TinyML for Acoustic Anomaly Detection in IoT Sensor Networks
This work addresses latency, power usage, and privacy challenges for IoT sensor networks by enabling real-time, energy-efficient acoustic anomaly detection, though it is incremental as it applies existing methods to a specific domain.
This paper tackled the problem of detecting anomalies in environmental sound within IoT sensor networks by developing a compact TinyML pipeline, achieving a test accuracy of 91% and balanced F1-scores of 0.91 on the UrbanSound8K dataset.
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.