1. Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing
- Author
-
Benatti, Simone, Montagna, Fabio, Kartsch, Victor, Rahimi, Abbas, Rossi, Davide, Benini, Luca, Benatti S., Montagna F., Kartsch V., Rahimi A., Rossi D., and Benini L.
- Subjects
Human-Machine Interface ,Automated ,hyperdimensional computing ,Computer science ,Embedded systems ,Biomedical Engineering ,Wearable computer ,02 engineering and technology ,Pattern Recognition ,Pattern Recognition, Automated ,Wearable Electronic Devices ,PULP platform ,Computer-Assisted ,0202 electrical engineering, electronic engineering, information engineering ,Humans ,Electrical and Electronic Engineering ,Hidden Markov model ,Embedded system ,HMI ,Gestures ,Electromyography ,gesture recognition ,020208 electrical & electronic engineering ,Signal Processing, Computer-Assisted ,Electromyography (EMG) ,Online learning ,Support vector machine ,Computer architecture ,Gesture recognition ,Scalability ,Personal computer ,Pattern recognition (psychology) ,Signal Processing ,Algorithms ,Gesture - Abstract
This work presents a wearable EMG gesture recognition system based on the hyperdimensional (HD) computing paradigm, running on a programmable Parallel Ultra-Low-Power (PULP) platform. The processing chain includes efficient on-chip training, which leads to a fully embedded implementation with no need to perform any offline training on a personal computer. The proposed solution has been tested on 10 subjects in a typical gesture recognition scenario achieving 85% average accuracy on 11 gestures recognition, which is aligned with the State-Of-the-Art (SoA), with the unique capability of performing online learning. Furthermore, by virtue of the Hardware (HW) friendly algorithm and of the efficient PULP System-on-Chip (SoC) (Mr. Wolf) used for prototyping and evaluation, the energy budget required to run the learning part with 11 gestures is 10.04mJ, and 83.2uJ per classification. The system works with a average power consumption of 10.4mW in classification, ensuring around 29h of autonomy with a 100mAh battery. Finally, the scalability of the system is explored by increasing the number of channels (up-to 256 electrodes), demonstrating the suitability of our approach as universal, energy-efficient biopotential wearable recognition framework., IEEE Transactions on Biomedical Circuits and Systems, 13 (3), ISSN:1932-4545, ISSN:1940-9990
- Published
- 2019