计算机科学 ›› 2009, Vol. 36 ›› Issue (9): 215-217.
• 人工智能 • 上一篇 下一篇
曾联明,吴湘滨,刘鹏
出版日期:
发布日期:
基金资助:
ZENG Lian-ming,WU Xiang-bin, LIU Peng
Online:
Published:
摘要: 对于大规模SVM训练样本数据,在分类前采用粒子群算法进行样本缩减,每一个粒子的维对应一个样本状态,通过更新粒子的速度和位置信息,调整训练样本的状态,引导粒子向分类最优的样本状态组合方向移动,去除样本中对分类不起作用的非支持向量和冗余的支持向量所对应的样本,生成新的缩减样本,进行分类训练,从而达到提高训练效率的目的。基于大规模遥感图像数据集的分类实验表明,此方法在确保不降低分类精度的前提下减少了分类时间。
关键词: 粒子群,支持向量机,训练样本,海量数据
Abstract: A PSO algorithm reduction strategy was proposed to a SVM large-scale training samples by updating the velocity and location of the particles, each particle was corresponding to the status of the training samples, the ideal status included the smallest number of sv, the new training sample has reduced some nsv which arc not effect the SVM classification, so as to reduce the size of the training data sets. A practice of the remote session image classification has proved that the strategy not only has reduced samples, but also enhanced the efficiency of the largcscale data sets training.
Key words: PSO, SVM, Training sample, Large-scale data
曾联明,吴湘滨,刘鹏. 利用粒子群算法缩减大规模数据集SVM训练样本[J]. 计算机科学, 2009, 36(9): 215-217. https://doi.org/
ZENG Lian-ming,WU Xiang-bin, LIU Peng. Sample Reduction Strategy for SVM Large-scale Training Data Set Using PSO[J]. Computer Science, 2009, 36(9): 215-217. https://doi.org/
0 / / 推荐
导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks
链接本文: https://www.jsjkx.com/CN/
https://www.jsjkx.com/CN/Y2009/V36/I9/215
Cited