一种基于小波变换特征提取的集成学习算法

An Ensemble Learning Algorithm Based on the Feature Extraction by Wavelet Transform

将不同训练数据子集和不同特征子集相结合,提出了一种基于小波变换特征提取的集成学习算法Wavelet-Forests.先随机划分特征集,用小波变换提取特征子集的特征,再用小波系数重构特征集训练基分类器.使用公认的WEKA平台验证了Wavelet-Forests算法的性能,与经典算法Bagging,AdaBoost和Random Forest相比,本文所提算法具有良好的泛化能力.

To combine different subsets of training data and different feature subset, a new ensemble learning algorithm is put forward based on the feature extraction by wavelet transform. To create the training data for a base classifier, the feature set is randomly split into n subsets and wavelet is applied to each subset. The com- mon platform WEKA has been used to validate the performance of Wavelet-Forests algorithm. The algorithm is superior to the classical algorithm Bagging, AdaBoost and Random Forest in comparison, and has good generali- zation ability.