Title: Reinforced confidence in self-training for a semi-supervised medical data classification

Authors: Mohammed El Amine Bechar; Nesma Settouti; Mohammed Amine Chikh; Mouloud Adel

Addresses: Aix Marseille Univ, CNRS, Centrale Marseille, Institut Fresnel UMR 7249, 13013, Marseille, France; Biomedical Engineering Laboratory GBM, Tlemcen University, Algeria ' Biomedical Engineering Laboratory GBM, Tlemcen University, Algeria ' Biomedical Engineering Laboratory GBM, Tlemcen University, Algeria ' CNRS, Centrale Marseille, Aix Marseille Univ, Institut Fresnel UMR 7249, 13013, Marseille, France

Abstract: The implication of semi-supervised method has become crucial to automate tasks that require the manual human expertise for data labelling, the advantage of this method resides in the fact that they require a low amount of labelled information. In this work, we are particularly interested in self-training paradigm. These techniques use the same principle as those of supervised techniques, but with a confidence measure that allows only a selection of the most confident samples. We propose a novel self-training algorithm named reinforced confidence in self-training (R-COSET) based on an iterative process. In each iteration the learned hypothesis can be improved by confidence data, where the proposed confidence measure is reinforced by two confidence levels in order to increase the robustness of the self-training process. Experiments show that the introduction of the second level of the neighbourhood graph in confidence measure is beneficial and that R-COSET can effectively improve classification performance.

Keywords: semi-supervised classification; SSC; self-training; graph-based method; confidence measure; medical data.

DOI: 10.1504/IJAPR.2017.085323

International Journal of Applied Pattern Recognition, 2017 Vol.4 No.2, pp.107 - 127

Received: 03 Oct 2016
Accepted: 07 Feb 2017
Published online: 21 Jul 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article