Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take ca...Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.展开更多
Due to the very high requirements on the quality of computational grids,stability property and computational efficiency,the application of high-order schemes to complex flow simulation is greatly constrained.In order ...Due to the very high requirements on the quality of computational grids,stability property and computational efficiency,the application of high-order schemes to complex flow simulation is greatly constrained.In order to solve these problems,the third-order hybrid cell-edge and cell-node weighted compact nonlinear scheme(HWCNS3)is improved by introducing a new nonlinear weighting mechanism.The new scheme uses only the central stencil to reconstruct the cell boundary value,which makes the convergence of the scheme more stable.The application of the scheme to Euler equations on curvilinear grids is also discussed.Numerical results show that the new HWCNS3 achieves the expected order in smooth regions,captures discontinuities sharply without obvious oscillation,has higher resolution than the original one and preserves freestream and vortex on curvilinear grids.展开更多
Using linear interpolation method, VIRE algorithm simply treats the signal strength value and distance of the reference tag as a linear relationship, leading to the inaccuracy of signal strength value for virtual refe...Using linear interpolation method, VIRE algorithm simply treats the signal strength value and distance of the reference tag as a linear relationship, leading to the inaccuracy of signal strength value for virtual reference tags. The threshold in VIRE algorithm is a fixed value that needs repeatedly adjustment through experiments, which results in the complicated algorithm. To solve these problems, an improved algorithm is proposed in this paper, including nonlinear interpolation algorithm, dynamic threshold setting and tag self-correction of fuzzy map, which builds an indoor positioning system based on reference tags. The experimental results show that the improved algorithm can improve the positioning accuracy and improve the stability of positioning results under bad environmental conditions without increasing the number of reference tags.展开更多
文摘Neural Networks (NN) are the functional unit of Deep Learning and are known to mimic the behavior of the human brain to solve complex data-driven problems. Whenever we train our own neural networks, we need to take care of something called the generalization of the neural network. The performance of Artificial Neural Networks (ANN) mostly depends upon its generalization capability. In this paper, we propose an innovative approach to enhance the generalization capability of artificial neural networks (ANN) using structural redundancy. A novel perspective on handling input data prototypes and their impact on the development of generalization, which could improve to ANN architectures accuracy and reliability is described.
基金supported by the Basic Research Foundation of the National Numerical Wind Tunnel Project(Grant No.NNW2018-ZT4A08)the National Key Project(Grant No.GJXM92579)of China.
文摘Due to the very high requirements on the quality of computational grids,stability property and computational efficiency,the application of high-order schemes to complex flow simulation is greatly constrained.In order to solve these problems,the third-order hybrid cell-edge and cell-node weighted compact nonlinear scheme(HWCNS3)is improved by introducing a new nonlinear weighting mechanism.The new scheme uses only the central stencil to reconstruct the cell boundary value,which makes the convergence of the scheme more stable.The application of the scheme to Euler equations on curvilinear grids is also discussed.Numerical results show that the new HWCNS3 achieves the expected order in smooth regions,captures discontinuities sharply without obvious oscillation,has higher resolution than the original one and preserves freestream and vortex on curvilinear grids.
文摘Using linear interpolation method, VIRE algorithm simply treats the signal strength value and distance of the reference tag as a linear relationship, leading to the inaccuracy of signal strength value for virtual reference tags. The threshold in VIRE algorithm is a fixed value that needs repeatedly adjustment through experiments, which results in the complicated algorithm. To solve these problems, an improved algorithm is proposed in this paper, including nonlinear interpolation algorithm, dynamic threshold setting and tag self-correction of fuzzy map, which builds an indoor positioning system based on reference tags. The experimental results show that the improved algorithm can improve the positioning accuracy and improve the stability of positioning results under bad environmental conditions without increasing the number of reference tags.
