Intelligent Garment Embedded CFS Evaluation based on PCA and Fuzzy SVM

摘要

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