Designing Kernel Scheme for Classifiers Fusion

TL;DR

This paper introduces a novel neural network-based fusion method called Neural Network Kernel Least Mean Square for combining classifier ensembles, aiming to enhance classification efficiency and adaptiveness.

Contribution

It proposes a new neural network neuron with kernel and LMS features for improved classifier output fusion, demonstrating superior performance over existing methods.

Findings

Higher classification accuracy compared to traditional fusion methods

Effective fusion of ensemble outputs with adaptive kernel properties

Demonstrated improved efficiency in classifier decision-making

Abstract

In this paper, we propose a special fusion method for combining ensembles of base classifiers utilizing new neural networks in order to improve overall efficiency of classification. While ensembles are designed such that each classifier is trained independently while the decision fusion is performed as a final procedure, in this method, we would be interested in making the fusion process more adaptive and efficient. This new combiner, called Neural Network Kernel Least Mean Square1, attempts to fuse outputs of the ensembles of classifiers. The proposed Neural Network has some special properties such as Kernel abilities,Least Mean Square features, easy learning over variants of patterns and traditional neuron capabilities. Neural Network Kernel Least Mean Square is a special neuron which is trained with Kernel Least Mean Square properties. This new neuron is used as a classifiers combiner to fuse outputs of base neural network classifiers. Performance of this method is analyzed and compared with other fusion methods. The analysis represents higher performance of our new method as opposed to others.