cqu_8092+ATTACHMENT02+ATTACHMENT02.5.pdf (1.78 MB)

Novel layered clustering-based approach for generating ensemble of classifiers

Download (1.78 MB)
journal contribution
posted on 06.12.2017, 00:00 by Ashfaqur Rahman, Brijesh Verma
This paper introduces a novel concept for creating an ensemble of classifiers. The concept is based on generating ensemble of classifiers through clustering of data at multiple layers. The ensemble classifier model generates a set of alternative clustering of a data set at different layers by randomly initializing the clustering parameters and trains a set of base classifiers on the patterns at different clusters in different layers. A test pattern is classified by first finding the appropriate cluster at each layer and then using the corresponding base classifier. The decisions obtained at different layers are fused into a final verdict using majority voting. As the base classifiers are trained on overlapping patterns at different layers, the proposed approach achieves diversity among the individual classifiers. Identification of difficult–to–classify patterns through clustering and achievement of diversity through layering leads to better classification results as evidenced from the experimental results.

Funding

Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)

History

Volume

22

Issue

5

Start Page

781

End Page

792

Number of Pages

12

ISSN

1045-9227

Location

USA

Publisher

IEEE

Language

en-aus

Peer Reviewed

Yes

Open Access

No

External Author Affiliations

Centre for Intelligent and Networked Systems (CINS); Faculty of Arts, Business, Informatics and Education; Institute for Resource Industries and Sustainability (IRIS);

Era Eligible

Yes

Journal

IEEE transactions on neural networks.

Exports