Rigorous performance assessment of the algorithms for resolving motor unit action potential superpositions |
| |
| Affiliation: | 1. Biomedical Engineering Department, Faculty of Engineering, the University of Isfahan, Isfahan, Iran;2. Department of Automatic Control, Biomedical Engineering Research Center, Universitat Politècnica de Catalunya, BarcelonaTech (UPC), Barcelona, Spain;3. VA Palo Alto Health Care System, Palo Alto, CA, USA;4. Biomedical Research Networking Center in Bioengineering, Biomaterials, and Nanomedicine (CIBER-BBN), Barcelona, Spain;1. Facultad de Ciencias de la Salud, Departamento de Enfermería, Fisioterapia y Medicina, Universidad de Almería, Almería, España;2. Facultad de Psicología, Universidad de Almería, Almería, España;3. Centro Deportivo Ego, Almería, España;1. Inserm Research Center for Epidemiology and Biostatistics (U897) – Team Neuroepidemiology, Bordeaux, France;2. University of Bordeaux, Bordeaux, France;3. Inserm Unit 897—Epidemiology and Biostatistics Research Center (U897) – Team Epidemiology and Neuropsychology of Cerebral Aging, Bordeaux, France;4. Inserm Unit 1061—Neuropsychiatry: Epidemiological and Clinical Research, University of Montpellier, Montpellier, France;5. Inserm Unit 657—Pharmacoepidemiology and Evaluation of the Impact of Health Products on Populations, Bordeaux, France;1. Department of Civil and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, 08826, Seoul, Republic of Korea;2. Department of Civil, Architectural, and Environmental Engineering, University of Miami, 1251 Memorial Dr. McArthur Engineering Building, Coral Gables, FL, 33146-0630, USA;3. Integrated Research Institute of Construction and Environmental Engineering, Seoul National University, 1 Gwanak-ro, Gwanak-gu, 08826, Seoul, Republic of Korea;1. Unidad de Kinesiología, Instituto de Aparato Locomotor y Rehabilitación, Facultad de Medicina, Universidad Austral de Chile, Valdivia, Chile;2. Laboratorio de función cardiorrespiratoria y metabólica – Neyün, Facultad de Medicina, Universidad Austral de Chile, Valdivia, Chile;3. Centro Interdisciplinario de Estudios del Sistema Nervioso (CISNe), Valdivia, Chile;4. Departamento de Salud Pública-Centro de Investigación EPICYN, Facultad de Medicina, Universidad de La Frontera, Temuco, Chile;1. Sports Department, Pará State University, Belém, Brazil;2. Northeast Biotechnology Network, Postgraduate Program in Biotechnology, Ceará State University, Fortaleza, Brazil;3. Biotechnology and Exercise Biology Research Laboratory, Institute of Physical Education and Sports, Federal University of Ceará, Fortaleza, Brazil;4. Metabolism, Nutrition and Exercise Laboratory, Physical Education and Sport Center, Londrina State University, Londrina, Brazil;5. Endocrine Physiology Doris Rosenthal Research Laboratory, Institute of Biophysical Carlos Chagas Filho, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil;6. Biochemistry and Gene Expression Research Laboratory, Superior Institute of Biomedical Science, Ceará State University, Fortaleza, Brazil |
| |
| Abstract: | It is necessary to decompose the intra-muscular EMG signal to extract motor unit action potential (MUAP) waveforms and firing times. Some algorithms were proposed in the literature to resolve superimposed MUAPs, including Peel-Off (PO), branch and bound (BB), genetic algorithm (GA), and particle swarm optimization (PSO). This study aimed to compare these algorithms in terms of overall accuracy and running time. Two sets of two-to-five MUAP templates (set1: a wide range of energies, and set2: a high degree of similarity) were used. Such templates were time-shifted, and white Gaussian noise was added. A total of 1000 superpositions were simulated for each template and were resolved using PO (also, POI: interpolated PO), BB, GA, and PSO algorithms. The generalized estimating equation was used to identify which method significantly outperformed, while the overall rank product was used for overall ranking. The rankings were PSO, BB, GA, PO, and POI in the first, and BB, PSO, GA, PO, POI in the second set. The overall ranking was BB, PSO, GA, PO, and POI in the entire dataset. Although the BB algorithm is generally fast, there are cases where the BB algorithm is too slow and it is thus not suitable for real-time applications. |
| |
| Keywords: | Resolving Superposition EMG decomposition Motor unit action potentials |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
