On-line unusual tension recognition system on twister using smooth support vector machine classifier

被引：0
作者：
Shih-Hsuan Chiu
Chuan-Pin Lu
机构：
[1] National Taiwan University of Science and Technology,Department of Polymer Engineering
来源：
The International Journal of Advanced Manufacturing Technology | 2006年 / 30卷
关键词：
Smooth support vector machine; Twister; Unusual tension;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this study, an on-line unusual tension recognition system for the yarn twist machine (twister) was proposed. This system is developed by a technique named smooth support vector machine (SSVM). SSVM is a robust supervised learning method, which is used as a classifier to recognize the unusual tension and noise type on the twister. This unusual tension recognition system includes three processes: unusual event check, feature analysis, and SSVM. The successful recognition ratio is greater than 90% from experimental results.
引用
收藏
页码：92 / 97
页数：5
相关论文
共 15 条
  • [1] Vapnik VN(1999)An overview of statistical learning theory IEEE Trans Neural Netw 10 988-999
  • [2] Brown M(1999)Support vector machines for optimal classification and spectral unmixing Ecol Model 120 167-179
  • [3] Gunn SR(2003)Hierarchical classification and feature reduction for fast face detection with support vector machines Pattern Recogn 36 2007-2017
  • [4] Lewis HG(2002)Asymptotic convergence of an SMO algorithm without any assumptions IEEE Trans Neural Netw 13 248-250
  • [5] Bernd H(2001)SSVM: a smooth support vector machine for classification Comput Optim Appl 20 5-22
  • [6] Thomas S(1995)Performance of filters for noise reduction in maxillary alveolar bone imaging IEEE Trans Biomed Eng 42 13-20
  • [7] Sam P(2003)Design and responses of Butterworth and critically damped digital filters J Electromyogr Kinesiol 13 569-573
  • [8] Tomaso P(undefined)undefined undefined undefined undefined-undefined
  • [9] Lin CJ(undefined)undefined undefined undefined undefined-undefined
  • [10] Lee YJ(undefined)undefined undefined undefined undefined-undefined
12