一种新的基于多样性赋权证据推理的集成学习方法  

New ensemble learning method for evidential reasoning based on diversity weighting

作　　者：汤凯 李康乐 孙国文 李红宇[1] 张昳哲 贺维 Tang Kai;Li Kangle;Sun Guowen;Li Hongyu;Zhang Yizhe;He Wei(College of Computer Science&Information Engineering,Harbin Normal University,Harbin 150025,China;Dept.of Computer Science,Harbin Finance University,Harbin 150030,China;Rocket Force University of Engineering,Xi’an 710025,China)

机构地区：[1]哈尔滨师范大学计算机科学与信息工程学院,哈尔滨150025 [2]哈尔滨金融学院计算机系,哈尔滨150030 [3]中国人民解放军火箭军工程大学,西安710025

出　　处：《计算机应用研究》2023年第4期1012-1018,共7页Application Research of Computers

基　　金：中国博士后科学基金资助项目;黑龙江省自然科学基金资助项目;黑龙江省高等教育教学改革项目。

摘　　要：在集成学习中使用平均法、投票法作为结合策略无法充分利用基分类器的有效信息,且根据波动性设置基分类器的权重不精确、不恰当。以上问题会降低集成学习的效果,为了进一步提高集成学习的性能,提出将证据推理(evidence reasoning, ER)规则作为结合策略,并使用多样性赋权法设置基分类器的权重。首先,由多个深度学习模型作为基分类器、ER规则作为结合策略,构建集成学习的基本结构;然后,通过多样性度量方法计算每个基分类器相对于其他基分类器的差异性;最后,将差异性归一化实现基分类器的权重设置。通过多个图像数据集的分类实验,结果表明提出的方法较实验选取的其他方法准确率更高且更稳定,证明了该方法可以充分利用基分类器的有效信息,且多样性赋权法更精确。Using the average method and the voting method as a combination strategy can’t make full use of the effective information of the base classifiers in ensemble learning,and the weights of base classifiers set with the volatility are imprecise and inappropriate.The above problems will reduce the effect of ensemble learning.In order to further improve the performance of ensemble learning,this paper proposed an ensemble learning method,which used evidence reasoning(ER)rules as a combination strategy and used diversity empowerment method set up the weights of the base classifiers.Firstly,the model used multiple deep learning models as the base classifiers and the ER rules as the combination strategy to construct the basic structure of ensemble learning.Then,it calculated the differences of each base classifier with respect to other base classifiers by the diversity measure method.Finally,it used the results of the differences normalization of the base classifiers as the weights of the base classifiers.Through the classification experiments of multiple image datasets,the experimental results show that the proposed method is more accurate and stable than other methods,which proves that this method can make full use of the effective information of the base classifiers,and the diversity weighting method is more accurate.

关 键 词：集成学习 深度学习 证据推理理论 多样性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]