Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/7992
Title: A machine learning approach to distinguish Parkinson's disease (PD) patient's with shuffling gait from older adults based on gait signals using 3D motion analysis
Authors: Aich S.
Pradhan, Pyari Mohan
Park J.
Kim H.-C.
Published in: International Journal of Engineering and Technology(UAE)
Abstract: In recent times the adverse impact of Parkinson's disease (PD) getting worse and worse with the increasing rate of old age population through out the world. This disease is the second common neurological disorder and has a tremendous economical and social impact because the cost associated with the healthcare as well as service is extremely high. The diagnosis process of this disease mostly done by closely observing the patient in the clinic as well as using the rating scale. However, this kind of diagnosis is subjective in nature and usually takes long time and assessment of this disease is complicated and cannot replicated in other patients. This kind of diagnosis method is also not suitable for the early detection of the PD. So, with this shortcoming it is necessary to find a suitable method that can automate the process as well as useful in the initial phase of diagnosis of PD. Recently with the invention of motion capture equipment's and artificial intelligent technique, the feasibility of the objective nature-based diagnosis is getting lot of attention, especially the objective quantification of gait parameters. Shuffling of gait is one of the important characteristics of PD patients and it is usually defined y shorter stride length and low foot clearance. In this study a novel method is proposed to quantify the gait parameters using 3D motion captures and then various feature selection algorithm have used to select the effective features and finally machine learning based techniques were implemented to automate the classification process of two groups composed of PD patients as well as older adults. We have found maximum accuracy of 98.54 %by using support vector machine (SVM) classifier with radial basis function coupled with minimum redundancy and maximum relevance (MRMR) algorithm-based feature set. Our result showed that the proposed method can help the clinicians to distinguish PD patients from the older adults. This method helps to detect the PD at early stage. © 2018 Satyabrata Aich et. al.
Citation: International Journal of Engineering and Technology(UAE) (2018), 7(3): 153-156
URI: https://doi.org/10.14419/ijet.v7i3.29.18547
http://repository.iitr.ac.in/handle/123456789/7992
Issue Date: 2018
Publisher: Science Publishing Corporation Inc
Keywords: Feature selection
Machine learning
Parkinson's disease
Shuffling gait
Wearable sensor
ISSN: 2227524X
Author Scopus IDs: 56149932800
26639724100
54938807200
55739535700
Author Affiliations: Aich, S., Department of Computer Engineering/IDA, Inje University, Gimhae, South Korea
Pradhan, P.M., Department of Electronics and Communication Engineering, IIT, Roorkee, India
Park, J., Department of Neurology, INJE University College of Medicine, Busan, South Korea
Kim, H.-C., Department of Computer Engineering/IDA, Inje University, Gimhae, South Korea
Corresponding Author: Aich, S.; Department of Computer Engineering/IDA, Inje UniversitySouth Korea; email: satyabrataaich@gmail.com
Appears in Collections:Journal Publications [ECE]

Files in This Item:
There are no files associated with this item.
Show full item record


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