Remote Sensing (RS) image classification has recently attracted great attention for its application in different tasks, including environmental monitoring, battlefield surveillance, and geospatial object detection. The best practices for these tasks often involve transfer learning from pre-trained Convolutional Neural Networks (CNNs). A common approach in the literature is employing CNNs for feature extraction, and subsequently train classifiers exploiting such features. In this paper, we propose the adoption of transfer learning by fine-tuning pre-trained CNNs for end-to-end aerial image classification. Our approach performs feature extraction from the fine-tuned neural networks and remote sensing image classification with a Support Vector Machine (SVM) model with linear and Radial Basis Function (RBF) kernels. To tune the learning rate hyperparameter, we employ a linear decay learning rate scheduler as well as cyclical learning rates. Moreover, in order to mitigate the overfitting problem of pre-trained models, we apply label smoothing regularization. For the fine-tuning and feature extraction process, we adopt the Inception-v3 and Xception inception-based CNNs, as well the residual-based networks ResNet50 and DenseNet121. We present extensive experiments on two real-world remote sensing image datasets: AID and NWPU-RESISC45. The results show that the proposed method exhibits classification accuracy of up to 98%, outperforming other state-of-the-art methods.

Abstract. Using the intrinsic definition of shape we prove an analogue of well known Borsuks theorem for compact metric spaces.Suppose X and Y are locally compact metric spaces with compact spaces of quasicomponents QX and QY . For a shape morphism f : X → Y there exists a unique continuous map f # : QX → QY , such that for a quasicomponent Q from X and W a clopen set containing f # (Q) the restriction f : Q → W , is a shape morphism, also.

Nowadays the rise of the artificial intelligence is with high speed. Even we are far away from the moment when machines are going to make decisions instead of human beings, the development in some fields of artificial intelligence is astonishing. Deep neural networks are such a filed. They are in a big expansion in a new millennium. Their application is wide: they are used in processing images, video, speech, audio, and text. In the last decade, researches put special attention and resources in the development of special kind of neural networks, convolutional neural networks. These networks have been widely applied to a variety of pattern recognition problems. Convolutional neural networks were trained on millions of images and it is difficult to outperform the accuracies that have been achieved. On the other hand, when we have a small dataset to train the network, there is no success to do it from a scratch. This article exploits the technique of transfer learning for classifying the images of small datasets. It consists fine-tuning of the pre-trained neural network. Here in details is presented the selection of hyper parameters in such networks, in order to maximize the classification accuracy. In the end, the directions have been proposed for the selection of the hyper parameters and of the pretrained network which can be suitable for transfer learning.

Paper proposes mathematical model of single phase shaded pole motor suitable for analysis of motor dynamic behavior. Derived mathematical model from d -q reference frame theory is applied at motor simulation model. Derived simulation model enables analysis of transient performance characteristics of motor currents, speed and electromagnetic torque under different operating regimes. Obtained results from the simulation are compared with data from analytical calculations based on method of symmetrical components and data from experiment for the purpose of verification of the simulation model. Simulation model is useful for studying the effect of parameters on motor starting and running characteristics at different types of loads.

In this paper, some products of distributions are derived. The results are obtained in Colombeau algebra of generalized functions, which is the most relevant algebraic construction for dealing with Schwartz distributions. Colombeau algebra contains the space of Schwartz distributions as a subspace, and has a notion of 'association’ that allows us to evaluate the results in terms of distributions.