| 基于类边界壳向量的快速SVM增量学习算法 |
| |
| 引用本文： | 吴崇明,王晓丹,白冬婴,张宏达.基于类边界壳向量的快速SVM增量学习算法[J].计算机工程与应用,2010,46(23):185-187. |
| |
| 作者姓名： | 吴崇明 王晓丹 白冬婴 张宏达 |
| |
| 作者单位： | 空军工程大学,导弹学院,计算机工程系,陕西,三原,713800 |
| |
| 基金项目： | 国家自然科学基金，陕西省自然科学研究计划 |
| |
| 摘 要： | 为进一步提高SVM增量训练的速度，在有效保留含有重要分类信息的历史样本的基础上，对当前增量训练样本集进行了约简，提出了一种基于类边界壳向量的快速SVM增量学习算法，定义了类边界壳向量。算法中增量训练样本集由壳向量集和新增样本集构成，在每一次增量训练过程中，首先从几何角度出发求出当前训练样本集的壳向量，然后利用中心距离比值法选择出类边界壳向量后进行增量SVM训练。分别使用人工数据集和UCI标准数据库中的数据进行了实验，结果表明了方法的有效性。
|
| 关 键 词： | 支持向量机 增量学习 壳向量 |
| 收稿时间： | 2009-1-20 |
| 修稿时间： | 2009-3-30
|
Fast SVM incremental learning algorithm based on between-class convex hull vectors |
| |
| WU Chong-ming,WANG Xiao-dan,BAI Dong-ying,ZHANG Hong-da.Fast SVM incremental learning algorithm based on between-class convex hull vectors[J].Computer Engineering and Applications,2010,46(23):185-187. |
| |
| Authors: | WU Chong-ming WANG Xiao-dan BAI Dong-ying ZHANG Hong-da |
| |
| Affiliation: | Department of Computer Engineering,Missile Institute,Air Force Engineering University,Sanyuan,Shaanxi 713800,China |
| |
| Abstract: | To reduce the computational cost of the incremental learning,a fast Support Vector Machine（SVM） incremental learning algorithm is proposed,and the definition of the between-class convex hull vector is given.The given algorithm is based on utilizing the result of the previous training effectively and retaining the most important samples for the incremental learning to reduce the computational cost.In the process of incremental learning,the convex hull vectors of the previous training and the newly added samples constitute the current training sample set,the current training sample set is pre-extracted from the geometric point of view by using the convex hulls algorithm,the central distance ratio method is used to obtain the between-class convex hull vectors before the SVM incremental training.Experiments prove that the given algorithm has better classification performance. |
| |
| Keywords: | Support Vector Machine（SVM） incremental learning convex hull vector |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
