Optimizing Human Gliding Performance Using Wearable Nano-biosensors

Mining human gliding data is beneficial for coaches and athletes to optimize gliding techniques, thereby improving gliding performance. However, due to the large variations and difficulties in collecting human gliding acceleration data, the quality of traditional data mining for human gliding has deteriorated. Therefore, a method for human gliding data mining using wearable nano-biosensors is proposed. First, the ultra-thin microbeam accelerometer in the wearable nano-biosensor is selected to collect acceleration data of gliding personnel during gliding. Second, the data is transmitted to the signal processing system through a wireless sensor network. Finally, the signal processing system uses a support vector machine mining model to classify and process human acceleration data samples, outputting the results of human gliding data mining. The results show that the proposed method can improve the accuracy of collecting human acceleration data. The average time consumption is 0.73 s, and can be applied to gliding sports training and competition analysis.