Multifunctional Human–Computer\nInteraction\nSystem Based on Deep Learning-Assisted Strain Sensing Array

Continuous and reliable monitoring of gait is crucial\nfor health\nmonitoring, such as postoperative recovery of bone joint surgery and\nearly diagnosis of disease. However, existing gait analysis systems\noften suffer from large volumes and the requirement of special space\nfor setting motion capture systems, limiting their application in\ndaily life. Here, we develop an intelligent gait monitoring and analysis\nprediction system based on flexible piezoelectric sensors and deep\nlearning neural networks with high sensitivity (241.29 mV/N), quick\nresponse (66 ms loading, 87 ms recovery), and excellent stability\n(<i>R</i><sup>2</sup> = 0.9946). The theoretical simulations\nand experiments confirm that the sensor provides exceptional signal\nfeedback, which can easily acquire accurate gait data when fitted\nto shoe soles. By integrating high-quality gait data with a custom-built\ndeep learning model, the system can detect and infer human motion\nstates in real time (the recognition accuracy reaches 94.7%). To further\nvalidate the sensor’s application in real life, we constructed\na flexible wearable recognition system with human–computer\ninteraction interface and a simple operation process for long-term\nand continuous tracking of athletes’ gait, potentially aiding\npersonalized health management, early detection of disease, and remote\nmedical care.