Application of Human Pose Recognition Method Based on Improved Artificial Neural Network in Human-machine Interactive Medical Devices
In order to improve the monitoring effect of human-computer interactive medical equipment on human body under the conditions of being sedentary and bedridden all the year round,wireless body area network(WBAN)is used to establish a human body posture recognition system,based on this,an improved artificial neural network is designed to fuse with the WBAN system,which is applied to the human-computer interactive medical equipment.The results show that in the HiEve dataset,the method starts to converge at 20 iterations,and the Loss function value is 0.011 2.In recognition verification on the different postures of patients,the human-machine interaction medical device recognition accuracy of this method is significantly higher than 90％,and the shortest time is only 23.16 s.It has high recognition accuracy and efficiency,providing a more reliable technical reference for the human pos-ture recognition and related medical device applications.
Improving artificial neural networksCNNwireless body area networkhuman pose recognitionhuman-computer interactionmedical equipment
万方数据
