Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Microbial Biosensors01:17

Microbial Biosensors

Microbial biosensors are analytical devices that utilize living microbes to detect specific substances through measurable signals. These devices consist of two main components: biosensing organisms and signal-transducing elements. Biosensing organisms, such as Escherichia coli or Saccharomyces cerevisiae, are typically housed in multiwell plates connected to transducers, enabling rapid, real-time detection of target analytes.Signal Generation MechanismWhen a target analyte—such as...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Coverage Probability Analysis and Relay Placement Optimization for Two-Hop LoRa Networks with Random Traffic Activation.

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: Jul 16, 2026

Enhancing an Avian Sound Recognition Model's Detection Precision via Logistic Regression of Large Acoustic Datasets: A Case Study of the European Robin (Erithacus rubecula)
10:55

Enhancing an Avian Sound Recognition Model's Detection Precision via Logistic Regression of Large Acoustic Datasets: A Case Study of the European Robin (Erithacus rubecula)

Published on: April 11, 2026

A Sensor-Based TinyML Acoustic Monitoring System for Edge-Side Animal Sound Recognition on Resource-Constrained

Zhiqing Wang1, Guicai Yu1

  • 1School of Intelligent Science and Engineering, Qinghai Minzu University, Xining 810007, China.

Sensors (Basel, Switzerland)
|July 15, 2026
PubMed
Summary

This study introduces a TinyML acoustic monitoring system for remote animal sound recognition. The efficient edge-side system achieves high accuracy with low power consumption and memory usage, enabling long-term deployment.

Keywords:
MFCCTinyMLanimal acoustic monitoringedge artificial intelligencefeature consistencymicrocontrollersensor-based recognition

More Related Videos

Pupillometry to Assess Auditory Sensation in Guinea Pigs
09:25

Pupillometry to Assess Auditory Sensation in Guinea Pigs

Published on: January 6, 2023

Related Experiment Videos

Last Updated: Jul 16, 2026

Enhancing an Avian Sound Recognition Model's Detection Precision via Logistic Regression of Large Acoustic Datasets: A Case Study of the European Robin (Erithacus rubecula)
10:55

Enhancing an Avian Sound Recognition Model's Detection Precision via Logistic Regression of Large Acoustic Datasets: A Case Study of the European Robin (Erithacus rubecula)

Published on: April 11, 2026

Pupillometry to Assess Auditory Sensation in Guinea Pigs
09:25

Pupillometry to Assess Auditory Sensation in Guinea Pigs

Published on: January 6, 2023

Area of Science:

  • Ecology
  • Computer Science
  • Electrical Engineering

Background:

  • Edge-side acoustic monitoring is crucial for remote animal sound recognition.
  • Microcontroller deployment faces challenges in feature extraction, consistency, memory, latency, and energy.
  • Tiny Machine Learning (TinyML) offers a solution for resource-constrained edge devices.

Purpose of the Study:

  • To develop and evaluate a sensor-based TinyML acoustic monitoring system for edge deployment.
  • To address feature extraction and numerical consistency challenges in microcontroller-based systems.
  • To optimize the system for low power consumption, minimal memory footprint, and low latency.

Main Methods:

  • Implemented a TinyML system on Arduino Nano 33 BLE Sense Rev2 with onboard PDM microphone and MFCC feature extraction.
  • Utilized deployment-side standardization, INT8 neural network inference, and edge-side decision output.
  • Ensured training-to-deployment feature alignment using consistent parameters and mirrored operators.

Main Results:

  • Achieved 98.28% test accuracy and 97.21% macro-F1 in baseline comparison.
  • Stability analysis showed 98.64% ± 0.26% test accuracy and 97.87% ± 0.38% macro-F1.
  • Deployed INT8 model size: ~26.9 KB; post-window latency: ~303 ms; power: 0.783-0.825 W; estimated autonomy: 7.63-8.03 h.

Conclusions:

  • The developed TinyML system effectively enables edge-side acoustic monitoring for animal sound recognition.
  • The system demonstrates high accuracy, low latency, and energy efficiency suitable for remote, long-term deployments.
  • The methodology addresses key microcontroller constraints for practical edge AI applications in ecology.