论文部分内容阅读
随着现实生活中数据集规模的不断增大,设计有效的分类算法势在必行。支持向量机(Support vector machine,SVM)是一种公认的性能较好的分类算法,目前一些SVM算法是针对减少支持向量的数目来提高分类的效率。文章提出一种基于混合度的层次粒度支持向量机算法(Hierarchical Granular Support Vector Machine Algorithm based on Mixed,MHG-SVM),利用混合度对已有的层次粒度SVM分类算法进行了改进,该算法通过定义一个数据置信度和一个粒度参数挑选出重要的分类信息。从实验结果可以看出,提出的算法在处理大规模数据集方面,保持了较高的分类精度,而且支持向量机的学习和分类速度也取得了大幅度提高。
With the increasing size of data sets in real life, it is imperative to design an effective classification algorithm. Support vector machine (SVM) is a recognized classification algorithm with better performance. At present, some SVM algorithms aim at reducing the number of support vectors to improve classification efficiency. In this paper, we propose an improved Hierarchical Granular Support Vector Machine (SVM) algorithm based on mixed algorithm (MHG-SVM), which improves the existing hierarchical granular SVM classification algorithm by means of the degree of blending A data confidence and a granularity parameter pick out important classification information. It can be seen from the experimental results that the proposed algorithm maintains high classification accuracy in dealing with large-scale data sets, and the speed of SVM learning and classification has also been greatly improved.