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.
1 January 2019 in Mathematical Problems in Engineering
Single‐phase motors are known for their small power ratings and their usage in various household appliances. Although they are not large electricity consumers, their widespread application contributes to the overall electricity consumption. In addition, standard IEC 60034‐30‐1:214 defines the efficiency levels for single‐ and three‐phase motors and stipulates the increased electrical efficiency for the electrical motors. Therefore, this paper sets the parametric analysis of permanently split capacitor motor with five different design parameters that have impact on the efficiency of the motor. As an output from the parametric analysis, two different optimized motor models are obtained with increased efficiency. The impact of each parameter on motor efficiency—as well as on the other operating characteristics, like starting torque, overloading capacity, rated current, starting current, total losses, and power factor—is analyzed and adequate conclusions are derived. The obtained motor models are verified with Finite Element Method (FEM) for magnetic flux density distribution.
This paper presents a mathematical modeling and numerical analysis of fluid-thermal processes in a two-stage steam turbine cascade, focusing on the application and comparative assessment of turbulence models in computational fluid dynamics (CFD) simulations. Using the finite volume method implemented in the ANSYS CFX-Task Flow (ANSYS CFX 2022 R2) workflow, the study investigates the performance of standard k-ε, k-ω, and SST turbulence models in predicting flow structures, pressure fields, and velocity distributions within the turbine flow passages. The governing equations, including the Reynolds-Averaged Navier–Stokes (RANS) equations and associated energy and constitutive relations, are solved in conservative form under compressible flow conditions. Experimental data from turbine tests performed at the Institute of Fluid Machinery at Lodz University of Technology are used for validation. Results demonstrate that turbulence modeling significantly influences the accuracy of predicted flow phenomena. The study identifies strengths and limitations of the models in capturing complex three-dimensional flow structures and provides quantitative error margins and practical guidance for their application in industrial turbine flow simulations.
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 $${\mathcal{G}}({\mathbf{R}})$$ G ( R ) contains the space $${\mathcal{D}'}({\mathbf{R}})$$ D ′ ( R ) of Schwartz distributions as a subspace, and has a notion of 'association’ that allows us to evaluate the results in terms of distributions.
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.
1 January 2018 in Functional Analysis and Its Applications