Application of An Improved Particle Swarm Optimization Neural Network Model in the Prediction of Physical Education in China

• Published in: Chemical engineering transactions Vol. 46
• Main Authors: L.G. Tian, P.J. Zhang, S. Zang
• Format: Journal Article
• Language: English
• Published: AIDIC Servizi S.r.l 01.12.2015
• ISSN: 2283-9216
• DOI: 10.3303/CET1546080

With the scientific development of the sports industry, as a kind of important quantitative analysis method, the prediction in the field of physical is bound to be paid more and more attention. People's requirements on the accuracy of the data will be more and more high. From the athletes' selection to the athletes' performance prediction, it depends on the statistics of a large number of historical data. As a result, the development of modern mathematics and computer technology is widely used in the field of physical education, such as grey theory, fuzzy mathematics, and neural network and so on. Grey forecasting model is suitable for analysing the nonlinear and uncertain system. But this method usually has a large prediction error. Artificial neural network has a strong self-learning function, so it can train the predictable data. However, it requires a large sample data set. Therefore, this paper tries to use the particle swarm optimization algorithm to optimize the parameters of neural network, and uses a discrete method to improve the neural network, so as to achieve the purpose of accurate prediction. The experimental results show that the fitting residuals of the neural network algorithm are small, and the prediction accuracy is high.