Physical test scores prediction based on different neural network models
In order to more accurately reflect the physical fitness of the current students,this study builds a physical test score prediction model based on a number of different neural network models.To reduce the data set for processing.Using the BP neural network combined with the spiking neural network to build a prediction model,the ability of the model to process and analyze the data set is strengthened,and the accu-racy of the prediction is improved.Adding an attention mechanism to the long short-term memory neural network builds another predictive model,making the model pay more attention to the key information in the dataset.Through experiments,the coincidence rate of the predicted value output by the prediction model and the actual value of the study is as high as 90％or more,and the overall prediction accuracy of the mod-el is more than 95％.
万方数据
维普
