Addressing Gap between Training Data and Deployed Environment by On-Device Learning
This work addresses the gap between training data and real-world deployment for low-end edge devices, offering an incremental improvement in efficiency and robustness for battery-powered IoT applications.
The paper tackles the problem of accuracy degradation in tinyML applications due to environmental factors by proposing an on-device learning approach that retrains neural networks in deployed settings, improving anomaly detection accuracy in noisy environments and reducing communication costs and energy consumption for IoT devices.
The accuracy of tinyML applications is often affected by various environmental factors, such as noises, location/calibration of sensors, and time-related changes. This article introduces a neural network based on-device learning (ODL) approach to address this issue by retraining in deployed environments. Our approach relies on semi-supervised sequential training of multiple neural networks tailored for low-end edge devices. This article introduces its algorithm and implementation on wireless sensor nodes consisting of a Raspberry Pi Pico and low-power wireless module. Experiments using vibration patterns of rotating machines demonstrate that retraining by ODL improves anomaly detection accuracy compared with a prediction-only deep neural network in a noisy environment. The results also show that the ODL approach can save communication cost and energy consumption for battery-powered Internet of Things devices.