Data with missing values,or incomplete information,brings some challenges to the development of classification,as the incompleteness may significantly affect the performance of classifiers.In this paper,we handle missing values in both training and test sets with uncertainty and imprecision reasoning by proposing a new belief combination of classifier(BCC)method based on the evidence theory.The proposed BCC method aims to improve the classification performance of incomplete data by characterizing the uncertainty and imprecision brought by incompleteness.In BCC,different attributes are regarded as independent sources,and the collection of each attribute is considered as a subset.Then,multiple classifiers are trained with each subset independently and allow each observed attribute to provide a sub-classification result for the query pattern.Finally,these sub-classification results with different weights(discounting factors)are used to provide supplementary information to jointly determine the final classes of query patterns.The weights consist of two aspects:global and local.The global weight calculated by an optimization function is employed to represent the reliability of each classifier,and the local weight obtained by mining attribute distribution characteristics is used to quantify the importance of observed attributes to the pattern classification.Abundant comparative experiments including seven methods on twelve datasets are executed,demonstrating the out-performance of BCC over all baseline methods in terms of accuracy,precision,recall,F1 measure,with pertinent computational costs.

Zuowei Zhang;Songtao Ye;Yiru Zhang;Weiping Ding;Hao Wang

Research Center for Optical Fiber Sensing,Zhejiang Laboratory,Hangzhou 310000;School of Automation,Northwestern Polytechnical University,Xi'an 710072,China;Research Center for Optical Fiber Sensing,Zhejiang Laboratory,Hangzhou 310000,China;School of Cyber Engineering,Xidian University,Xi'an 710000,China;Department of Computer Science,CY Cergy Paris Université,2 Av.Adolphe Chauvin,95302 Cedex,France;School of Information Science and Technology,Nantong University,Nantong 226019,China;School with of Cyber Engineering,Xidian University,Xi'an 710000,China;Department of Computer Science,Norwegian University of Science and Technology,Trondheim 7491,Norway

自动化学报（英文版）

[1]Zuowei Zhang;Songtao Ye;Yiru Zhang;Weiping Ding;Hao Wang-.Belief Combination of Classifiers for Incomplete Data)[J].自动化学报（英文版）,2022(04):652-667

discounting

Belief,Combination,Classifiers,Incomplete,Data,missing,values,information,brings,some,challenges,development,classification,incompleteness,may,significantly,affect,performance,classifiers,this,paper,handle,both,training,test,uncertainty,imprecision,reasoning,by,proposing,new,belief,combination,BCC,evidence,theory,proposed,aims,improve,characterizing,brought,different,attributes,are,regarded,sources,collection,each,considered,subset,Then,multiple,trained,independently,allow,observed,provide,query,Finally,these,results,weights,factors,used,supplementary,jointly,determine,final,classes,patterns,consist,two,aspects,global,local,calculated,optimization,function,employed,represent,reliability,obtained,mining,distribution,characteristics,quantify,importance,Abundant,comparative,experiments,including,seven,methods,twelve,datasets,executed,demonstrating,out,over,baseline,terms,accuracy,recall,measure,pertinent,computational,costs

0.542529