A wearable three-axis force sensor based on deep learning technology for plantar measurement

Abstract

A challenge in the measurement of plantar shear stress measurement is the absence of wearable and comfortable monitoring devices. In this paper, a wearable three-axis force sensor based on end-to-end deep learning technology is developed for plantar shear stress monitoring. The sensor can convert the three-axis stress it experiences into image signals through the deformation of the pattern layer embedded in the elastomeric probe. These images and three-axis stresses are fed into a convolution neural network for training, establishing a mapping relationship between images and three-axis forces. The prepared sensor has the advantages of small size (1.62 cm3), light weight (1.68 g), and flexibility, which make it possible to form a sensor array in the shoe without affecting the comfort of the wearer. By synchronizing with an action camera, the sensor array can provide real-time three-axis stress in different plantar regions for each frame of motions such as walking, running, playing football or basketball. This work contributes to the advancement of gait analysis, the clinical diagnosis of foot diseases, and the evaluation of athletic training.