Please use this identifier to cite or link to this item:
Title: Fuzzy classification methods based diagnosis of parkinson’s disease from speech test cases
Authors: Dastjerd, Niousha Karim
Sert, Onur Can
Özyer, Tansel
Alhajj, Reda
Keywords: Adaptive neuro fuzzy classification
data mining
fuzzy classification
machine learning
neuro fuzzy classification
Parkinson’s disease
Issue Date: 2019
Publisher: Bentham Science Publishers
Source: Dastjerd, N. K., Sert, O. C., Ozyer, T and Alhajj, R. (2019). Fuzzy classification methods based diagnosis of Parkinson’s disease from speech test cases. Current Aging Science, 12(2), 100-120.
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. © 2019 Bentham Science Publishers.
ISSN: 18746098
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Yapay Zeka Mühendisliği Bölümü / Department of Artificial Intelligence Engineering

Show full item record

CORE Recommender


checked on Jul 13, 2022

Page view(s)

checked on Aug 8, 2022

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.