Pengfei Zhou
Nanyang Technological University, Singapore
Pengfei Zhou has 1 paper in the ChatPPG research atlas (2021), linked to 1 model and 4 co-authors in the atlas. Main topics: IMU, accelerometer, gyroscope, BERT, masked-reconstruction, SenSys.
Papers
- LIMU-BERT: Unleashing the Potential of Unlabeled Data for IMU Sensing Applications2021 · SenSys 2021
LIMU-BERT applies BERT-style self-supervised training to unlabelled IMU data to learn general features for mobile sensing. The authors adapted the method to the characteristics of IMU sensors and kept the models light enough for mobile devices. Tested on four open datasets, models built on LIMU-BERT features and trained with few labels clearly beat earlier approaches in two typical IMU sensing applications.
- Published: ACM SenSys 2021
- Signals: IMU (accelerometer, gyroscope)
- Method: BERT-style masked self-supervised pretraining