Next Article in Journal
Multi-Modal Joint Pulsed Eddy Current Sensor Signal Denoising Method Integrating Inductive Disturbance Mechanism
Next Article in Special Issue
Noninvasive Acoustic Recognition of Water Flow Sources for Human Activity Monitoring in Smart Homes
Previous Article in Journal
Software Trusted Platform Module (SWTPM) Resource Sharing Scheme for Embedded Systems
Previous Article in Special Issue
Human Activity Recognition Through Augmented WiFi CSI Signals by Lightweight Attention-GRU
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition

by
Kevin Di Leo
,
Giorgio Biagetti
,
Laura Falaschetti
and
Paolo Crippa
*
DII—Dipartimento di Ingegneria dell’Informazione, Università Politecnica delle Marche, Via Brecce Bianche 12, I-60131 Ancona, Italy
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(12), 3831; https://doi.org/10.3390/s25123831
Submission received: 18 April 2025 / Revised: 4 June 2025 / Accepted: 18 June 2025 / Published: 19 June 2025
(This article belongs to the Special Issue Smart Sensing Technology for Human Activity Recognition)

Abstract

Accelerometers are nowadays included in almost any portable or mobile device, including smartphones, smartwatches, wrist-bands, and even smart rings. The data collected from them is therefore an ideal candidate to tackle human motion recognition, as it can easily and unobtrusively be acquired. In this work we analyze the performance of a hand-gesture classification system implemented using LSTM neural networks on a resource-constrained microcontroller platform, which required trade-offs between network accuracy and resource utilization. Using a publicly available dataset, which includes data for 20 different hand gestures recorded from 10 subjects using a wrist-worn device with a 3-axial accelerometer, we achieved nearly 90.25% accuracy while running the model on an STM32L4-series microcontroller, with an inference time of 418 ms for 4 s sequences, corresponding to an average CPU usage of about 10% for the recognition task.
Keywords: LSTM; neural networks; hand gesture recognition; STM32; microcontroller; embedded systems; accelerometer LSTM; neural networks; hand gesture recognition; STM32; microcontroller; embedded systems; accelerometer

Share and Cite

MDPI and ACS Style

Di Leo, K.; Biagetti, G.; Falaschetti, L.; Crippa, P. Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition. Sensors 2025, 25, 3831. https://doi.org/10.3390/s25123831

AMA Style

Di Leo K, Biagetti G, Falaschetti L, Crippa P. Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition. Sensors. 2025; 25(12):3831. https://doi.org/10.3390/s25123831

Chicago/Turabian Style

Di Leo, Kevin, Giorgio Biagetti, Laura Falaschetti, and Paolo Crippa. 2025. "Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition" Sensors 25, no. 12: 3831. https://doi.org/10.3390/s25123831

APA Style

Di Leo, K., Biagetti, G., Falaschetti, L., & Crippa, P. (2025). Microcontroller Implementation of LSTM Neural Networks for Dynamic Hand Gesture Recognition. Sensors, 25(12), 3831. https://doi.org/10.3390/s25123831

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop