Generating fuzzy rules for classifier fusion | |
Liu, M ; Yuan, BZ ; Tang, XF ; Li, M | |
2005 | |
关键词 | classification multiple classifier fusion fuzzy system FRAMEWORK |
英文摘要 | This paper addresses the issues in developing a fuzzy system for multiple classifier fusion. The proposed new approach has advantage in automatically generating fuzzy rules and determining the structure of the fuzzy system. Partitioning the attribute space into small regions can increase the description accuracy of the fuzzy system, but the number of training samples fall in each region will be decreased, and the reliability of the derived rules will be decreased also. To resolve this problem, we use membership functions with broad support set in the learning step, and propose an evaluation method to determine the structure of the fuzzy system. Experimental results are compared with other classifier fusion methods such as multi-response linear regression and neural network.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000233670801029&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Computer Science, Artificial Intelligence; Computer Science, Information Systems; Computer Science, Interdisciplinary Applications; CPCI-S(ISTP); 0 |
语种 | 英语 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/387239] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Liu, M,Yuan, BZ,Tang, XF,et al. Generating fuzzy rules for classifier fusion. 2005-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论