证据理论在模式分类中的应用综述  

Review on the Application of Evidence Theory in Pattern Classification

作　　者：刘帅彤 李晓军 周志杰 姚俊萍 王杰 LIU Shuai-tong;LI Xiao-jun;ZHOU Zhi-jie;YAO Jun-ping;WANG Jie(Rocket Force University of Engineering,Xi’an,710025,China)

机构地区：[1]火箭军工程大学,陕西西安710025

出　　处：《中国电子科学研究院学报》2022年第3期247-258,共12页Journal of China Academy of Electronics and Information Technology

基　　金：陕西省杰出青年科学基金资助项目(2020JC-34)。

摘　　要：随着技术水平的发展和研究的不断深入,在模式分类问题中需要处理的信息往往存在有大量的不确定性。证据理论作为处理不确定性一大强有力的工具,将其应用于模式分类能够有效提高分类器分析、表达以及处理不确定性数据的能力。对此,文中开展了证据理论在模式分类中应用的研究综述,在对模式分类、证据理论的基本原理进行概述的基础上,重点围绕单分类器设计和多分类器集成两个角度,系统梳理了证据理论在模式分类中的研究现状,并从不同分类特性的角度出发比较了各阶段方法的优缺点,旨在为相关研究人员提供借鉴和参考。With the development of technology and the deepening of research,there is often a lot of uncertainty in the information to be processed in pattern classification.As a powerful tool to deal with uncertainty,the application of evidence theory to pattern classification can effectively improve the ability of classifiers to analyze,express,and deal with uncertain data.In this regard,this paper reviews the research on the application of evidence theory in pattern classification.Based on the overview of the basic principles of pattern classification and evidence theory,this paper systematically combs the research status of evidence theory in pattern classification from the perspectives of single classifier design and multi classifier integration,From the perspective of different classification characteristics,the advantages and disadvantages of each stage method are compared to provide a reference for relevant researchers.

关 键 词：证据理论 不确定性 模式分类 分类器设计 多分类器集成 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]