Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification
IntroductionMuscular activation sequences have been shown to be suitable time-domain features for classification of motion gestures. However, their clinical application in myoelectric prosthesis control was never investigated so far. The aim of the paper is to evaluate the robustness of these featur...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2023.1264802/full |
| _version_ | 1797629588483866624 |
|---|---|
| author | Federico Mereu Federico Mereu Federico Morosato Francesca Cordella Loredana Zollo Emanuele Gruppioni |
| author_facet | Federico Mereu Federico Mereu Federico Morosato Francesca Cordella Loredana Zollo Emanuele Gruppioni |
| author_sort | Federico Mereu |
| collection | DOAJ |
| description | IntroductionMuscular activation sequences have been shown to be suitable time-domain features for classification of motion gestures. However, their clinical application in myoelectric prosthesis control was never investigated so far. The aim of the paper is to evaluate the robustness of these features extracted from the EMG signal in transient state, on the forearm, for classifying common hand tasks.MethodsThe signal associated to four hand gestures and the rest condition were acquired from ten healthy people and two persons with trans-radial amputation. A feature extraction algorithm allowed for encoding the EMG signals into muscular activation sequences, which were used to train four commonly used classifiers, namely Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Non-linear Logistic Regression (NLR) and Artificial Neural Network (ANN). The offline performances were assessed with the entire sample of recruited people. The online performances were assessed with the amputee subjects. Moreover, a comparison of the proposed method with approaches based on the signal envelope in the transient state and in the steady state was conducted.ResultsThe highest performance were obtained with the NLR classifier. Using the sequences, the offline classification accuracy was higher than 93% for healthy and amputee subjects and always higher than the approach with the signal envelope in transient state. As regards the comparison with the steady state, the performances obtained with the proposed method are slightly lower (<4%), but the classification occurred at least 200 ms earlier. In the online application, the motion completion rate reached up to 85% of the total classification attempts, with a motion selection time that never exceeded 218 ms.DiscussionMuscular activation sequences are suitable alternatives to the time-domain features commonly used in classification problems belonging to the sole EMG transient state and could be potentially exploited in control strategies of myoelectric prosthesis hands. |
| first_indexed | 2024-03-11T10:55:20Z |
| format | Article |
| id | doaj.art-8d86f8dd54af425983b312b381852502 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-03-11T10:55:20Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-8d86f8dd54af425983b312b3818525022023-11-13T10:19:35ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182023-11-011710.3389/fnbot.2023.12648021264802Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classificationFederico Mereu0Federico Mereu1Federico Morosato2Francesca Cordella3Loredana Zollo4Emanuele Gruppioni5Centro Protesi Inail, Vigorso di Budrio, Bologna, ItalyUnit of Advanced Robotics and Human-Centred Technologies, Università Campus Bio-Medico di Roma, Rome, ItalyCentro Protesi Inail, Vigorso di Budrio, Bologna, ItalyUnit of Advanced Robotics and Human-Centred Technologies, Università Campus Bio-Medico di Roma, Rome, ItalyUnit of Advanced Robotics and Human-Centred Technologies, Università Campus Bio-Medico di Roma, Rome, ItalyCentro Protesi Inail, Vigorso di Budrio, Bologna, ItalyIntroductionMuscular activation sequences have been shown to be suitable time-domain features for classification of motion gestures. However, their clinical application in myoelectric prosthesis control was never investigated so far. The aim of the paper is to evaluate the robustness of these features extracted from the EMG signal in transient state, on the forearm, for classifying common hand tasks.MethodsThe signal associated to four hand gestures and the rest condition were acquired from ten healthy people and two persons with trans-radial amputation. A feature extraction algorithm allowed for encoding the EMG signals into muscular activation sequences, which were used to train four commonly used classifiers, namely Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Non-linear Logistic Regression (NLR) and Artificial Neural Network (ANN). The offline performances were assessed with the entire sample of recruited people. The online performances were assessed with the amputee subjects. Moreover, a comparison of the proposed method with approaches based on the signal envelope in the transient state and in the steady state was conducted.ResultsThe highest performance were obtained with the NLR classifier. Using the sequences, the offline classification accuracy was higher than 93% for healthy and amputee subjects and always higher than the approach with the signal envelope in transient state. As regards the comparison with the steady state, the performances obtained with the proposed method are slightly lower (<4%), but the classification occurred at least 200 ms earlier. In the online application, the motion completion rate reached up to 85% of the total classification attempts, with a motion selection time that never exceeded 218 ms.DiscussionMuscular activation sequences are suitable alternatives to the time-domain features commonly used in classification problems belonging to the sole EMG transient state and could be potentially exploited in control strategies of myoelectric prosthesis hands.https://www.frontiersin.org/articles/10.3389/fnbot.2023.1264802/fullmuscular activation sequenceonset detectionhand gesture classificationpattern recognitiontransientupper-limb amputation |
| spellingShingle | Federico Mereu Federico Mereu Federico Morosato Francesca Cordella Loredana Zollo Emanuele Gruppioni Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification Frontiers in Neurorobotics muscular activation sequence onset detection hand gesture classification pattern recognition transient upper-limb amputation |
| title | Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification |
| title_full | Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification |
| title_fullStr | Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification |
| title_full_unstemmed | Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification |
| title_short | Exploring the EMG transient: the muscular activation sequences used as novel time-domain features for hand gestures classification |
| title_sort | exploring the emg transient the muscular activation sequences used as novel time domain features for hand gestures classification |
| topic | muscular activation sequence onset detection hand gesture classification pattern recognition transient upper-limb amputation |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2023.1264802/full |
| work_keys_str_mv | AT federicomereu exploringtheemgtransientthemuscularactivationsequencesusedasnoveltimedomainfeaturesforhandgesturesclassification AT federicomereu exploringtheemgtransientthemuscularactivationsequencesusedasnoveltimedomainfeaturesforhandgesturesclassification AT federicomorosato exploringtheemgtransientthemuscularactivationsequencesusedasnoveltimedomainfeaturesforhandgesturesclassification AT francescacordella exploringtheemgtransientthemuscularactivationsequencesusedasnoveltimedomainfeaturesforhandgesturesclassification AT loredanazollo exploringtheemgtransientthemuscularactivationsequencesusedasnoveltimedomainfeaturesforhandgesturesclassification AT emanuelegruppioni exploringtheemgtransientthemuscularactivationsequencesusedasnoveltimedomainfeaturesforhandgesturesclassification |