现代电子技术2017，Vol.40Issue(3)：100-102,3.DOI:10.16652/j.issn.1004-373x.2017.03.027
基于LSSVM的六价铬含量预测模型
Hexavalent chromium content prediction model based on LSSVM
摘要
Abstract
A hexavalent chromium automatic measuring system was designed to improve the measurement accuracy. The least square support vector machine(LSSVM)algorithm is used to establish the prediction model,and the shuffled frog leaping algorithm is used to optimize the parameters of LSSVM algorithm to prevent the algorithm converging to the local optimum,en?hance the generalization ability of the algorithm,reduce the algorithm′s prediction deviation for the abnormal samples,and im?prove the accuracy. The neural network model and LSSVM model are simulated respectively. The results show that the prediction error of the hexavalent chromium content predicted with LSSVM model is much smaller.关键词
支持向量机/六价铬/预测偏差/自动测量系统Key words
support vector machine/hexavalent chromium/prediction deviation/automatic measuring system分类
信息技术与安全科学引用本文复制引用
居锦武..基于LSSVM的六价铬含量预测模型[J].现代电子技术,2017,40(3):100-102,3.基金项目
四川省科技厅科技支撑计划（15ZC0195）；四川省人工智能重点实验室项目（2013RZY03）；企业信息化与物联网测控技术四川省高校重点实验室基金项目（2013WZY04，2014WYY01）；泸州老窖奖学金项目 （）
