Analysis and prediction of athlete's anxiety state based on artificial intelligence

Obtaining athletes' anxiety accurately and regulating their psychological state helps improve their competitive performance. Therefore, this article uses a hierarchical clustering algorithm to identify the sources of stress of track and field athletes. A novel and efficient hierarchical clustering algorithm is proposed in this article. The algorithm consists of two stages: dividing and agglomerating. In the dividing stage, the initial data set is taken as a class and subclasses more than the actual number of clusters are obtained through multiple dividing. In the agglomerating phase, the subclasses divided during the dividing process are merged into the correct class. In addition, we construct an analysis model of athletes' anxiety state based on the radial basis function (RBF) model, where athletes' anxiety is divided into three categories: physical condition anxiety, competition state and cognitive state. The proposed model is trained from the official website of the China Track and Field Association. The athletes' information from 500 samples was arranged to form the sample database of athletes' data. The implicit unit center, function width and connection weight record the characteristics of various sports anxiety states. Then we used the Bayesian and Lagrange models as comparative models for evaluating the psychological state. Precision and efficiency were used for evaluation indexes. The proposed model's results are much better in accuracy and time than those of the Lagrange and Bayesian models. The outcome of the proposed research can provide a reasonable basis for the decision-making of stress relief for track and field athletes.