Wavelet Encoding Network for Inertial Signal Enhancement via Feature Supervision
- 30 July 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (11) , 12924-12934
Abstract
Inertial sensors, as motion-sensing components, are widely used in inertial navigation, aerospace, and consumer electronics. Their wide applications and severe errors form a sharp contradiction, which attracts considerable attention. Wavelet is hailed as the mathematical signal microscope due to the diverse wavelet basis functions. However, complicated noise types and application scenarios of inertial sensors make selecting wavelet basis perplexing. To this end, we propose a wavelet encoding network (WENet), which intelligently selects the appropriate wavelet for variable inertial signals by representing wavelet characteristics through the devised category representation mechanism (CRM). Furthermore, CRM introduces a feature supervision effect, which imposes interpretability on a black-box network and forces it to provide direct supervision for other network structures. This supervision strategy is closer and more effective than the supervision provided by the output end, which is far and needs to go through backpropagation. The proposed WENet has the reliability of the model-driven method and the flexibility of the data-driven method. As a weakly supervised method, the WENet achieves the best performance among all signal improvement methods, including fully supervised ones. After being enhanced by WENet, the low-cost sensor signal can perform accurate spatial trajectory reconstruction, which was once considered an impossible task.Keywords
Funding Information
- Science Center Program of National Natural Science Foundation of China (62188101)
- Natural Science Foundation of Guangdong Province (2020A1515010812, 2021A1515011594)
- China Scholarship Council (202306120304)
This publication has 29 references indexed in Scilit:
- Handwriting Recognition Under Natural Writing Habits Based on a Low-Cost Inertial SensorIEEE Sensors Journal, 2023
- Data-driven denoising of stationary accelerometer signalsMeasurement, 2023
- Arbitrary Spatial Trajectory Reconstruction Based on a Single Inertial SensorIEEE Sensors Journal, 2023
- Multi-sensor information fusion based on machine learning for real applications in human activity recognition: State-of-the-art and research challengesInformation Fusion, 2022
- A wearable motion capture device able to detect dynamic motion of human limbsNature Communications, 2020
- Deep Learning for Fall Risk Assessment With Inertial Sensors: Utilizing Domain Knowledge in Spatio-Temporal Gait ParametersIEEE Journal of Biomedical and Health Informatics, 2019
- Proximity Human-Robot Interaction Using Pointing Gestures and a Wrist-mounted IMU2019
- Sensor Glove Based on Novel Inertial Sensor Fusion Control Algorithm for 3-D Real-Time Hand Gestures MeasurementsIEEE Transactions on Industrial Electronics, 2019
- A comparison of feature ranking techniques for fault diagnosis of ball bearingSoft Computing, 2015
- A high-resolution microchip optomechanical accelerometerNature Photonics, 2012