Open AccessFiltering and analyzing normal and abnormal electromyogram signals
Author(s) -
Samir Elouaham,
Azzedine Dliou,
Mostafa Laaboubi,
Rachid Latif,
Najib Elkamoun,
Hicham Zougagh
Publication year - 2020
Publication title -
indonesian journal of electrical engineering and computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.241
H-Index - 17
eISSN - 2502-4760
pISSN - 2502-4752
DOI - 10.11591/ijeecs.v20.i1.pp176-184
Subject(s) - hilbert–huang transform , noise (video) , pattern recognition (psychology) , electromyography , noise reduction , artificial intelligence , speech recognition , signal (programming language) , motor unit , computer science , kernel (algebra) , mathematics , computer vision , filter (signal processing) , neuroscience , physical medicine and rehabilitation , medicine , combinatorics , image (mathematics) , programming language , biology
The electromyogram (EMG) is an important measurement to assess the health of muscles and the nerve cells that control them. The appearance of noise in electromyography (EMG) signals may unquestionably minimize the efficiency of the analysis of the signal. The denoising techniques are inevitable for minimizing noise affecting the EMG signals; these methods are Complete Ensemble Empirical Mode Decompositions with Adaptive Noise (CEEMDAN) and the Ensemble Empirical Mode Decomposition (EEMD). After that, we analyze these signals by time-frequency techniques as Adaptive Optimal Kernel (AOK) and Choi-Williams. Firstly, the obtained results illustrate the effectiveness of the CEEMDAN that permits reducing noise that interferes with normal and abnormal EMG signals with higher resolution than other techniques used as EEMD. Secondly, they show that the AOK technique is adapted to the detection and classification of these types of normal and abnormal EMG signals by the good localization of the Motor Unit Action Potentials (MUAPs) in the time-frequency plan. This paper shows the efficiency of the combination of the AOK and CEEMDAN techniques in analyzing the EMG signals.