Novel coronavirus disease 2019 (COVID-19) is an infectious disease that spreads very rapidly and threatens the health of billions of people worldwide. With the number of cases increasing rapidly, most countries are facing the problem of a shortage of testing kits and resources, and it is necessary to use other diagnostic methods as an alternative to these test kits. In this paper, we propose a convolutional neural network (CNN) model (ULNet) to detect COVID-19 using chest X-ray images. The proposed architecture is constructed by adding a new downsampling side, skip connections and fully connected layers on the basis of U-net. Because the shape of the network is similar to UL, it is named ULNet. This model is trained and tested on a publicly available Kaggle dataset (consisting of a combination of 219 COVID-19, 1314 normal and 1345 viral pneumonia chest X-ray images), including binary classification (COVID-19 vs. Normal) and multiclass classification (COVID-19 vs. Normal vs. Viral Pneumonia). The accuracy of the proposed model in the detection of COVID-19 in the binary-class and multiclass tasks is 99.53% and 95.35%, respectively. Based on these promising results, this method is expected to help doctors diagnose and detect COVID-19. Overall, our ULNet provides a quick method for identifying patients with COVID-19, which is conducive to the control of the COVID-19 pandemic.

No abstract

No abstract

As far as we know, there is no paper reported to retrieve the phase of an object in rain by the fringe projection profilometry (FPP) method. The fringe projection pattern taken in rain contains much rain noise, which makes it difficult to accurately retrieve the phase of the object. In this paper, we focus on the phase retrieval of the object in rain by the FPP method. We first decompose the original fringe projection pattern into a series of band-limited intrinsic mode functions by the two-dimensional variational mode decomposition (2D-VMD) method. Then we screen out fringe-associated modes adaptively based on mutual information and reconstruct the fringe projection pattern. Next, we decompose the reconstructed fringe projection pattern by the TGV-Hilbert-BM3D variational model to obtain the de-rained fringe component. Finally, we use the Fourier transform method, phase unwrapping method, and carrier-removal method to obtain the unwrapped phase. We test the proposed method on three fringe projection patterns taken in simulated rain weather, and we compare our proposed method with the phase-shifting method, windowed Fourier method, morphological operation-based bidimensional empirical mode decomposition method, 2D-VMD method, and the TGV-Hilbert-BM3D method. The experimental results demonstrate that, for the first time to our knowledge, our method can effectively retrieve the phase of an object in rain from a single fringe projection pattern.

As to the task allocation in Virtual Enterprise(VE), a negotiation based task allocation model was constructed. According to this model, the calculation method of utility values for each dealer was given out and an equivalent utility based bidding strategy was put forward. At last, the process of muti-issue nogtiation based task allocation was discussed, and the alogrithm of generating equivalent utility was designed.