Journal of Computer Applications ›› 2005, Vol. 25 ›› Issue (01): 25-27.DOI: 10.3724/SP.J.1087.2005.00025
• Data mining • Previous Articles Next Articles
ZHAO Zheng1, WANG Hong-mei1, ZHAO Yi-su2, ZHENG Jian-hua1
Online:
Published:
赵政1,王红梅1,赵怿甦2,郑建华1
Abstract: Support vector machine is a new classification algorithm based on statistical learning theory. After the discussion of the current multiclass SVMs, a novel multiclass SVM classifier based on geometric distance was proposed. The Posterior probability output of binary SVM was generalized to multiclass SVM. Without iteration computing, this method improved prediction accuracy with fast computing. The numeric experiments prove that above two methods have good generalization, which can increase prediction accuracy to unknown examples.
Key words: Support Vector Machine(SVM), posterior probability, statistical learning theory
摘要: 支持向量机是基于统计学习理论的一种新的分类规则挖掘方法。在已有多分类支持向量机基础上,首次提出了几何距离多分类支持向量分类器;随后,将二值支持向量机的后验概率输出也推广到多分类问题,避免了使用迭代算法,在快速预测的前提下提高了预测准确率。数值实验的结果表明,这两种方法都具有很好的推广性能,能明显提高分类器对未知样本的分类准确率。
关键词: 支持向量机, 后验概率, 统计学习理论
CLC Number:
TP301.6
ZHAO Zheng, WANG Hong-mei, ZHAO Yi-su, ZHENG Jian-hua. Application of posterior probability to multiclass SVM[J]. Journal of Computer Applications, 2005, 25(01): 25-27.
赵政,王红梅,赵怿甦,郑建华. 后验概率在多分类支持向量机上的应用[J]. 计算机应用, 2005, 25(01): 25-27.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://www.joca.cn/EN/10.3724/SP.J.1087.2005.00025
http://www.joca.cn/EN/Y2005/V25/I01/25