Unbalanced Decision Trees for Multi-class Classification
Unbalanced Decision Trees for Multi-class Classification
In this paper we propose a new learning architecture that we call Unbalanced Decision Tree (UDT), attempting to improve existing methods based on Directed Acyclic Graph (DAG) and One-versus-All (OVA) approaches to multi-class pattern classification tasks. Several standard techniques, namely One-versus-One (OVO), OVA, and DAG, are compared against UDT by some benchmark datasets from the University of California, Irvine (UCI) repository of machine learning databases. Our experiments indicate that UDT is faster in testing compared to DAG, while maintaining accuracy comparable to those standard algorithms tested. This new learning architecture UDT is general, and could be applied to any classification task in machine learning in which there are natural groupings among the patterns.
291-294
Ramanan, Amirthalingam
4b287910-5234-42ef-83f0-d9875c319a56
Suppharangsan, Somjet
8a015408-b35c-429e-ba10-9d14e39b994d
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
10 August 2007
Ramanan, Amirthalingam
4b287910-5234-42ef-83f0-d9875c319a56
Suppharangsan, Somjet
8a015408-b35c-429e-ba10-9d14e39b994d
Niranjan, Mahesan
5cbaeea8-7288-4b55-a89c-c43d212ddd4f
Ramanan, Amirthalingam, Suppharangsan, Somjet and Niranjan, Mahesan
(2007)
Unbalanced Decision Trees for Multi-class Classification.
IEEE - Second International Conference on Industrial and Information Systems, ICIIS 2007, Sri Lanka.
08 - 11 Aug 2007.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this paper we propose a new learning architecture that we call Unbalanced Decision Tree (UDT), attempting to improve existing methods based on Directed Acyclic Graph (DAG) and One-versus-All (OVA) approaches to multi-class pattern classification tasks. Several standard techniques, namely One-versus-One (OVO), OVA, and DAG, are compared against UDT by some benchmark datasets from the University of California, Irvine (UCI) repository of machine learning databases. Our experiments indicate that UDT is faster in testing compared to DAG, while maintaining accuracy comparable to those standard algorithms tested. This new learning architecture UDT is general, and could be applied to any classification task in machine learning in which there are natural groupings among the patterns.
Text
188.pdf
- Version of Record
More information
Published date: 10 August 2007
Additional Information:
Event Dates: 8-11 August 2007
Venue - Dates:
IEEE - Second International Conference on Industrial and Information Systems, ICIIS 2007, Sri Lanka, 2007-08-08 - 2007-08-11
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 271490
URI: http://eprints.soton.ac.uk/id/eprint/271490
PURE UUID: 0b96010c-2679-4b25-aed1-f9bed2f711d5
Catalogue record
Date deposited: 18 Aug 2010 18:46
Last modified: 15 Mar 2024 03:29
Export record
Contributors
Author:
Amirthalingam Ramanan
Author:
Somjet Suppharangsan
Author:
Mahesan Niranjan
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics