EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enabling gesture recognition on a resource-constrained device: a TinyML approach with envelope EMG data an dreal-time testing

Mohsin Ali Shah, Masood Ahmad Arbab, Shahkaar Ahmad Khan, Ansar Ullah

Journal of Edge Computing · 19.11.2026

DOI: 10.55056/jec.1092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Edge Computing, online erschienen am 19.11.2026. Verfasst von Mohsin Ali Shah und 3 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gesture recognition from electromyography (EMG) is used to control prostheses and rehabilitation devices, but real-time classifiers must balance accuracy, latency, cost and computational load. This paper presents a tiny machine learning (TinyML) pipeline that classifies hand and arm gestures from envelope EMG on a low-cost microcontroller. Four-channel envelope EMG was recorded with a six-lead myoelectric module and an Arduino UNO from 10 healthy participants, who performed six gestures for 4 s each in two sessions. A joint accuracy-complexity search selected the window length, overlap and four time-domain features used to train an artificial neural network (ANN). On a 60/20/20 window-level training/validation/test split, the test accuracy was 98.35%. Five-fold cross-validation (97.37 ± 1.05%) indicated stable performance across data partitions, and leave-one-subject-out (LOSO) evaluation, the only subject-independent test, gave 97.22 ± 1.33%. Compared with a support vector machine (SVM), k-nearest neighbours (KNN), a decision tree and a random forest, the ANN had the lowest golden distance (GD = 0.0325). Deployed on a Raspberry Pi Pico in TensorFlow Lite format, the model uses 9.1% of flash memory and an estimated 10.6% of static random-access memory (SRAM), with a 23 ms inference time, a 254 ms total on-device cycle and a 12.9% active processing duty cycle. In a representative real-time test, with a PC relaying the EMG data to the Pico, per-gesture accuracy over 500 consecutive predictions was 95.8–99.6%. These results show that real-time envelope-EMG gesture recognition is feasible on a resource-constrained microcontroller; with validation on larger and more diverse populations, the approach may inform human-machine interfaces for prosthetics, rehabilitation and assistive devices.

Zitieren

APA

Shah, M. A., Arbab, M. A., Khan, S. A., & Ullah, A. (2026). Enabling gesture recognition on a resource-constrained device: a TinyML approach with envelope EMG data an dreal-time testing. Journal of Edge Computing. https://doi.org/10.55056/jec.1092

Vancouver

Shah MA, Arbab MA, Khan SA, Ullah A. Enabling gesture recognition on a resource-constrained device: a TinyML approach with envelope EMG data an dreal-time testing. Journal of Edge Computing. 2026. doi:10.55056/jec.1092

BibTeX
@article{Shah2026,
  author = {Shah, Mohsin Ali and Arbab, Masood Ahmad and Khan, Shahkaar Ahmad and Ullah, Ansar},
  title = {Enabling gesture recognition on a resource-constrained device: a TinyML approach with envelope EMG data an dreal-time testing},
  journal = {Journal of Edge Computing},
  year = {2026},
  doi = {10.55056/jec.1092}
}
Kostenlos starten →