Title :
Research and application of non-negative matrix factorization with sparseness constraint in recognition of traditional Chinese medicine pulse condition
Author :
Guo Rui ; Wang Yiqin ; Yan Haixia ; Li Fufeng ; Xu Zhaoxia ; Yan Jianjun
Author_Institution :
Lab. of Inf. Access & Synthesis of TCM Four Diagnosis, Shanghai Univ. of Traditional Chinese Med., Shanghai, China
Abstract :
In this paper, the recognition method based on non-negative matrix factorization with sparseness constraint (NMFs) combined with the support vector machine (SVM) was proposed to identify the type of the common pulse condition of Chinese Traditional Medicine (TCM). First, pulse data were factorized by NMFs to obtain projection coefficients as training sample set to build recognition mode with SVM. Then the method proposed was compared with the classical time-domain method of pulse feature extraction. And time-domain features were extracted to identify the type of pulse with the same SVM classifier. Finally, the results showed that projection coefficients obtained by NMFs more use of recognition of TCM pulse.
Keywords :
feature extraction; matrix decomposition; medical signal processing; patient diagnosis; support vector machines; NMF; SVM classifier; TCM pulse condition recognition; nonnegative matrix factorization; projection coefficients; pulse data; sparseness constraint; support vector machine; time domain pulse feature extraction; traditional Chinese medicine; Traditional Chinese Medicine; feature extraction and recognition of pulse; non-negative matrix factorization with sparseness constraint; pulse condition; support vector machine;
Conference_Titel :
Bioinformatics and Biomedicine Workshops (BIBMW), 2010 IEEE International Conference on
Conference_Location :
Hong, Kong
Print_ISBN :
978-1-4244-8303-7
Electronic_ISBN :
978-1-4244-8304-4
DOI :
10.1109/BIBMW.2010.5703888
