Construction and Application of Performance Prediction Model for Aerobics Athletes Based on Online-SVM

Aerobics has been broadly adopted in colleges and universities in our country. For aerobics can be better able to carry out, the performance prediction is very important. Aiming at the problems that the predictive model is often mismatching and difficult to solve the nonlinear optimization function of nonlinear system model of predictive control, an online support vector machine (OSVM) modeling is proposed. This proposed method builds a nonlinear model for objects using OSVM. Furthermore, we apply this method to the performance prediction of the aerobics. The results show that the online-SVM applying to the aerobics performance prediction is feasible and effective.