期刊文献+

聚簇的分布式SVM算法优化 被引量:4

A Distributed SVM Algorithm Optimization of Clustering
下载PDF
导出
摘要 针对分层并行SVM算法采用完全随机划分方法生成的子样本集与原始样本集的分布情况存在偏差的问题,提出分布式k-means聚簇的导向随机划分方法。该方法并非将上一层的训练结果直接作为下一层的输入,而是使用k-means聚簇算法聚成下一层节点数N的不同簇,然后把每一簇样本再随机划分成N份,从每一簇中随机取出一份重新组合成下一层训练的N个子样本集,进而保证子样本集与原始样本集的分布情况具有相似性。结果表明,该方法既能有效提高学习能力,又能减少多次训练模型的抖动。 Aimed at the problems that the layered parallel SVM algorithm is to generate sub-sample sets by completely adopting the random partition method,and the distribution deviation exists in between the subsample sets and the original sample set,this paper proposes a random-oriented partition method based on distributed k-means clustering.Not that the method is used to take a layer of the training results directly as input of the next layer,but that the k-means clustering algorithm is used to cluster into the number of the next layer node clusters.Then,the paper divides each cluster samples into N parts randomly,and takes out one from each cluster reassembled into Nsub-sample sets to next layer of training to ensure the distribution of the sub-sample sets similar to original sample set.The results show that this method can not only improve learning ability effectively,but also reduce the jitter of training model.
作者 王瑞 向新 肖冰松 WANG Rui;XIANG Xin;XIAO Bingsong(Aeronautics Engineering College, Air Force Engineering University, Xi'an 710038, China)
出处 《空军工程大学学报(自然科学版)》 CSCD 北大核心 2018年第2期86-92,共7页 Journal of Air Force Engineering University(Natural Science Edition)
基金 陕西省自然科学基础研究计划(DF011000306)
关键词 支持向量机 导向随机划分 聚簇 分布式k-means 并行计算 模型抖动 support vector machine random-oriented partition clustering distributed k-means parallelcomputing model jitter
  • 相关文献

参考文献1

二级参考文献15

  • 1SHAWE-TAYLO J, CRISTIANINI N, Kernel methods for pattern analysis[M]. Cambridge: Cambridge University Press, 2004:15-25.
  • 2CAMPS-VALLS ~ SHERVASHIDZE N, BORGWARDT M K. Spatio-spectral remote sensing image classification with graph kernels[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(4): 741-745.
  • 3LIU Xiao-fang. Research on remote sensing image classification methods based on kernel theory[D]. Chengdu: University of Electronic Science and Technology of China, 2011.
  • 4FRANC V, HLAV,/~t2 V. Greedy algorithm for a training set reduction in the kernel methods[M]. Heidelberg: Springer- Verlag Berlin, 2003.
  • 5FRANC V. Optimization algorithms for kernel methods[D]. Czech: Czech Technical University, 2005.
  • 6TANGKUAMPIEN T, SUTER D. Human motion de-noising via greedy kernel principal component analysis filtering [C]//Proc of the IEEE 8th International Conference on Pattern Recognition. Piscataway, USA: IEEE, 2006.
  • 7QIN Jian-ling, LI Jun. Theory of feature extraction and samples filtration based on KPCA[C]//Proe of the 12th International Conference on Industrial Engineering and Engieering Management. Beijing: Industrial Engineering Institute of China, 2005:1577-1580.
  • 8SCH(3LKOPF B, SMOLA A, MULLER K R. Nonline~x component analysis as a kernel eigenvalue problem[J]. Neural Computation, 1998(10): 1299-1319.
  • 9BANKJ M H, SHIRAZI A A B. New kernel function for hyperspectral image classification[C]// The 2rid International Conference on Computer and Automation En~,ineerin~,. Piscatawav: IEEE Comouter Society. 2010.
  • 10CRISTIANINI N, SHAWE-TAYLOR J. An introduction to support vector machines and other kernel-based learning methods[M]. Translated by LI Guo-zheng, WANG Meng, ZENG Hua-jun. Beijing: Publishing House of Electronic Industry, 2004.

共引文献1

同被引文献27

引证文献4

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部