基于SVM的动态建模新方法

A NEW DYNAMIC MODELING METHOD BASED ON SVM

为了提高传感器系统的动态特性 ,本文提出了一种基于支持向量机 (SVM)的传感器动态建模新方法。由于支持向量机是基于统计学习理论的新一代机器学习技术 ,它有效地解决了小样本学习问题 ,因此本方法建模对实验样本数量没有特殊的要求。最后 ,仿真实验结果也证明了该动态建模方法在小样本情况下特别有效。

In order to enhance the dynamic characteristics of sensors system,a new method has been introduced for dynamic modeling of sensors using support vector machine(SVM)in this paper.Support vector machines(SVM)are a new-generation machine learning technique based on the statistica learning theory.SVM can solve small-sample learning problems better,So this method has no special demand for data number.At last a simulation expermental results is given to demonstrate that the dynamic modeling method is effective.