No abstract

With the continuous increase of the ageing population, the number of patients with chronic diseases has increased dramatically. The limited medical resources and the strong demand for high-quality medical services are in stark contradiction. Active rehabilitation training is one of the most effective rehabilitation methods, but it is difficult to achieve through traditional medical equipment. In this paper, aiming at effective clinical rehabilitation, an in-depth study was carried out on the exercise intention recognition experiment of patients, hoping to provide an effective rehabilitation treatment method for the recovery of patients with lower extremity motor function injury. This paper introduces the detection principle of the photoelectric pulse sensor and the design scheme that is used in physical education. In the experiment, through the hardware connection, programming, and the development of the host computer software, the pulse signal of the human body can be presented stably on the computer. The monitoring of the pulse of the students can help the physical education teacher to understand the situation of the students and prevent accidents. In addition, we believe that the acquisition of students’ pulse signals in physical education to build a database is of great significance for research and tracking of students’ health status and the research results will certainly promote the development of pulse diagnosis. In order to make the lower extremity exoskeleton rehabilitation system that can be applied in clinical rehabilitation, according to the Brunnstrom staging of patients with central nervous system injury, the needs of patients in different stages in the rehabilitation process were analysed and active and passive lower extremity rehabilitation strategies were formulated. Aiming at the problem of real-time and accurate identification of human motion intention, and to alleviate the mechanism motion delay caused by the delay of mechanical and control systems in the human-machine integrated system, a differential sEMG real-time feature extraction algorithm is proposed. The results show that the sensor and monitoring system have excellent stability, and the auxiliary system can accurately reflect the changing trend of the human biological pulse, achieve the expected effect, and effectively assist in the monitoring of exercise data for patients with chronic diseases. After treatment, the joint range of motion and muscle strength basically returned to normal levels, and the patient was able to walk independently. Compared with traditional treatment methods, the recovery time is shorter, the recovery of muscle strength is more effective, and the medical staff is more relaxed.