Detection of CAN by ensemble classifiers based on ripple down rules

Andrei Kelarev, Richard Dazeley, Andrew Stranieri, John Yearwood, Herbert Jelinek

Research output: Book chapter/Published conference paperConference paperpeer-review

10 Citations (Scopus)

Abstract

It is well known that classication models produced by the
Ripple Down Rules are easier to maintain and update. They are compact
and can provide an explanation of their reasoning making them easy to
understand for medical practitioners. This article is devoted to an empir-
ical investigation and comparison of several ensemble methods based on
Ripple Down Rules in a novel application for the detection of cardiovas-
cular autonomic neuropathy (CAN) from an extensive data set collected
by the Diabetes Complications Screening Research Initiative at Charles
Sturt University. Our experiments included essential ensemble methods,
several more recent state-of-the-art techniques, and a novel consensus
function based on graph partitioning. The results show that our novel
application of Ripple Down Rules in ensemble classiers for the detec-
tion of CAN achieved better performance parameters compared with the
outcomes obtained previously in the literature.
Original languageEnglish
Title of host publicationKnowledge Management and Acquisition for Intelligent Systems
Subtitle of host publicationProceedings of the 12th Pacific Rim Knowledge Acquisition Workshop, PKAW 2012
Place of PublicationUnited States
PublisherSpringer
Pages147-159
Number of pages13
ISBN (Print)9783642325403
Publication statusPublished - 2012
Event12th International Workshop on Knowledge Management and Acquisition for Intelligent Systems: PKAW 2012 - Kuching, Sarawak, Malaysia, Kuching, Malaysia
Duration: 05 Sept 201206 Sept 2012
http://web.science.mq.edu.au/~richards/pkaw12/

Conference

Conference12th International Workshop on Knowledge Management and Acquisition for Intelligent Systems
Country/TerritoryMalaysia
CityKuching
Period05/09/1206/09/12
OtherThe purpose of this workshop is to provide a forum for presentation and discussion of all aspects of knowledge acquisition from both the theoretician's and practitioner's points of view. While it is well accepted that knowledge is vital for our individual, organisational and societal survival and growth, the nature of knowledge and how it can be captured, represented, reused, maintained and shared are not fully-understood. This workshop will explore approaches that address these issues. PKAW includes knowledge acquisition research involving manual and automated methods and combinations of both. We invite authors to submit papers on any aspect of knowledge engineering, management and acquisition research and practice. Research which addresses advanced application issues such as scalability, security, and robustness are particularly welcome. All papers will be peer reviewed, and those accepted for the conference will be included in the Springer LNAI proceedings.
Internet address

Fingerprint

Dive into the research topics of 'Detection of CAN by ensemble classifiers based on ripple down rules'. Together they form a unique fingerprint.

Cite this