orbital angular momentumdiffractive deep neural networkmode recognitionoceanic turbulenceOrbital angular momentum(OAM)has the characteristics of mutual orthogonality between modes,and has been applied to underwater wireless optical communication(UWOC)systems to increase the channel capacity.In this work,we pro...
In this study, we propose a new deep neural network (DNN) for phase retrieval of imperfect diffraction patterns, enabling real-time image reconstruction for single-particle imaging experiments using XFELs. The network is based on a residual neural network (ResNet) with weight-corrected convolution...
Here, we propose an approach towards an end-to-end deep neural network that is able to determine a transformed three-dimensional electron density field directly from a 1-dimensional diffraction pattern. The actual electron density distribution may then be recovered with the inverse transform as we ...
37 trained a deep neural network (DNN) and a CNN, but also evaluated their model’s performance on the RRUFF experimental dataset. This dataset is a collection of experimentally verified high-quality spectral data from well-characterized minerals38. Their best model, the CNN, tested at 86% ...
Recently, machine learning and even deep learning have been applied in various applications of GNSS, including vehicle navigation and autonomous driving (Zhu et al.,2023). With the continuous development of artificial intelligence, modeling of multipath effects is one of the main application areas (...
Islam, M., Kim, J.M.: Automated bearing fault diagnosis scheme using 2D representation of wavelet packet transform and deep convolutional neural network. Comput. Ind. 106, 142–153 (2019) Article Google Scholar Deng, W., Xu, J., Song, Y., et al.: Differential evolution algorithm with...
Researchers have optimized and fabricated a four-layer passive S-DNN based ondeep learning, achieving a super-resolution DOA estimation with an angular resolution of 1°, which is four times higher than the diffraction-limited resolution.
DP-DT processes the multi-angle data using a phase retrieval algorithm that is extended by a deep image prior (DIP), which reparameterizes the 3D sample reconstruction with an untrained, deep generative 3D convolutional neural network (CNN). We show that DP-DT effectively addresses the missing ...
A deep convolutional neural network (DCNN) architecture ResNet has been tested to verify its ability to handle selected area electron diffraction pattern (... Jae Min Jeong,Moonsoo Ra,Jinha Jeong,... - RSC Advances 被引量: 0发表: 2024年 Thermal transport in turbostratic multilayer graphene qua...
By default, we parameterize this function as a deep neural network with parameters θ. In particular, we use a multilayer perceptron with leaky rectified linear units (ReLU) as the activation. The parameters, correspond to the kernels and biases of each layer. The kernels are initialized to the...