Title:Fuzzy Classification Methods Based Diagnosis of Parkinson’s disease from Speech Test Cases
VOLUME: 12 ISSUE: 2
Author(s):Niousha Karimi Dastjerd, Onur Can Sert, Tansel Ozyer and Reda Alhajj*
Affiliation:TOBB University of Economics and Technology, Sogutozu, Ankara, 06560, TOBB University of Economics and Technology, Sogutozu, Ankara, 06560, TOBB University of Economics and Technology, Sogutozu, Ankara, 06560, Department of Computer Science, University of Calgary, Calgary, Alberta
Keywords:Parkinson's disease, data mining, machine learning, fuzzy classification, neuro fuzzy classification, adaptive neuro
fuzzy classification.
Abstract:
Background: Together with the Alzheimer’s disease, Parkinson’s disease is considered
as one of the two serious known neurodegenerative diseases. Physicians find it hard to
predict whether a given patient has already developed or is expected to develop the Parkinson’s
disease in the future. To overcome this difficulty, it is possible to develop a computing
model, which analyzes the data related to a given patient and predicts with acceptable accuracy
when he/she is anticipated to develop the Parkinson’s disease.
Objectives: This paper contributes an attractive prediction framework based on some machine
learning approaches for distinguishing people with Parkinsonism from healthy individuals.
Methods: Several fuzzy classifiers such as Inductive Fuzzy Classifier, Fuzzy Rough Classifier
and two types of neuro-fuzzy classifiers have been employed.
Results: The fuzzy classifiers utilized in this study have been tested using the “Parkinson
Speech Dataset with Multiple Types of Sound Recordings Data Set” of 40 subjects available
on the UCI repository.
Conclusion: The results achieved show that FURIA, MLP- Bagging - SGD, genfis2 and scg1
performed the best among the fuzzy rough, WEKA, adaptive neuro-fuzzy and neuro-fuzzy
classifiers, respectively. The worst performance belongs to nearest neighborhood, IBK, genfis3
and scg3 among the formerly mentioned classifiers. The results reported in this paper are better
in comparison to the results reported in Sakar et al., where the same dataset was used, with utilization
of different classifiers. This demonstrates the applicability and effectiveness of the
fuzzy classifiers used in this study as compared to the non-fuzzy classifiers used by Sakar et al.
