This paper introduces a stretchable iontronic pressure sensor (SIPS) with an ultrabroad linear range and high sensitivity for biophysical monitoring and deep learning-aided knee rehabilitation. The sensor, optimized in structure and material composition, exhibits high sensitivity (12.43 kPa⁻¹), an ultrabroad linear sensing range (1 MPa), high pressure resolution (6.4 Pa), and excellent stretchability (up to 20%). Its durability is demonstrated through 12000 cycles with no decay. The SIPS accurately tracks biophysical signals (pulse waves, muscle movements, plantar pressure) and, combined with a neuro-inspired fully convolutional network (FCN), precisely predicts knee joint postures for post-surgical rehabilitation. The high signal-to-noise ratio and ultrabroad linear range make it promising for wearable electronics and AI medical engineering.

Hongcheng Xu, Libo Gao, Haitao Zhao, Hanlin Huang, Yuejiao Wang, Gang Chen, Yuxin Qin, Ningjuan Zhao, Dandan Xu, Ling Duan, Xuan Li, Siyu Li, Zhongbao Luo, Weidong Wang, Yang Lu