【摘要】 针对多分类器决策融合研究中利用有限的训练数据对分类器概率参数估计时存在较大偏差的问题,提出一种基于D-S证据推理(ER)的多分类器决策融合算法。利用不确定性描述分类器性能,并针对D-S组合规则在分类器结果高冲突情形下易出现决策融合悖论的问题,提出基于分类器信度加权融合算法实现流量识别决策融合。实验结果表明,多数投票法和Bayes最大后验概率法识别准确率分别为78.3%和81.7%,证据推理决策融合的识别准确率提高到82.2%~91.6%,而拒识率则保持在4.1%~6.2%。更多还原

【Abstract】 In multi-classifier decision fusion, there is great warp when using limited training data to estimate the probability parameters of classifier. For dealing with this problem, a multi-classifier decision fusion method based on D-S( Dempster-Shafer) Evidential Reasoning( ER) was presented. The method utilized the advantages of D-S theory to describe uncertainty of classifiers. To solve the paradox problem in high conflict circumstance among multiple classifiers, a reliability weighted fusion algorithm was proposed to realize the traffic identification decision fusion. The experimental results show that the accuracy rate of majority voting and Bayes maximum posteriori probability are 78. 3% and 81. 7% respectively, while the proposed algorithm can improve the accuracy rate up to 82. 2%- 91. 6%, and remain the reject rate between 4. 1% and6. 2%.更多还原