摘要
精确的儿童成年身高预测对于制定儿童青少年的发展计划、运动员的选材具有重要的参考意义。目前的儿童成年身高预测方法存在方法过时、预测精度不高等问题。针对这些问题,通过分析中国儿童青少年学生体质和生长发育健康工程在浙江省中小学采集的数据,在BP神经网络的基础上提出一种高精度的儿童成年身高预测方法。针对BP神经网络易陷入局部解的缺陷,提出一种基于位置策略的蚁狮算法并对其进行优化。该算法改进了蚂蚁的游走方式,增强了全局搜索能力。通过10个基准函数的对比实验,证明了位置策略的可行性和有效性。实验结果表明:优化后的BP神经网络模型真实值和预测值的差值在±2 cm以内时,男生成年身高预测精确度达到了86.67%,女生达到了85.32%,相较于其他模型而言,该模型对儿童青少年成年身高预测的结果具有更高的精度。
Precise prediction of children's adult height has important reference significance for the development of children and adolescents and the selection of athletes.The current methods for predicting children's adult height have problems such as outdated methods and low accuracy.In response to these problems,this article analyzes the data collected by the Chinese children and adolescents physical fitness and growth and development health project in Zhejiang's primary and secondary schools,a high-precision method for children's adult height prediction is proposed based on the BP neural network.Aiming at the defect that BP neural network is easy to fall into local solution,an Antlion algorithm based on location strategy is proposed to optimize it.The algorithm improves the way ants walk and enhances the global search ability of the algorithm.Through the comparative experiment of 10 benchmark functions,the feasibility and effectiveness of the location strategy are proved.The experimental results show that the accuracy of the optimized BP neural network model when the difference between the true value and the predicted value is within±2 cm,the accuracy of boys reaches 86.67%,and that of girls reaches 85.32%.Compared with other models,this model has higher accuracy in predicting the height of children and adolescents.
作者
毛科技
华子雯
张拓
陈立建
赵小敏
李博
MAO Keji;HUA Ziwen;ZHANG Tuo;CHEN Lijian;ZHAO Xiaomin;LI Bo(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China;Affiliated Zhejiang Hospital Zhejiang University,School of Medicine,Hangzhou 310023,China)
出处
《浙江工业大学学报》
CAS
北大核心
2022年第1期34-43,共10页
Journal of Zhejiang University of Technology
基金
国家自然科学基金资助项目(62072410)
浙江省重点研发项目(2018C01082)
浙江省公益性技术应用研究资助项目(LGG22F020014,LGG20F020018,2017C31027)
东南数字经济发展研究院资助项目(KYY-HX-20200417)。
关键词
儿童成年身高预测
预测模型
蚁狮算法
BP神经网络
children's adult height prediction
prediction model
Antlion algorithm
BP neural network