Remote sensing textual image classification based on extreme learning machine and hybrid rice optimization algorithm

In view of textual remote sensing image classification, a classification approach based on Extreme Learning Machine (ELM) in introduced. As the performance of ELM is mainly affected by the value of input weights and hidden biases genetic algorithm (GA) and particle swarm optimization algorithm (PSO) have been used to learn these parameters for ELM in order to improve the stability of extreme learning machine. However, these algorithms are easy to fall into the local optimum themselves. Therefore, the newly proposed hybrid rice optimization algorithm (HRO) is proposed to train the best parameters for ELM in the paper. To demonstrate the superior performance of the model, five UCI public data sets are tested firstly then the model is applied to distinguish some remote sensing textural images. Experimental results display that the proposed model is superior to other models involved in the paper, which is a very promising machine learning approach.