计算机与数字工程2019，Vol.47Issue(6)：1283-1286,1302,5.DOI:10.3969/j.issn.1672-9722.2019.06.001
改进型极限学习机模型在粮食产量预测中的应用
Improved Extreme Learning Machine Model for Grop Yield Prediction
摘要
Abstract
To improve the accuracy and timeliness of grop yield prediction,a forecasting algorithm of grain yield based on growing extreme learning machine(GELM)is proposed,whose theoretical framework is extreme learning machine(ELM). In order to solve the problem of hidden nodes number L optimization for ELM,under the situation of L increasing,the recursive formula of output weight generalized inverse matrix is deduced. The deduced equation avoids the problem that output weight generalized in?verse matrix is calculated repeatedly under different L,which reduces ELM computation load. Then the GELM is presented. Finally the grain yield prediction flow is given. Taking 1960-2015 year grain production of China as experiment dataset,testing results show that,comparing with ELM and support vector machine(SVM),GELM prediction accuracy is higher than SVM,and is close to ELM. However,GELM time consuming is much lower than ELM and SVM.关键词
极限学习机/时间序列预测/广义逆矩阵/粮食产量/神经网络Key words
extreme learning machine/time series prediction/generalized inverse matrix/grain production/neural network分类
信息技术与安全科学引用本文复制引用
吴耀东..改进型极限学习机模型在粮食产量预测中的应用[J].计算机与数字工程,2019,47(6):1283-1286,1302,5.基金项目
新疆维吾尔自治区科技厅项目(编号:2017D01B09)资助. （编号:2017D01B09）
