Classification of Hyperspectral Remote Sensing Image Data from IoT Based on Rotation Forest and ELM with Kernel

Abstract

The technology of Internet of Things(IoT) and remote sensing technology become more and more closely linked, and hyperspectral remote sensing data can be obtained through IoT. Hyperspectral image classification is a popular issue in the domain of remote sensing. It is possible to achieve high accuracy and strong generalization through good classification method is used to process image data. In this paper, an efficient hyperspectral image classification method based on rotation forest and extreme learning machine with kernel(ROF-KELM) is presented. The proposed method uses non-negative matrix factorization(NMF) to do feature segmentation in order to get more effective data firstly. Extreme learning machine with kernel(KELM) is chosen as base classifier to improve the classification efficiency. The proposed method inherits the advantages of KELM and has an analytic solution to directly implement the multiclass classification. Then, mutual information theory is used to select base classifiers with high correlation. Finally, the results are obtained by using the voting method. Two simulation examples, classification of AVIRIS image and the UCI public data sets respectively, are conducted to demonstrate the effectiveness of the proposed method.