Title: Fuzzy SVM-based chronic fatigue syndrome evaluation embedded in intelligent garment

Authors: YiZhi Wu, Yong Sheng Ding, HongAn Xu, Hong Fan, BoHui Zhu

Addresses: College of Information Sciences and Technology, Donghua University, Shanghai 201620, China; Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, Shanghai 201620, China. ' College of Information Sciences and Technology, Donghua University, Shanghai 201620, China; Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, Shanghai 201620, China. ' College of Information Sciences and Technology, East China Normal University, Shanghai, 200062, China. ' College of Information Sciences and Technology, Donghua University, Shanghai, 201620, China. ' College of Information Sciences and Technology, Donghua University, Shanghai, 201620, China

Abstract: Intelligent garment (IG), which is embedded with electrical vital signal capturing and analysis model, can be used to offer personal health monitoring anytime and anywhere. Chronic fatigue syndrome (CFS) is a serious and complex problem for people all over the world. But the methods of CFS diagnosis up to now have been very elementary. In this paper, we present the architecture and design consideration of IG embedded in an online CFS evaluation system based on our previous work. To meet the system needs, we perfect the schema by decreasing feature space using principal component analyses (PCA) and by diagnosing CFS more accurately using fuzzy multiclass SVM. Using the ISNI-DHU CFS database we set up, two series of experiments are done and the results show that the RR interval and R amplitude are the most important features and the fuzzy SVM achieved 93.3% of average sensitivity.

Keywords: intelligent garments; chronic fatigue syndrome; CFS; fuzzy SVM classifier; principal component analysis; PCA; ECG feature; personal health monitoring; support vector machines.

DOI: 10.1504/IJMIC.2009.029028

International Journal of Modelling, Identification and Control, 2009 Vol.8 No.2, pp.155 - 163

Published online: 27 Oct 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article