An Empirical Analysis Of The Chinese Men's Basketball Achievement Prediction In The Olympic Games Of 2008 Based On ANN

Physical education forecast refers to the predictor's prediction and deduction to all kinds of future or unknown factors in the field of physical education. Physical education forecast is not only very important to the development of physical education career, but also important to the assessment of the development trend of sports achievement. It provides scientific basis to policy-maker.How to establish a forecasting model for athletic contest achievement is an important project of tourism study. But to this day there is not a centralized normal form for which kind of mathematics model can be used. At present commonly used mathematics models are:(1)Time sequence model: often used to predict simple, stable or periodic statistics. As for the apparent rising Chinese athletic contest achievement, the prediction result may be lower than the real one.(2)Regression model: rely too much on limited variables, and many major influential factors have been excluded from the model. The model is usually in static state. It is hard to predict the future changing trend of the self-variables that set up in the competitive achievement function.(3)Gray prediction: is a linear model, however the change of the athletic contest achievement is a nonlinear dynamic process, so it is hard for the Gray model to predict the exact change of the athletic contest achievement.(4) Delphi method: it can not effectively reveal the relationship among various kinds of factors in physical education system, in which they interact and associate with each other. And can not reveal the relationship between physical education system and outside environment.ANN is an artificial nonlinear dynamic system based on the recognition of cerebra neural network theory ANN is a theoretic cerebra neural network mathematic model and an information processing system based on imitating cerebra neural net structure. Based on previous samples, it can carry on "learn by itself, and model identification. And it is proved to be a good instrument for classification and forecasting in practice application just for it is model identification ability. ANN can discriminate the relativity between training samples precisely, so it is better than traditional statistical method on forecasting function. And that, while the training sample is few and there is random error, ANN is much better than ordinary statistical models. Generally speaking, while the athletic contest achievement statistical data is for a short period time, and athletic contest achievement is disturbed by many unpredictable factors, ANN is a more superior model.The writer try to speed the science process of physical education forecast by apply the ANN.In the thesis, based on time sequence statistical data, applying three-layer BP network model, applying rolling prediction, forecast the athletic contest achievement of the Chinese Men's basketball in the 2008 Olympic Games.The processes are:(1)Training net: input the technologic and statistic number of Rocket in 2005-2006 season, and set the athletic contest achievement of the Chinese Men's basketball as ideal outputs in the 2004 Olympic Games, the 14^th Man's basketball world brocade match, the 2006 Intercontinental cup basketball match, the 15^th Man's basketball world brocade match, then make up of the sample book collection to train the net. (2)Forecast net: By the trained net ,input the technologic and statistic number of the Chinese Men's basketball in the 2004 Olympic Games, the 14^th Man's basketball world brocade match, the 2006 Intercontinental cup basketball match, the 15^th Man's basketball world brocade match, output the technologic and statistic number of the Chinese Men's basketball in the 2008 Olympic Games.In the thesis, the establishment and achievement ANN forecasting model is with the help of MATLAB. The ANN toolbox of MATLAB constructs many tool functions based on ANN theory. Prediction is easily realized and program codes are easily written by ANN toolbox.