Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization
The main goal of this work was to assess the performance of different initializations of matrix factorization algorithms for an accurate identification of muscle synergies. Currently, nonnegative matrix factorization (NNMF) is the most commonly used method to identify muscle synergies. However, it h...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Applied Bionics and Biomechanics |
| Online Access: | http://dx.doi.org/10.1155/2018/3629347 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849304654069891072 |
|---|---|
| author | Mumtaz Hussain Soomro Silvia Conforto Gaetano Giunta Simone Ranaldi Cristiano De Marchis |
| author_facet | Mumtaz Hussain Soomro Silvia Conforto Gaetano Giunta Simone Ranaldi Cristiano De Marchis |
| author_sort | Mumtaz Hussain Soomro |
| collection | DOAJ |
| description | The main goal of this work was to assess the performance of different initializations of matrix factorization algorithms for an accurate identification of muscle synergies. Currently, nonnegative matrix factorization (NNMF) is the most commonly used method to identify muscle synergies. However, it has been shown that NNMF performance might be affected by different kinds of initialization. The present study aims at optimizing the traditional NNMF initialization for data with partial or complete temporal dependencies. For this purpose, three different initializations are used: random, SVD-based, and sparse. NNMF was used to identify muscle synergies from simulated data as well as from experimental surface EMG signals. Simulated data were generated from synthetic independent and dependent synergy vectors (i.e., shared muscle components), whose activation coefficients were corrupted by simulating controlled degrees of correlation. Similarly, EMG data were artificially modified, making the extracted activation coefficients temporally dependent. By measuring the quality of identification of the original synergies underlying the data, it was possible to compare the performance of different initialization techniques. Simulation results demonstrate that sparse initialization performs significantly better than all other kinds of initialization in reconstructing muscle synergies, regardless of the correlation level in the data. |
| format | Article |
| id | doaj-art-41ac324e378a4edc8e0d64d39b922c11 |
| institution | Kabale University |
| issn | 1176-2322 1754-2103 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Bionics and Biomechanics |
| spelling | doaj-art-41ac324e378a4edc8e0d64d39b922c112025-08-20T03:55:40ZengWileyApplied Bionics and Biomechanics1176-23221754-21032018-01-01201810.1155/2018/36293473629347Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix FactorizationMumtaz Hussain Soomro0Silvia Conforto1Gaetano Giunta2Simone Ranaldi3Cristiano De Marchis4Department of Engineering, Roma Tre University, Via Vito Volterra 62, 00146 Rome, ItalyDepartment of Engineering, Roma Tre University, Via Vito Volterra 62, 00146 Rome, ItalyDepartment of Engineering, Roma Tre University, Via Vito Volterra 62, 00146 Rome, ItalyDepartment of Engineering, Roma Tre University, Via Vito Volterra 62, 00146 Rome, ItalyDepartment of Engineering, Roma Tre University, Via Vito Volterra 62, 00146 Rome, ItalyThe main goal of this work was to assess the performance of different initializations of matrix factorization algorithms for an accurate identification of muscle synergies. Currently, nonnegative matrix factorization (NNMF) is the most commonly used method to identify muscle synergies. However, it has been shown that NNMF performance might be affected by different kinds of initialization. The present study aims at optimizing the traditional NNMF initialization for data with partial or complete temporal dependencies. For this purpose, three different initializations are used: random, SVD-based, and sparse. NNMF was used to identify muscle synergies from simulated data as well as from experimental surface EMG signals. Simulated data were generated from synthetic independent and dependent synergy vectors (i.e., shared muscle components), whose activation coefficients were corrupted by simulating controlled degrees of correlation. Similarly, EMG data were artificially modified, making the extracted activation coefficients temporally dependent. By measuring the quality of identification of the original synergies underlying the data, it was possible to compare the performance of different initialization techniques. Simulation results demonstrate that sparse initialization performs significantly better than all other kinds of initialization in reconstructing muscle synergies, regardless of the correlation level in the data.http://dx.doi.org/10.1155/2018/3629347 |
| spellingShingle | Mumtaz Hussain Soomro Silvia Conforto Gaetano Giunta Simone Ranaldi Cristiano De Marchis Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization Applied Bionics and Biomechanics |
| title | Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization |
| title_full | Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization |
| title_fullStr | Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization |
| title_full_unstemmed | Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization |
| title_short | Comparison of Initialization Techniques for the Accurate Extraction of Muscle Synergies from Myoelectric Signals via Nonnegative Matrix Factorization |
| title_sort | comparison of initialization techniques for the accurate extraction of muscle synergies from myoelectric signals via nonnegative matrix factorization |
| url | http://dx.doi.org/10.1155/2018/3629347 |
| work_keys_str_mv | AT mumtazhussainsoomro comparisonofinitializationtechniquesfortheaccurateextractionofmusclesynergiesfrommyoelectricsignalsvianonnegativematrixfactorization AT silviaconforto comparisonofinitializationtechniquesfortheaccurateextractionofmusclesynergiesfrommyoelectricsignalsvianonnegativematrixfactorization AT gaetanogiunta comparisonofinitializationtechniquesfortheaccurateextractionofmusclesynergiesfrommyoelectricsignalsvianonnegativematrixfactorization AT simoneranaldi comparisonofinitializationtechniquesfortheaccurateextractionofmusclesynergiesfrommyoelectricsignalsvianonnegativematrixfactorization AT cristianodemarchis comparisonofinitializationtechniquesfortheaccurateextractionofmusclesynergiesfrommyoelectricsignalsvianonnegativematrixfactorization |