基于RBF核函数的集成分类AdaBoost算法研究

Research on AdaBoost Integrated Classification Algorithm Based on RBF Kernel Function

基于径向基函数的神经网络、支持向量机已被广泛应用于模式分类。为了进一步提高分类的精度,将径向基函数应用于集成的AdaBoost算法,即以RBF神经网络和以RBF核函数的支持向量机分别作为AdaBoost的弱分类器,集成更高精度的强分类。通过对标准数据集的分类实验性能对比,证明了其算法解决分类问题有效性。

Both neural network and SVM （Support Vector Machine） based on RBF have already been widely used in pattern classification. In order to further improve the classification accuracy, RBF function is applied to in- tegrated AdaBoost, namely, RBF neural network and SVM with RBF kernel function are applied as to AdaBoost respectively. Thus it will integrate a higher accuracy strong classifier. By performance classification experiment for standard data set, it proved the algorithm effectiveness in classification.