Combination of multiple diverse classifiers using belief functions for handling data with imperfect labels

This paper addresses the supervised learning in which the class memberships of training data are subject to ambiguity. This problem is tackled in the ensemble learning and the Dempster–Shafer theory of evidence frameworks. The initial labels of the training data are ignored and by utilizing the main classes’ prototypes, each training pattern is reassigned to one class or a subset of the main classes based on the level of ambiguity concerning its class label. Multilayer perceptron neural network is employed to learn the characteristics of the data with new labels and for a given test pattern its outputs are considered as basic belief assignment. Experiments with artificial and real data demonstrate that taking into account the ambiguity in labels of the learning data can provide better classification results than single and ensemble classifiers that solve the classification problem using data with initial imperfect labels.

► A new evidence-based ensemble model is proposed for handling data with imperfect labels. ► By utilizing the prototypes of the pre-defined classes, the possible uncertainty in the label of each learning data is detected. ► Based on the level of ambiguity concerning each learning sample class, it is re-assigned to only one class or a subset of the pre-defined classes. ► Complementary representations of the data are used for properly estimating the class labels. ► Multilayer perceptrons neural network is used to learn the characteristics of the data with new labels and its outputs are considered as basic belief assignment.