File(s) under permanent embargo
Applying a multi-agent classifier system with a novel trust measurement method to classifying medical data
chapter
posted on 2014-01-01, 00:00 authored by M F Mohammed, Chee Peng LimChee Peng Lim, U K Bt NgahIn this paper, we present the application of a Multi-Agent Classifier System (MACS) to medical data classification tasks. The MACS model comprises a number of Fuzzy Min-Max (FMM) neural network classifiers as its agents. A trust measurement method is used to integrate the predictions from multiple agents, in order to improve the overall performance of the MACS model. An auction procedure based on the sealed bid is adopted for the MACS model in determining the winning agent. The effectiveness of the MACS model is evaluated using the Wisconsin Breast Cancer (WBC) benchmark problem and a real-world heart disease diagnosis problem. The results demonstrate that stable results are produced by the MACS model in undertaking medical data classification tasks. © 2014 Springer Science+Business Media Singapore.
History
Title of book
The 8th international conference on robotic, vision, signal processing & power applications : innovation excellence towards humanistic technologyVolume
291Series
Lecture Notes in Electrical EngineeringChapter number
41Pagination
355 - 362Publisher
SpringerPlace of publication
SingaporePublisher DOI
ISSN
1876-1100eISSN
1876-1119ISBN-13
9789814585415Language
engNotes
Proceedings of the 8th International Conference on Robotics, Vision, Signal Processing & Power Applications (ROVISP 2013)Publication classification
B Book chapter; B1 Book chapterCopyright notice
2014, SpringerExtent
60Editor/Contributor(s)
M Sakim, H Amylia, M MustaffaUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC