TinyML for Acoustic Anomaly Detection in IoT Sensor Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Almaini, Amar, Folz, Jakob, Ashour, Ghadeer
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918412706381824
author Almaini, Amar
Folz, Jakob
Ashour, Ghadeer
author_facet Almaini, Amar
Folz, Jakob
Ashour, Ghadeer
contents Tiny Machine Learning enables real-time, energy-efficient data processing directly on microcontrollers, making it ideal for Internet of Things sensor networks. This paper presents a compact TinyML pipeline for detecting anomalies in environmental sound within IoT sensor networks. Acoustic monitoring in IoT systems can enhance safety and context awareness, yet cloud-based processing introduces challenges related to latency, power usage, and privacy. Our pipeline addresses these issues by extracting Mel Frequency Cepstral Coefficients from sound signals and training a lightweight neural network classifier optimized for deployment on edge devices. The model was trained and evaluated using the UrbanSound8K dataset, achieving a test accuracy of 91% and balanced F1-scores of 0.91 across both normal and anomalous sound classes. These results demonstrate the feasibility and reliability of embedded acoustic anomaly detection for scalable and responsive IoT deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26135
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TinyML for Acoustic Anomaly Detection in IoT Sensor Networks
Almaini, Amar
Folz, Jakob
Ashour, Ghadeer
Machine Learning
Tiny Machine Learning enables real-time, energy-efficient data processing directly on microcontrollers, making it ideal for Internet of Things sensor networks. This paper presents a compact TinyML pipeline for detecting anomalies in environmental sound within IoT sensor networks. Acoustic monitoring in IoT systems can enhance safety and context awareness, yet cloud-based processing introduces challenges related to latency, power usage, and privacy. Our pipeline addresses these issues by extracting Mel Frequency Cepstral Coefficients from sound signals and training a lightweight neural network classifier optimized for deployment on edge devices. The model was trained and evaluated using the UrbanSound8K dataset, achieving a test accuracy of 91% and balanced F1-scores of 0.91 across both normal and anomalous sound classes. These results demonstrate the feasibility and reliability of embedded acoustic anomaly detection for scalable and responsive IoT deployments.
title TinyML for Acoustic Anomaly Detection in IoT Sensor Networks
topic Machine Learning
url https://arxiv.org/abs/2603.26135