Title :
Loudspeaker defect detection and classification using Support Vector Machine
Author :
Wei, Junfeng ; Yang, Yi ; Wen, Zhoubin ; Feng, Haihong
Author_Institution :
Shanghai Acoust. Lab., Chinese Acad. of Sci., Shanghai, China
Abstract :
A new method for detecting and classifying loudspeaker faults is presented in this paper. Total response of high-order harmonics groups is measured and used as defect features of loudspeaker. Based on support vector machine (SVM), we built a classification system combined with one-class SVM and Directed Acyclic Graphic SVM (DAGSVM). Comparing with K-nearest neighbor (k-NN) classifier, the accuracy of the method is higher in the experiment.
Keywords :
loudspeakers; pattern classification; support vector machines; K-nearest neighbor classifier; directed acyclic graphic SVM; high order harmonics group; loudspeaker defect detection; loudspeaker fault classification; one class SVM; support vector machine; Accuracy; Classification algorithms; Kernel; Loudspeakers; Noise; Support vector machines; Training; classification; detection; loudspeaker defect; support vector machine;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2010 Seventh International Conference on
Conference_Location :
Yantai, Shandong
Print_ISBN :
978-1-4244-5931-5
DOI :
10.1109/FSKD.2010.5569344
