摘要
针对当前体育成绩预测方法无法全面描述体育成绩变化特点,预测误差大的缺陷,以提高体育成绩预测效果为目标,提出了基于时间序列分析法的体育成绩预测方法。选取奇异值分解滤波算法将原始数据序列分解为随机成分和趋势成分两部分;利用GM(1,1)模型和PSO-RBFNN模型分别对随机成分和趋势成分进行预测;结合2个模型预测结果进行融合得到最终体育成绩预测结果,并进行了具体的仿真实验。实验结果表明,提出的方法提高了体育成绩预测精度,大幅度降低了体育成绩预测误差,具有一定的实际应用价值。
The current sports performance prediction methods cannot fully describe the characteristics of sports performance prediction and have large prediction error. In order to improve the effect of sports performance prediction, this paper puts forward a sports performance prediction method based on time series analysis. The singular value decomposition algorithm is used to decompose the original data sequence into two parts: random component and trend component. The model GM(1,1) and PSO-RBFNN are used respectively to predict the random components and trend components. The prediction results of the two models are combined to get the final sports prediction. A specific simulation experiment is carried out. The experimental results show that the method improves the accuracy of sports performance prediction, greatly reduces the prediction error of sports performance, and has certain practical application value.
作者
冯其明
FENG Qiming(School of Physical Education,Sichuan University of Arts and Science,Dazhou 635000,China)
出处
《微型电脑应用》
2022年第12期35-37,48,共4页
Microcomputer Applications
基金
四川省社会科学重点研究基地(YJY2020014)
四川文理学院一流课程建设项目资助(2020KCB019)。
