High-resolution pressure sensing insole via sensitivity-tunable fibers towards gait recognition

Real-time and accurate monitoring of abnormal gait is highly desired in preventive healthcare and medical diagnosis of neurodegenerative disorders. However, the development of wearable monitoring devices that are both comfortable to wear and capable of real-time sensing remains a significant challenge. Herein, a high-resolution gait recognition insole (GRI) composed of the sensitivity-tunable sensing fiber is proposed. The GRI is capable of both static and dynamic plantar pressure mapping with a 144-pixel sensor array pixel. We design a sensitivity-tunable sensing fiber with core-sheath structure through conductive particles concentration gradient directed migration. The sheath layer exhibits a hierarchical architecture with micro-scale pores formed by carbon black concentration gradient directed migration. This fabrication technique strategically enhances sensor sensitivity by magnifying the initial resistance values. Furthermore, the GRI system is designed to integrate with machine learning algorithms, thereby enabling the recognition of abnormal gait patterns associated with neurological disorders. The system can accurately recognize abnormal gait with an accuracy of 98.42%, showing great potential for reliable applications in healthcare monitoring, sports training, and rehabilitation engineering.