No abstract

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.Index Terms-Fuzzy information granulation, granular neural network (GNN), land use/cover classification, pattern recognition, remote sensing (RS).

Prediction of weather condition is important to take efficient decisions. In general, the relationship between the input weather parameters and the output weather condition is non linear and predicting the weather conditions in non linear relationship posses challenging task. The traditional methods of weather prediction sometimes deviate in predicting the weather conditions due to non linear relationship between the input features and output condition. Motivated with this factor, we propose a neural networks based model for weather prediction. The superiority of the proposed model is tested with the weather data collected from Indian metrological Department (IMD). The performance of model is tested with various metrics..

Land use/land cover classification of remote sensing images provide information to take efficient decisions related to resource monitoring. There exists several algorithms for remote sensing image classification. In the recent years, Deep learning models like convolution neural networks (CNNs) are widely used for remote sensing image classification. The learning and generalization ability of CNN, results in better performance in comparison with similar type of models. The functional behavior of CNNs is unexplainable because of its multiple layers of convolution and pooling operations. This results in black box characteristics of CNNs. Motivated with this factor, a CNN model with functional transparency is proposed in the present study. The model is named as Knowledge Based Morphological Deep Transparent Neural Networks (KBMDTNN) for remote sensing image classification. The architecture of KBMDTNN model provides functional transparency due to application of morphological operators, convolutional and pooling layers, and transparent neural network. In KBMDTNN model, the morphological operator preserve the shape/size information of the objects through efficient image segmentation. Convolution and pooling layers are used to produce minimal number of features from the image. The operational transparency of proposed model is coined based on the mathematical understanding of each layer in the model instead of randomly adding layers to the architecture of model. The transparency of proposed model is also because of assigning the initial weights of NN in output layer of model with computed values instead of random values. The proposed KBMDTNN model outperformed similar type of models as tested with multispectral and hyperspectral remote sensing images. The performance of KBMDTNN model is evaluated with the metrics like overall accuracy (OA), overall accuracy standard deviation (OA STD ), producer's accuracy (PA), user's accuracy (UA), dispersion score (DS), and kappa coefficient (KC).

No abstract