Hyperspectral Image Classification with Hybrid Kernel Extreme Learning Machine

Abstract

Extreme learning machine, which has recently lead to gain popularity of single hidden layer feed-forward neural networks, provides a key solution for non-linear problems with least norm and least square solutions at a very low run time. In this work, it is intended to increase the success of hyperspectral image classification with using kernel extreme learning machine. For this purpose, a hybrid kernel is proposed by the convex combination of radial base and polynomial base kernels. In the simulations, Indian Pine hyperspectral image is used and obtained classification results of proposed method are presented with different kernels' results besides results of non-kernel extreme learning machines.