中文摘要：

基于数据离散化方法，提出一种新的支持向量机集成算法．该算法采用粗糙集和布尔推理离散化方法构造有差异的基分类器，并引入一致度指标控制离散化过程。可进一步提高集成学习的分类性能。实验结果表明，该算法不仅具有明显优于单一支持向量机的分类性能，而且能取得比传统集成学习算法Bagging和Adaboost更高的分类正确率。

英文摘要：

Proposes a novel Support Vector Machine （SVM） ensemble algorithm based on discretization method, this algorithm uses the rough sets and boolean reasoning approach, which is controlled by the consistency level coined from the rough sets theory, to construct base classifiers with good diversity so that the performance of ensemble learning can be improved. Experimental results show that the proposed algorithm has better classification performance than single SVM. Compared with the traditional ensemble learning methods such as Bagging and Adaboost, this novel ensemble method also has better classification accuracy.