDF(123KB)
Export: BibTeX | EndNote (RIS)      

Abstract  Posterior probability support vector machines (PPSVMs) prove robust against noises and outliers and need fewer storage support vectors (SVs). Gonen et al. (2008) extended PPSVMs to a multiclass case by both single-machine and multimachine approaches. However, these extensions suffer from low classification efficiency, high computational burden, and more importantly, unclassifiable regions. To achieve higher classification efficiency and accuracy with fewer SVs, a binary tree of PPSVMs for the multiclass classification problem is proposed in this letter. Moreover, a Fisher ratio separability measure is adopted to determine the tree structure. Several experiments on handwritten recognition datasets are included to illustrate the proposed approach. Specifically, the Fisher ratio separability accelerated binary tree of PPSVMs obtains overall test accuracy, if not higher than, at least comparable to those of other multiclass algorithms, while using significantly fewer SVs and much less test time.

Key wordsBinary tree      Support vector machine      Handwritten recognition      Classification     
Received: 01 February 2010      Published: 08 February 2011
CLC:  TP391  
Cite this article:

Dong-li Wang, Jian-guo Zheng, Yan Zhou. Binary tree of posterior probability support vector machines. Front. Inform. Technol. Electron. Eng., 2011, 12(2): 83-87.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1000022     OR     http://www.zjujournals.com/xueshu/fitee/Y2011/V12/I2/83


Binary tree of posterior probability support vector machines

Posterior probability support vector machines (PPSVMs) prove robust against noises and outliers and need fewer storage support vectors (SVs). Gonen et al. (2008) extended PPSVMs to a multiclass case by both single-machine and multimachine approaches. However, these extensions suffer from low classification efficiency, high computational burden, and more importantly, unclassifiable regions. To achieve higher classification efficiency and accuracy with fewer SVs, a binary tree of PPSVMs for the multiclass classification problem is proposed in this letter. Moreover, a Fisher ratio separability measure is adopted to determine the tree structure. Several experiments on handwritten recognition datasets are included to illustrate the proposed approach. Specifically, the Fisher ratio separability accelerated binary tree of PPSVMs obtains overall test accuracy, if not higher than, at least comparable to those of other multiclass algorithms, while using significantly fewer SVs and much less test time.

关键词: Binary tree,  Support vector machine,  Handwritten recognition,  Classification 
[1] Yue-peng ZOU , Ji-hong OUYANG , Xi-ming LI. Supervised topic models with weighted words: multi-label document classification[J]. Front. Inform. Technol. Electron. Eng., 2018, 19(4): 513-523.
[2] You-wei WANG, Li-zhou FENG. A new feature selection method for handling redundant information in text classification[J]. Front. Inform. Technol. Electron. Eng., 2018, 19(2): 221-234.
[3] Xi-bin JIA, Ya JIN , Ning LI, Xing SU, Barry CARDIFF, Bir BHANU. Words alignment based on association rules for cross-domain sentiment classification[J]. Front. Inform. Technol. Electron. Eng., 2018, 19(2): 260-272.
[4] Liu LIU , Bao-sheng WANG, Bo YU, Qiu-xi ZHONG. Automatic malware classification and new malware detection using machine learning[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(9): 1336-1347.
[5] Ehab ALI , Mahamod ISMAIL, Rosdiadee NORDIN, Nor Fadzilah ABDULAH. Beamforming techniques for massive MIMO systems in 5G: overview, classification, and trends for future research[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(6): 753-772.
[6] Ehsan Saeedi, Yinan Kong, Md. Selim Hossain. Side-channel attacks and learning-vector quantization[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 511-518.
[7] Jun-hong Zhang, Yu Liu. Application of complete ensemble intrinsic time-scale decomposition and least-square SVM optimized using hybrid DE and PSO to fault diagnosis of diesel engines[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(2): 272-286.
[8] Chu HE , Ya-ping YE , Ling TIAN , Guo-peng YANG , Dong CHEN. A statistical distribution texton feature for synthetic aperture radar image classification[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(10): 1614-1623.
[9] Guang-hui Song, Xiao-gang Jin, Gen-lang Chen, Yan Nie. Two-level hierarchical feature learning for image classification[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(9): 897-906.
[10] Mohammad Mosleh, Hadi Latifpour, Mohammad Kheyrandish, Mahdi Mosleh, Najmeh Hosseinpour. A robust intelligent audio watermarking scheme using support vector machine[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(12): 1320-1330.
[11] G. R. Brindha, P. Swaminathan, B. Santhi. Performance analysis of new word weighting procedures for opinion mining[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(11): 1186-1198.
[12] Gurmanik Kaur, Ajat Shatru Arora, Vijender Kumar Jain. Using hybrid models to predict blood pressure reactivity to unsupported back based on anthropometric characteristics[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(6): 474-485.
[13] Jie He, Yue-xiang Yang, Yong Qiao, Wen-ping Deng. Fine-grained P2P traffic classification by simply counting flows[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 391-403.
[14] Qi-rong Mao, Xin-yu Pan, Yong-zhao Zhan, Xiang-jun Shen. Using Kinect for real-time emotion recognition via facial expressions[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(4): 272-282.
[15] Li-gang Ma, Jin-song Deng, Huai Yang, Yang Hong, Ke Wang. Urban landscape classification using Chinese advanced high-resolution satellite imagery and an object-oriented multi-variable model[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(3): 238-248.