基于不同神经网络模型预测体测成绩  

Physical test scores prediction based on different neural network models

作　　者：刘建伟[1] 董征宇 LIU Jian-wei;DONG Zheng-yu(Heilongjiang University of traditional Chinese Medicine,Harbin 150006,China;Harbin Natural Resources and Planning Bureau,Harbin 150028,China)

机构地区：[1]黑龙江中医药大学,哈尔滨150006 [2]哈尔滨市自然资源和规划局,哈尔滨150028

出　　处：《信息技术》2024年第1期65-70,76,共7页Information Technology

基　　金：黑龙江省教育科学规划课题(GJB1421323)。

摘　　要：为更加准确地反应当前学生的身体素质情况,基于多个不同的神经网络模型构建体测成绩预测模型,为降低体测成绩中各项目数据之间的相关性,使用主成分分析法对数据集进行处理。使用BP神经网络结合脉冲神经网络构建一个预测模型,加强模型处理分析数据集的能力,提高预测的准确性。在长短期记忆神经网络中加入注意力机制构建另一个预测模型,使模型更加关注数据集中的关键信息。通过实验,预测模型输出的预测值与实际值的重合率高达90%以上,预测准确率整体在95%以上。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 accuracy 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 model is more than 95%.

关 键 词：体测成绩分析 神经网络模型 主成分分析 BP神经网络 脉冲神经网络 

分 类 号：TP37[自动化与计算机技术—计算机系统结构]