Ensemble of Adaptive Rule-Based Granular Neural Network Classifiers for Multispectral Remote Sensing Images

Information granulation opens ample scope to design likely transparent neural networks called granular neural networks (GNNs). The paper proposes a classification model in the framework of ensemble of GNN-based classifiers, and justifies its improved performance in classifying land use/cover classes of multispectral remote sensing (RS) images. The model also provides an adaptive method for fuzzy rules extraction from the fuzzified input variables for GNN and thus avoid the uncertainty in empirical search of rules for output class labels. The superiority of the proposed model to other similar methods is established both visually and quantitatively for land use/cover classification of multispectral RS images. Comparative analysis revealed that GNN with multiple rules performed better than GNN with single rule assigned for each of the classes, and ensemble of GNNs outperformed all other methods. Various performance measures, such as overall accuracy, producer's accuracy, user's accuracy, kappa coefficient, and measure of dispersion estimation, are used for comparative analysis.