A Comparative Study of the Techniques for Decomposition of EMG Signals

Abstract

This paper deals with four decomposition algorithms, which have been modified, implemented, analyzed and evaluated, for their performance in separation of motor unit action potentials (MUAPs) from the Electromyogram (EMG) Signals. The performance of algorithms has been evaluated to determine, as to which one out of the four algorithms is accurate, fast, reliable, efficient and can extract clean MUAPs even from those EMG signals which have been recorded for limited duration. Both synthetic and real time EMG signals have been used for testing the algorithms. The classification success rate achieved with statistical pattern recognition and cross-correlation approaches is 98.9% and 98.8% respectively whereas with Kohonen neural network 99.2% and wavelet transform 99.8%. Therefore the wavelet transform method is recommended because of its highest success rate, as this method does not require any correction for baseline drift or high frequency moise. It allows fast extraction of the localized frequency components, provides good time-resolution, and is capable of tracking rapid changes in MUAPs. The superimposed signal, which could not be separated by one of the above technique, has been decomposed by using cross-correlation and Euclidean distance. For earlier three techniques, the results are given only in tabular form while for wavelet technique, the results are presented both in tabular and graphical forms. All the algorithms have been successfully implemented and tested for decomposition of EMG signals recorded from subjects having normal (NOR) state of muscles and having motor neuron disorder (MND) and myopathy (MYO) disease.

Indexing terms:

• Signal
• Decomposition
• Motor unit action potential (MUAP)
• Statistical
• Cross-correlation
• Kohonen Neural-network
• Wavelet

Additional information

Notes on contributors

S C Saxena

S C Saxena obtained BE (Electrical) from Allahabad University in 1970 and ME Electrical (M&l) and PhD from University of Roorkee in 1973 and 1977 respectively. Dr Saxena joined Electrical Engineering Department of University of Roorkee (presently IIT Roorkee) in 1973, served as Professor and Head of Electrical Engineering Department during 1997–2000 and Dean of Student Welfare during 2001–2002. He was an expert at MTC, Baghdad, Iraq during 1983–86 and Adviser AICTE New Delhi during 1994. Since June 2002, he is serving as the Director, Thapar Institute of Engineering & Technology (Deemed University), Patiala and since January 2004 also as the Director, Thapar Centre for Industrial Research & Development (TCIRD). He has published over 150 research papers at National & International levels, guided large number of candidates for their PhD Theses, ME/M Phil Dissertations and UG/PG Projects, written 6 monographs, received 8 awards including Khosla Gold Medal and Cash Award, President of India's Prize, Jawaharlal Memorial Award. Dr Saxena is a fellow of IEI, IETE, and Life Member of BMESI, NIQR, ISTE and ISCEE. He is former Vice-President of Biomedical Engineering Society of India, Council member of the IE (I) and Chairman, Consultants Committee of Roorkee School for the Deaf, Chairman/Honorary Secretary of Roorkee Centre of the IE(I) Chairman ISTE Chapter at Roorkee and Vice-Chairman NIQR Chapter at Roorkee. He has worked on a number of Expert Committees of AICTE and University Sector Institutions and is a trained Motivation Trainer. He has wide experience of consultancy and testing. He is known for his contributions in Bio-medical Engineering, Measurement and Instrumentation, Signal Processing and Higher Technical Education.

A K Wadhwani

A K Wadhwani obtained his BE (Electrical) from Bhopal University in 1987, ME Electrical (Measurement & Instrumentation) from University of Roorkee in 1993 and PhD from Indian Institute of Technology Roorkee, in 2003 and he is serving as Reader in Electrical Engineering Department at Madhav Institute of Technology & Science, Gwalior. He has published 10 research papers. He is the life member of ISTE. His areas of interest are Applications of Artificial Neural Network, Fuzzy logic and Wavelets in the field of Biomedical Engineering, Measurement & Instrumentation, Process Instrumentation and Real Time Instrumentation.