Human-machine interaction is gaining traction in rehabilitation tasks, such as controlling prosthetic hands or robotic arms. Gesture recognition exploiting surface electromyographic (sEMG) signals is one of the most promising approaches, given that sEMG signal acquisition is non-invasive and is directly related to muscle contraction. However, the analysis of these signals still presents many challenges since similar gestures result in similar muscle contractions. Thus the resulting signal shapes are almost identical, leading to low classification accuracy. To tackle this challenge, complex neural networks are employed, which require large memory footprints, consume relatively high energy and limit the maximum battery life of devices used for classification. This work addresses this problem with the introduction of the Bioformers. This new family of ultra-small attention-based architectures approaches state-of-the-art performance while reducing the number of parameters and operations of 4.9 ×. Additionally, by introducing a new inter-subjects pre-training, we improve the accuracy of our best Bioformer by 3.39 %, matching state-of-the-art accuracy without any additional inference cost. Deploying our best performing Bioformer on a Parallel, Ultra-Low Power (PULP) microcontroller unit (MCU), the GreenWaves GAP8, we achieve an inference latency and energy of 2.72 ms and 0.14 mJ, respectively, 8.0× lower than the previous state-of-the-art neural network, while occupying just 94.2 kB of memory.
Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition / Burrello, A.; Bianco Morghet, F.; Scherer, M.; Benatti, S.; Benini, L.; Macii, E.; Poncino, M.; Jahier Pagliari, D.. - ELETTRONICO. - (2022), pp. 1443-1448. (Intervento presentato al convegno 2022 Design, Automation and Test in Europe Conference and Exhibition, DATE 2022 tenutosi a Antwerp, Belgium nel 2022) [10.23919/DATE54114.2022.9774639].
Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition
Burrello A.;Bianco Morghet F.;MacIi E.;Poncino M.;Jahier Pagliari D.
2022
Abstract
Human-machine interaction is gaining traction in rehabilitation tasks, such as controlling prosthetic hands or robotic arms. Gesture recognition exploiting surface electromyographic (sEMG) signals is one of the most promising approaches, given that sEMG signal acquisition is non-invasive and is directly related to muscle contraction. However, the analysis of these signals still presents many challenges since similar gestures result in similar muscle contractions. Thus the resulting signal shapes are almost identical, leading to low classification accuracy. To tackle this challenge, complex neural networks are employed, which require large memory footprints, consume relatively high energy and limit the maximum battery life of devices used for classification. This work addresses this problem with the introduction of the Bioformers. This new family of ultra-small attention-based architectures approaches state-of-the-art performance while reducing the number of parameters and operations of 4.9 ×. Additionally, by introducing a new inter-subjects pre-training, we improve the accuracy of our best Bioformer by 3.39 %, matching state-of-the-art accuracy without any additional inference cost. Deploying our best performing Bioformer on a Parallel, Ultra-Low Power (PULP) microcontroller unit (MCU), the GreenWaves GAP8, we achieve an inference latency and energy of 2.72 ms and 0.14 mJ, respectively, 8.0× lower than the previous state-of-the-art neural network, while occupying just 94.2 kB of memory.File | Dimensione | Formato | |
---|---|---|---|
DATE22___Bioformer.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
373.39 kB
Formato
Adobe PDF
|
373.39 kB | Adobe PDF | Visualizza/Apri |
Burrello_et_al_2022_Bioformers.pdf
accesso riservato
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
451.27 kB
Formato
Adobe PDF
|
451.27 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2974503