Title: Study on the compensation for wrist-wearing sensor displacement based on transfer learning
Authors: Hongmei Yang; Yan Wang; YingRui Geng; Xin Wang; Hongnian Yu; Xiaoxu Wen
Addresses: School of Electric and Information, Zhongyuan University of Technology, Zhengzhou, 450007, China ' School of Electric and Information, Zhongyuan University of Technology, Zhengzhou, 450007, China ' School of Electric and Information, Zhongyuan University of Technology, Zhengzhou, 450007, China ' School of Electric and Information, Zhongyuan University of Technology, Zhengzhou, 450007, China ' School of Engineering and the Built Environment, Edinburgh Napier University, Edinburgh, EH104DH, UK ' School of Electric and Information, Zhongyuan University of Technology, Zhengzhou, 450007, China
Abstract: The loose wearing of wrist smartwatches or wristbands usually causes sensor displacement. Sensor displacement can result in the distribution changing of the sensor data and thus deteriorate the performance of human activity recognition models. This paper proposes a model-based transfer learning framework to compensate for the decline in recognition accuracy caused by the sensor displacement on the wrist. We construct two convolutional neural network (CNN) models for feature extraction in activity recognition and design three transfer scenarios to evaluate the framework. Experimental results demonstrate that the recognition accuracy distinctly drops due to the sensor displacement along a wrist. Also, our proposed CNN-based transfer learning effectively compensates for the decreased recognition accuracies and improves the models' robustness.
Keywords: wrist wearing; human activity recognition; HAR; transfer learning; 1DCNN; 2DCNN.
DOI: 10.1504/IJHFMS.2023.130160
International Journal of Human Factors Modelling and Simulation, 2023 Vol.8 No.1, pp.63 - 75
Received: 18 Aug 2022
Accepted: 01 Dec 2022
Published online: 05 Apr 2023 *