摘要
针对多传感器数据融合分类中,DS证据理论基本概率赋值难以解决的问题,提出了一种结合SVM与DS证据理论的信息融合改进方法。根据SVM对输入数据分类的实际情况和基于混淆矩阵得到的分类器局部识别可信度来构造基本概率赋值函数,实现了两者的有效结合,建立了SVM与DS证据相结合的多传感器信息融合模型。在决策融合过程中,重视和考虑了分类器局部识别可信度信息,并对算法进行了复杂度分析。基于UCI数据集和人工数据集的仿真结果表明该方法能够有效地降低融合识别的误差率,提高识别的可信度。
Based on the difficulty of obtaining the Basic Probability Assignment（BPA） of DS evidence theory in the practical application, an improved method of information fusion combing SVM and DS evidence theory is proposed. It uses the specific classification situation based on SVM and classifiers＇ reliabilities from confusion matrix to construct the basic probability assign- ment, which achieves the combination of SVM and the evidence theory in the information fusion. The method also presents a multi-sensor information fusion model. In the process of decision and fusion, it takes the sensors＇ local reliabilities into consider- ation and regards them as weights to integrate into BPA. The time complexity is also analyzed. The simulation results based on UCI data set and synthetic data set show that the fusion error rate can be decreased through the method proposed in this paper and the fusion reliabilities are increased.
出处
《计算机工程与应用》
CSCD
2013年第11期114-117,共4页
Computer Engineering and Applications
基金
国家自然科学基金(No.60975026)
关键词
信息融合
支持向量机
证据理论
混淆矩阵
information fusion
Support Vector Machine（ SVM）
evidence theory
confusion matrix
