节点文献
边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究
Research on non-linear time sequence intelligent model construction and prediction of slope displacement by using support vector machine algorithm
【摘要】 介绍了人工智能领域最新的基于结构风险最小化原理的数据挖掘算法———支持向量机算法,运用Matlab语言编写了程序,采用不同的核函数对具体的边坡工程实例作了计算,并将人工神经元网络计算结果与之对比,可见无论是在学习或预测精度方面,支持向量机算法较基于经验风险最小化原理的人工神经元网络算法都有很大的优越性,可以运用于实际工程。
【Abstract】 Based on the Structural Risk Minimization principle,the latest data mining method in artificial intelligence field—support vector machine algorithm was introduced in this paper.A program was worked out in language Matlab for a slope engineering project by using different kernel function.Compared with the result obtained by using the Artificial Neural Network algorithm based on the Empirical Risk Minimization principle,the SVM algorithm is obviously superior to the ANN algorithm whatever on machine learning or prediction accuracy and it can be used to practical engineering.
【Key words】 data mining； support vector machine； regression algorithm； machine learning； displacement prediction；
- 【文献出处】 岩土工程学报 ,Chinese Jounal of Geotechnical Engineering , 编辑部邮箱 ,2004年01期
- 【分类号】TU457
- 【被引频次】111
- 【下载频次】805