模式识别与人工智能
2025年4月4日 星期五   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2022, Vol. 35 Issue (4): 291-305    DOI: 10.16451/j.cnki.issn1003-6059.202204001
论文与报告 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于证据理论的广义多尺度覆盖决策系统的最优尺度组合
王金波1,2, 吴伟志1,2
1.浙江海洋大学 信息工程学院 舟山 316022;
2.浙江海洋大学 浙江省海洋大数据挖掘与应用重点实验室 舟山 316022
Evidence-Theory-Based Optimal Scale Combinations in Generalized Multi-scale Covering Decision Systems
WANG Jinbo1,2, WU Weizhi1,2
1. School of Information Engineering, Zhejiang Ocean University, Zhoushan 316022;
2. Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province, Zhejiang Ocean University, Zhou-shan 316022

全文: PDF (642 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 多尺度数据分析是当前粒计算研究领域的热门研究方向,它模拟人类思考模式,以建立多层次的复杂数据和信息处理的有效计算模型为目标.在多尺度数据分析中,一个关键的问题是从系统中选择一个合适的子系统用于最终的分类或决策,这个子系统对应的每个属性的尺度水平的组合称为系统的一个最优尺度组合.针对广义多尺度覆盖决策系统中的知识获取问题,首先,在协调广义多尺度覆盖决策系统中,使用信任函数和似然函数刻画最优尺度组合.然后,在不协调广义多尺度覆盖决策系统中定义7种最优尺度组合的概念,并给出它们之间的关系,结果表明实际有4种不同的最优尺度组合,阐明使用似然函数和信任函数可以定量刻画不协调广义多尺度覆盖决策系统的上、下近似最优尺度组合的特征.最后,举例说明文中方法可用在不完备广义多尺度决策系统和广义多尺度集值决策系统中的最优尺度组合的选择.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
王金波
吴伟志
关键词 粒计算尺度组合多尺度决策系统覆盖粗糙集证据理论    
Abstract:Multi-scale data analysis is a hot research direction in the field of granular computing. It simulates the mode of human thinking to establish effective computation models for dealing with multi-level complex data and information. A critical problem in multi-scale data analysis is to select a suitable sub-system from a given system for final classification or decision, and the combination of scale level of each attribute corresponding to the sub-system is called an optimal scale combination of the system. To solve the problem of knowledge acquisition in generalized multi-scale covering decision systems, scale combinations are firstly characterized by belief and plausibility functions in consistent generalized multi-scale covering decision systems. Then, the concepts of seven types of optimal scale combinations in inconsistent generalized multi-scale covering decision systems are defined and their relationships are clarified. It is showed that there are actually four different types of optimal scale combinations. Moreover, it is illuminated that belief and plausibility functions can be applied to characterize lower-approximation optimal scale combinations and upper-approximation optimal scale combinations in inconsistent generalized multi-scale covering decision systems, respectively. Finally, it is illustrated that the proposed methods can be applied to the optimal scale combination selection in incomplete generalized multi-scale decision systems and generalized multi-scale set-valued decision systems, respectively.
Key wordsGranular Computing    Scale Combinations    Multi-scale Decision Systems    Covering Rough Sets    Evidence Theory   
收稿日期: 2021-11-01     
ZTFLH: TP18  
基金资助:国家自然科学基金项目(No.61976194,41631179,62076221)资助
通讯作者: 吴伟志,博士,教授,主要研究方向为粗糙集、粒计算、数据挖掘、人工智能.E-mail:wuwz@zjou.edu.cn.   
作者简介: 王金波,硕士研究生,主要研究方向为粗糙集、粒计算.E-mail:1638346787@qq.com.
引用本文:   
王金波, 吴伟志. 基于证据理论的广义多尺度覆盖决策系统的最优尺度组合[J]. 模式识别与人工智能, 2022, 35(4): 291-305. WANG Jinbo, WU Weizhi. Evidence-Theory-Based Optimal Scale Combinations in Generalized Multi-scale Covering Decision Systems. Pattern Recognition and Artificial Intelligence, 2022, 35(4): 291-305.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202204001      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2022/V35/I4/291
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn