Human Motion Recognition of Knitted Flexible Sensor in Walking Cycle

Abstract

Knitted fabric sensors have been widely used as strain sensors in the sports health field and its large strain performance and structure are suitable for human body movements. When a knitted structure is worn, different human body movements are reflected through the large strain deformation of fabric structure and consequently change the electrical signal. Here, the mechanical and electrical properties of highly elastic knitted sweatpants were tested under large strain. This sensor has good sensitivity and stability during movement. Compared with traditional motion monitoring, this technique divides the walking cycle into two stages, namely, stance and swing phases, which can be further subdivided into six stages. The corresponding resistance characteristic values can accurately distinguish the gait cycle. Analysis on hysteresis and repeatability revealed that the sensor exhibits a constant electrical performance. Four kinds of motion postures were predicted and judged by comparing the resistance characteristic range value, peak value calculation function and time axis. The measured sensor outputs were transferred to a computer via 4.0 Bluetooth. Matlab language was used to detect the status through a rule-based algorithm and the sensor outputs.