Cross-Comparison of Three Electromyogram Decomposition Algorithms Assessed With Experimental and Simulated Data
- 22 May 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 23 (1) , 32-40
Abstract
The reliability of clinical and scientific information provided by algorithms that automatically decompose the electromyogram (EMG) depends on the algorithms' accuracies. We used experimental and simulated data to assess the agreement and accuracy of three publicly available decomposition algorithms-EMGlab (McGill , 2005) (single channel data only), Fuzzy Expert (Erim and Lim, 2008) and Montreal (Florestal , 2009). Data consisted of quadrifilar needle EMGs from the tibialis anterior of 12 subjects at 10%, 20% and 50% maximum voluntary contraction (MVC); single channel needle EMGs from the biceps brachii of 10 controls and 10 patients during contractions just above threshold; and matched simulated data. Performance was assessed via agreement between pairs of algorithms for experimental data and accuracy with respect to the known decomposition for simulated data. For the quadrifilar experimental data, median agreements between the Montreal and Fuzzy Expert algorithms at 10%, 20%, and 50% MVC were 95%, 86%, and 64%, respectively. For the single channel control and patient data, median agreements between the three algorithm pairs were statistically similar at ~ 97% and ~ 92%, respectively. Accuracy on the simulated data exceeded this performance. Agreement/accuracy was strongly related to the Decomposability Index (Florestal , 2009). When agreement was high between algorithm pairs applied to simulated data, so was accuracy.Keywords
This publication has 28 references indexed in Scilit:
- Rigorous a Posteriori Assessment of Accuracy in EMG DecompositionIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2010
- Intramuscular EMG Signal DecompositionCritical Reviews in Biomedical Engineering, 2010
- Unsupervised Bayesian Decomposition of Multiunit EMG Recordings Using Tabu SearchIEEE Transactions on Biomedical Engineering, 2009
- Automated decomposition of intramuscular electromyographic signalsIEEE Transactions on Biomedical Engineering, 2006
- A software package for the decomposition of long-term multichannel EMG signals using wavelet coefficientsIEEE Transactions on Biomedical Engineering, 2003
- Evaluation of intra-muscular EMG signal decomposition algorithmsJournal of Electromyography and Kinesiology, 2001
- High-precision EMG signal decomposition using communication techniquesIEEE Transactions on Signal Processing, 2000
- Decomposition of multiunit electromyographic signalsIEEE Transactions on Biomedical Engineering, 1999
- Unsupervised pattern recognition for the classification of EMG signalsIEEE Transactions on Biomedical Engineering, 1999
- Automatic Decomposition of the Clinical ElectromyogramIEEE Transactions on Biomedical Engineering, 1985