A Sensor-Based TinyML Acoustic Monitoring System for Edge-Side Animal Sound Recognition on Resource-Constrained Microcontrollers
Sensors · 23.06.2026 · 26 (13) · 3972
DOI: 10.3390/s26133972 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 23.06.2026. Verfasst von Zhiqing Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Intelligent Science and Engineering, Qinghai Minzu University, Xining 810007, China. Hauptthemen laut MEDLINE: Acoustics, Machine Learning, Sound. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Qinghai Minzu University Key Scientific Research Project in Science and Engineering.
Abstract (Originalsprache)
Edge-side acoustic monitoring enables animal sound recognition in remote environments, but microcontroller deployment remains constrained by feature extraction, numerical consistency, memory, latency, and energy consumption. This study presents a sensor-based tiny machine learning (TinyML) acoustic monitoring system on an Arduino Nano 33 BLE Sense Rev2 platform, integrating onboard pulse-density modulation (PDM) microphone acquisition, Mel-frequency cepstral coefficient (MFCC) feature extraction, deployment-side standardization, 8-bit integer (INT8) neural-network inference, and edge-side decision output. To reduce training-to-deployment feature drift, consistent frame parameters, mirrored C++ feature operators, and exported standardization parameters are used to align personal-computer-side and microcontroller-side feature representations. A source-isolated seven-class protocol was constructed for six target animal classes and one compound background-noise class. In the single-run baseline comparison, the proposed multilayer perceptron achieved 98.28% test accuracy and 97.21% test macro-F1, while the ten-seed stability analysis yielded 98.64% ± 0.26% test accuracy and 97.87% ± 0.38% test macro-F1. The deployed INT8 model occupied approximately 26.9 KB, with a post-window latency of about 303 ms. System-level input power was 0.783–0.825 W, corresponding to an estimated autonomy of 7.63–8.03 h under the reference battery setting.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Intelligent Science and Engineering, Qinghai Minzu University, Xining 810007, China.
ORCID-Profile: Zhiqing Wang, Guicai Yu
Förderung
- National Natural Science Foundation of China
- Qinghai Minzu University Key Scientific Research Project in Science and Engineering
Zitieren
APA
Wang, Z., & Yu, G. (2026). A Sensor-Based TinyML Acoustic Monitoring System for Edge-Side Animal Sound Recognition on Resource-Constrained Microcontrollers. Sensors, 26(13), 3972. https://doi.org/10.3390/s26133972
Vancouver
Wang Z, Yu G. A Sensor-Based TinyML Acoustic Monitoring System for Edge-Side Animal Sound Recognition on Resource-Constrained Microcontrollers. Sensors. 2026;26(13):3972. doi:10.3390/s26133972
BibTeX
@article{Wang2026,
author = {Wang, Zhiqing and Yu, Guicai},
title = {A Sensor-Based TinyML Acoustic Monitoring System for Edge-Side Animal Sound Recognition on Resource-Constrained Microcontrollers},
journal = {Sensors},
year = {2026},
volume = {26},
number = {13},
pages = {3972},
doi = {10.3390/s26133972}
}
EUVIMED