Neurodegenerative Disease Classification Using Nonlinear Gait Signal Analysis, Genetic Algorithm and Ensemble Classifier

摘要

Neurodegenerative diseases refer to the dysfunction of muscular and nervous system control. Gait analysis is an effective tool for identification and classification of the severity and the types of these diseases. In this paper, a novel method for neurodegenerative disease classification using nonlinear gait signal analysis is presented. For this purpose, the physionet database, which contains four sets of records for Huntington, Amyotrophic lateral sclerosis, Parkinson's and the control group, was used. The signal is decomposed by independent components analysis after pre-processing using wavelet transform and noise reduction. A set of chaotic and fractal features were extracted. Optimal features were selected using the genetic algorithm. The set of optimal features were considered as the input of AdaBoost structure. The results of the simulation showed an accuracy of 92.34±2.1% in classification of neurodegenerative diseases.