A PSO-based rule extractor for medical diagnosis

NCU Institutional Repository > 資訊電機學院 > 資訊工程學系 > 期刊論文 > Item 987654321/106118

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106118

题名:	A PSO-based rule extractor for medical diagnosis
作者:	蘇木春;Hsieh, Yi-Zeng;Su, Mu-Chun;Wang, Pa-Chun
贡献者:	資訊電機學院資訊工程學系
关键词:	Benchmarking;Computer Simulation;Crisps;Diagnosis;Disorders;Fuzzy Logic;Fuzzy systems;Humans;Medical;Nerve Net;Neural networks;Pattern recognition;PSO;Recognition;Rule extraction;Swarm intelligence
日期:	2014-01-01
上传时间:	2026-04-23 13:09:26 (UTC+8)
出版者:	Academic Press Inc.;United States: Elsevier Inc
摘要:	摘要： [Display omitted] •A PSO-based rule extractor called a PFHRCNN is proposed to overcome the bottleneck of the knowledge acquisition.•The knowledge embedded in a trained PFHRCNN can be represented by a set of fuzzy If-Then rules.•The performance of the proposed PFHRCNNs is demonstrated on three benchmark medical databases. One of the major bottlenecks in applying conventional neural networks to the medical field is that it is very difficult to interpret, in a physically meaningful way, because the learned knowledge is numerically encoded in the trained synaptic weights. In one of our previous works, we proposed a class of Hyper-Rectangular Composite Neural Networks (HRCNNs) of which synaptic weights can be interpreted as a set of crisp If-Then rules; however, a trained HRCNN may result in some ineffective If-Then rules which can only justify very few positive examples (i.e., poor generalization). This motivated us to propose a PSO-based Fuzzy Hyper-Rectangular Composite Neural Network (PFHRCNN) which applies particle swarm optimization (PSO) to trim the rules generated by a trained HRCNN while the recognition performance will not be degraded or even be improved. The performance of the proposed PFHRCNN is demonstrated on three benchmark medical databases including liver disorders data set, the breast cancer data set and the Parkinson’s disease data set. 其他題名： J Biomed Inform 出版者： United States: Elsevier Inc 出版日期： 2014-06-01 出處： Journal of biomedical informatics, 2014-06, Vol.49, p.53-60 資源來源： Elsevier ScienceDirect Journals Complete 版權： 2014 Elsevier Inc. 版權： Copyright © 2014 Elsevier Inc. All rights reserved. 識別號： ISSN: 1532-0464 識別號： ISSN: 1532-0480 識別號： EISSN: 1532-0480 識別號： DOI: 10.1016/j.jbi.2014.05.001 識別號： PMID: 24835617
显示于类别:	[資訊工程學系] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	21	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....