An MFCC based machine learning frame work for neuromuscular disorder detection

Cepstral analysis aimed at separating the excitation from the system is implemented in the current work for discriminating the healthy controls from the subjects with neuromuscular disorders. Because of aging, hereditary or diabetics these days, muscles related disorders are increasing. Neuropathy a...

Full description

Saved in:
Bibliographic Details
Main Authors: Murthy, G. L. N., Dharani, K., Likhith, E. Durga, Rao, K. Rama Tirupathi, Sandeep, M.
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Cepstral analysis
Disorders
Machine learning
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Cepstral analysis aimed at separating the excitation from the system is implemented in the current work for discriminating the healthy controls from the subjects with neuromuscular disorders. Because of aging, hereditary or diabetics these days, muscles related disorders are increasing. Neuropathy and myopathy diseases are investigated by the incorporation of two level algorithms. The work disassociates the healthy controls from the affected subjects initially by using mel frequency cepstral coefficients (MFCC) and then discriminates between the nature of disorder. Taeger energy operator ad standard deviation are the two features that are used in this process. Accuracy of 86.36 was obtained for identifying healthy controls while 93.33% for type of disorder.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0125634