基于代价敏感不平衡数据流分类算法

在数据流分类学习过程中,类不平衡和概念漂移是两大挑战问题.在分析传统特征选择算法和代价敏感学习方法的基础上,将代价敏感学习算法的思想引入特征选择算法中,设计并实现了一种基于代价敏感的Relief F剪枝的数据流分类算法,不仅能删除冗余的特征,而且适应动态变化的数据流环境.与经典的算法进行分析比较,结果表明所提算法可显著提升分类效果.

Classification for Imbalanced Data Streams Based on Cost-sensitive

In the process of data stream classification,class imbalance and concept drift are two major challenges.On the basis of feature selection and cost-sensitive learning,the idea of cost-sensitive learning algorithm is introduced into the feature selection algorithm,and a cost-sensitive Relief F method is designed and implemented. The algorithm can not only delete redundant features,but also adapt to dynamic data stream environment. The classical algorithms are analyzed and compared,and the results show that the proposed algorithm can significantly improve the performance of classification.