Open AccessMINIMIZED FEATURE SELECTION FOR DETECTION OF PARKINSON’S DISEASE USING NEURO-FUZZY SYSTEM
Author(s) -
SANG-HONG LEE
Publication year - 2022
Publication title -
journal of mechanics in medicine and biology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.236
H-Index - 30
eISSN - 1793-6810
pISSN - 0219-5194
DOI - 10.1142/s0219519422400048
Subject(s) - feature selection , pattern recognition (psychology) , artificial intelligence , fuzzy logic , sensitivity (control systems) , norm (philosophy) , computer science , artificial neural network , parkinson's disease , feature (linguistics) , mathematics , data mining , disease , engineering , medicine , pathology , political science , linguistics , philosophy , electronic engineering , law
This study presents a methodology for detecting Parkinson’s disease using a neuro-fuzzy system (NFS) with feature selection. From all the 22 features, the five most accurate minimized features were selected using neural networks with weighted fuzzy membership functions (NEWFMs), which supported the nonoverlapping region method (NORM). NORM eliminates the worst features and can select the minimized features constituting each interpretable fuzzy membership. As an input to the NEWFMs, all 22 features indicated a performance sensitivity, specificity and accuracy of 87.43%, 96.43% and 88.72%, respectively. In addition, at least five features of the NEWFMs showed performance sensitivity, specificity and accuracy of 95.24%, 85.42% and 92.82%, respectively.