Movements of the hands are among the most natural means humans use to express information. Automated recognition of hand movements is a very active research domain for developing Human-Machine Interfaces. The surface electromyographic (sEMG) signal is a versatile and accurate data source for intuitive control of machines, robots, or prostheses based on gesture classification, which is a non-trivial mapping. Algorithms for Blind Source Separation (BSS) can retrieve the sEMG's Motor Unit signals, which are the originary format of physiological information, and can be forwarded to a Machine Learning classifier. However, implementation of BSS algorithms for execution on resource-constrained hardware is still in its infancy. In this work, we propose a novel, parallelized version of the FastICA BSS method ported on the Mr. Wolf microcontroller based on PULP, achieving latency < 50ms and energy consumption < 1mJ. In an end-to-end approach, we fed the reconstructed neural signals to an SVM and an MLP classifier, obtaining accuracy >92% on 5 classes (rest and 4 gestures). These results prove that our setup is suitable for running in real-time on the limited resources of embedded hardware, while guaranteeing the same accuracy as black-box state-of-the-art solutions lacking any physiological insight.
sEMG Neural Spikes Reconstruction for Gesture Recognition on a Low-Power Multicore Processor / Orlandi, M.; Zanghieri, M.; Morinigo, V. J. K.; Conti, F.; Schiavone, D.; Benini, L.; Benatti, S.. - pp:(2022), pp. 704-708. (Intervento presentato al convegno 2022 IEEE Biomedical Circuits and Systems Conference, BioCAS 2022 tenutosi a Chang Yung-Fa Foundation International Convention Center (CYFF), twn nel 2022) [10.1109/BioCAS54905.2022.9948617].
sEMG Neural Spikes Reconstruction for Gesture Recognition on a Low-Power Multicore Processor
Benatti S.
2022
Abstract
Movements of the hands are among the most natural means humans use to express information. Automated recognition of hand movements is a very active research domain for developing Human-Machine Interfaces. The surface electromyographic (sEMG) signal is a versatile and accurate data source for intuitive control of machines, robots, or prostheses based on gesture classification, which is a non-trivial mapping. Algorithms for Blind Source Separation (BSS) can retrieve the sEMG's Motor Unit signals, which are the originary format of physiological information, and can be forwarded to a Machine Learning classifier. However, implementation of BSS algorithms for execution on resource-constrained hardware is still in its infancy. In this work, we propose a novel, parallelized version of the FastICA BSS method ported on the Mr. Wolf microcontroller based on PULP, achieving latency < 50ms and energy consumption < 1mJ. In an end-to-end approach, we fed the reconstructed neural signals to an SVM and an MLP classifier, obtaining accuracy >92% on 5 classes (rest and 4 gestures). These results prove that our setup is suitable for running in real-time on the limited resources of embedded hardware, while guaranteeing the same accuracy as black-box state-of-the-art solutions lacking any physiological insight.Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris