EMG signal processing and diagnostic of muscle diseases

Author

Alim, O.A. ; Moselhy, Mohamed ; Mroueh, F.

Author_Institution

Electr. & Comput. Eng. Dept., Beirut Arab Univ., Beirut, Lebanon

fYear

2012

fDate

12-15 Dec. 2012

Firstpage

1

Lastpage

6

Abstract

Real time recordings of motor unit action potential (MUAP) signals from myopathy (MYO), neuropathy (NEU), and normal (NOR) subjects, using intramuscular electromyography (needle EMG) are treated and processed in order to be classified for the diagnosis of neuromuscular pathology. Feedforward-backpropagation neural network is used for the classification. Recognition rates were found to be higher than 70% and higher when using time domain features as inputs for the neural network.

Keywords

backpropagation; diseases; electromyography; feedforward; medical signal processing; neural nets; EMG signal processing; feed forward back propagation neural network; intramuscular electromyography; motor unit action potential; muscle disease diagnosis; myopathy subjects; needle EMG; neuromuscular pathology diagnosis; neuropathy subjects; real time MUAP recordings; recognition rate; Biological neural networks; Electromyography; Feature extraction; Frequency domain analysis; MATLAB; Support vector machine classification; Time domain analysis; Biomedical; EMG; Neural Network; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in Computational Tools for Engineering Applications (ACTEA), 2012 2nd International Conference on

Conference_Location

Beirut

Print_ISBN

978-1-4673-2488-5

Type

conf

DOI

10.1109/ICTEA.2012.6462866

Filename

6462866