Addressing the Gap Between Training Data and Deployed Environment by On-Device Learning
- Resource Type
- Periodical
- Authors
- Sunaga, K.; Kondo, M.; Matsutani, H.
- Source
- IEEE Micro Micro, IEEE. 43(6):66-73 Jan, 2023
- Subject
- Computing and Processing
Training
Artificial intelligence
Anomaly detection
Wireless communication
Prediction algorithms
Neural networks
Internet of Things
Tiny machine learning
Microcontrollers
Machine learning
- Language
- ISSN
- 0272-1732
1937-4143
The accuracy of tiny machine learning 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 semisupervised 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 modules. 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.