Please use this identifier to cite or link to this item: https://doi.org/10.1016/S0933-3657(00)00064-6
DC FieldValue
dc.titleA comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders
dc.contributor.authorHayashi, Y.
dc.contributor.authorSetiono, R.
dc.contributor.authorYoshida, K.
dc.date.accessioned2013-07-11T10:20:15Z
dc.date.available2013-07-11T10:20:15Z
dc.date.issued2000
dc.identifier.citationHayashi, Y., Setiono, R., Yoshida, K. (2000). A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders. Artificial Intelligence in Medicine 20 (3) : 205-216. ScholarBank@NUS Repository. https://doi.org/10.1016/S0933-3657(00)00064-6
dc.identifier.issn09333657
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/42876
dc.description.abstractNeural networks have been widely used as tools for prediction in medicine. We expect to see even more applications of neural networks for medical diagnosis as recently developed neural network rule extraction algorithms make it possible for the decision process of a trained network to be expressed as classification rules. These rules are more comprehensible to a human user than the classification process of the networks which involves complex nonlinear mapping of the input data. This paper reports the results from two neural network rule extraction techniques, NeuroLinear and NeuroRule applied to the diagnosis of hepatobiliary disorders. The dataset consists of nine measurements collected from patients in a Japanese hospital and these measurements have continuous values. NeuroLinear generates piece-wise linear discriminant functions for this dataset. The continuous measurements have previously been discretized by domain experts. NeuroRule is applied to the discretized dataset to generate symbolic classification rules. We compare the rules generated by the two techniques and find that the rules generated by NeuroLinear from the original continuously valued dataset to be slightly more accurate and more concise than the rules generated by NeuroRule from the discretized dataset. Copyright (C) 2000 Elsevier Science B.V.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1016/S0933-3657(00)00064-6
dc.sourceScopus
dc.subjectHepatobiliary disorders
dc.subjectNetwork pruning
dc.subjectNeural networks
dc.subjectNeuroLinear
dc.subjectNeuroRule
dc.subjectRule extraction
dc.typeOthers
dc.contributor.departmentINFORMATION SYSTEMS
dc.description.doi10.1016/S0933-3657(00)00064-6
dc.description.sourcetitleArtificial Intelligence in Medicine
dc.description.volume20
dc.description.issue3
dc.description.page205-216
dc.description.codenAIMEE
dc.identifier.isiut000089670400002
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

48
checked on May 6, 2021

WEB OF SCIENCETM
Citations

36
checked on May 6, 2021

Page view(s)

718
checked on May 5, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.