A fine-grained Random Forests using class decomposition: an application to medical diagnosis.

Elyan, Eyad; Gaber, Mohamed Medhat

Abstract

Class decomposition describes the process of segmenting each class into a number of homogeneous subclasses. This can be naturally achieved through clustering. Utilising class decomposition can provide a number of benefits to supervised learning, especially ensembles. It can be a computationally efficient way to provide a linearly separable data set without the need for feature engineering required by techniques like support vector machines and deep learning. For ensembles, the decomposition is a natural way to increase diversity, a key factor for the success of ensemble classifiers. In this paper, we propose to adopt class decomposition to the state-of-the-art ensemble learning Random Forests. Medical data for patient diagnosis may greatly benefit from this technique, as the same disease can have a diverse of symptoms. We have experimentally validated our proposed method on a number of data sets that are mainly related to the medical domain. Results reported in this paper show clearly that our method has significantly improved the accuracy of Random Forests.

Citation

ELYAN, E. and GABER, M.M. 2015. A fine-grained Random Forests using class decomposition: an application to medical diagnosis. Neural computing and applications [online], 27(8), pages 2279-2288. Available from: https://doi.org/10.1007/s00521-015-2064-z

• Journal Article Type: Article
• Acceptance Date: Sep 8, 2015
• Online Publication Date: Sep 22, 2015
• Publication Date: Nov 1, 2016
• Deposit Date: Sep 9, 2016
• Publicly Available Date: Sep 23, 2016
• Journal: Neural computing and applications
• Print ISSN: 0941-0643
• Electronic ISSN: 1433-3058
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 27
• Issue: 8
• Pages: 2279-2288
• DOI: https://doi.org/10.1007/s00521-015-2064-z
• Keywords: Machine learning; Random Forests; Clustering; Ensemble learning
• Public URL: http://hdl.handle.net/10059/1644
• Contract Date: Sep 9, 2016