摘要
由于类别较多或者特征单一等原因,传统的支持向量机方法对一些复杂问题的分类,很难获得好的识别效果。首先使用一种树状结构将概率支持向量机推广到多分类问题;然后提出一种自适应权值的多特征融合方法,根据概率输出自动调整不同分类器的相关权值,将所有分类器的结果进行加权得到最终的判决结果。为解决实际应用中常出现的非平衡问题,提出综合权值方法,将类别权值与特征权值进行综合。实验结果表明,融合方法较之传统的支持向量机一对一方法以及概率支持向量机方法能够获得更高的识别率;对于非平衡问题,综合权值方法可以得到更加合理的识别结果。
Because the number of classes is large or the feature is simple, the conventional support vector machine (SVM) cannot achieve a good recognition performance for some complex classification problems. First- ly, the SVM method is extended to the multi-class problems by using a tree structure. Then, an adaptive weighted feature fusion method is introduced. The weights of the different classifiers are automatically adjusted according to the probabillstic output and are used to calculate the final result. To solve the unbalance problem in the real applications, a compositive weights method which integrates the classes weights and the character weights is proposed. Simulation experiments show that the proposed method can achieve a higher recognition rate compared with the conventional SVM and probabilistie SVM (PSVM) and the compositive weights method can achieve a more logical result for the unbalance problems.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2013年第6期1133-1137,共5页
Systems Engineering and Electronics
基金
国家自然科学基金(61203137)资助课题
关键词
模式识别
特征融合
概率支持向量机
自适应权值
pattern recognition
feature fusion
probabilistie support vector machine
adaptive weight