Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects: Experiments with statistical features and different classification models. (April 2015)

• Record Type: Journal Article
• Authors: Xia, Yi; Gao, Qingwei; Ye, Qiang
• Is Part Of: Biomedical signal processing and control. Volume 18(2015)
• Page Start: 254
• Page End: 262
• Publication Date: 2015-04
• Subjects: Gait classification -- Neuro-degenerative diseases -- Statistical features -- Feature selection; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2015.02.002
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Different statistical features are extracted from gait rhythm signals. A heuristic feature selection method is applied to generate the optimal subset. An accurate multi-class diagnosis system for neuro-degenerative diseases is proposed. Mean value, Teager energy and fuzzy entropy are the most discriminating features. Abstract: For the purpose of realizing an intelligent and highly accurate diagnosis system for neuro-degenerative diseases (NDD), such as amyotrophic lateral sclerosis (ALS), Parkinson's disease (PD) and Huntington's disease (HD), the present study investigated the classification capability of different gait statistical features extracted from gait rhythm signals. Nine statistical measures, including several seldom-used variability measures for these signals, were calculated for each time series. Next, after an evaluation of four popular machine learning methods, the optimal feature subset was generated with a hill-climbing feature selection method. Experiments were performed on a data set with 16 healthy control (CO) subjects, 13 ALS, 15 PD and 20 HD patients. When evaluated with the leave-one-out cross-validation (LOOCV) method, the highest accuracy rate for discriminating between groups of NDD patients and healthy control subjects was 96.83%. The best classification accuracy (100%) was obtained with two subtype binary classifiers (PD vs. CO and HD vs. CO).