Search

Images captured under low-light conditions are characterized by lower visual quality and perception levels than images obtained in better lighting scenarios. Studies focused on low-light enhancement techniques seek to address this dilemma. However, simple image brightening results in significant noise, blurring, and color distortion. In this paper, we present a low-light enhancement (LLE) solution that effectively synergizes Retinex theory with deep learning. Specifically, we construct an efficient image gradient map estimation module based on convolutional networks that can efficiently generate noise-free image gradient maps to assist with denoising. Second, to improve upon the traditional optimization model, we design a matrix-preserving optimization method (MPOM) coupled with deep learning modules, and it exhibits high speed and low memory consumption. Third, we incorporate image structure, image texture, and implicit prior information to optimize the enhancement process for low-light conditions and overcome prevailing limitations, such as oversmoothing, significant noise, and so forth. Through extensive experiments, we show that our approach has notable advantages over the existing methods and demonstrate superiority and effectiveness, surpassing the state-of-the-art methods by an average of 1.23 dB in PSNR for the LOL and VE-LOL datasets. The code for the proposed method is available in a public repository for open-source use: https://github.com/luxunL/DRNet. [ABSTRACT FROM AUTHOR]

Credit card fraud identification is an important issue in risk prevention and control for banks and financial institutions. In order to establish an efficient credit card fraud identification model, this article studied the relevant factors that affect fraud identification. A credit card fraud identification model based on neural networks was constructed, and in-depth discussions and research were conducted. First, the layers of neural networks were deepened to improve the prediction accuracy of the model; second, this paper increase the hidden layer width of the neural network to improve the prediction accuracy of the model. This article proposes a new fusion neural network model by combining deep neural networks and wide neural networks, and applies the model to credit card fraud identification. The characteristic of this model is that the accuracy of prediction and F1 score are relatively high. Finally, use the random gradient descent method to train the model. On the test set, the proposed method has an accuracy of 96.44% and an F1 value of 96.17%, demonstrating good fraud recognition performance. After comparison, the method proposed in this paper is superior to machine learning models, ensemble learning models, and deep learning models. [ABSTRACT FROM AUTHOR]

BackgroundSystemic lupus erythematosus, characterized by persistent inflammation, is a complex autoimmune disorder with no known cure. Immunosuppressants used in treatment put patients at a higher risk of infections. New knowledge of disease modulators, such as symbiotic bacteria, can enable fine-tuning of parts of the immune system, rather than suppressing it altogether.ResultsDysbiosis of gut microbiota promotes autoimmune disorders that damage extraintestinal organs. Here we report a role of gut microbiota in the pathogenesis of renal dysfunction in lupus. Using a classical model of lupus nephritis, MRL/lpr, we found a marked depletion of Lactobacillales in the gut microbiota. Increasing Lactobacillales in the gut improved renal function of these mice and prolonged their survival. We used a mixture of 5 Lactobacillus strains (Lactobacillus oris, Lactobacillus rhamnosus, Lactobacillus reuteri, Lactobacillus johnsonii, and Lactobacillus gasseri), but L. reuteri and an uncultured Lactobacillus sp. accounted for most of the observed effects. Further studies revealed that MRL/lpr mice possessed a "leaky" gut, which was reversed by increased Lactobacillus colonization. Lactobacillus treatment contributed to an anti-inflammatory environment by decreasing IL-6 and increasing IL-10 production in the gut. In the circulation, Lactobacillus treatment increased IL-10 and decreased IgG2a that is considered to be a major immune deposit in the kidney of MRL/lpr mice. Inside the kidney, Lactobacillus treatment also skewed the Treg-Th17 balance towards a Treg phenotype. These beneficial effects were present in female and castrated male mice, but not in intact males, suggesting that the gut microbiota controls lupus nephritis in a sex hormone-dependent manner.ConclusionsThis work demonstrates essential mechanisms on how changes of the gut microbiota regulate lupus-associated immune responses in mice. Future studies are warranted to determine if these results can be replicated in human subjects.

Compelling evidence has shown that geomagnetic disturbances in vertical intensity polarization before great earthquakes are promising precursors across diverse rupture conditions. However, the geomagnetic vertical intensity polarization method uses the spectrum of smooth signals, and the anomalous waveforms of seismic electromagnetic radiation, which are basically nonstationary, have not been adequately considered. By combining pulse amplitude analysis and an experimental study of the cumulative frequency of anomalies, we found that the pulse amplitudes before the 2022 Luding M6.8 earthquake show characteristics of multiple synchronous anomalies, with the highest (or higher) values occurring during the analyzed period. Similar synchronous anomalies were observed before the 2021 Yangbi M6.4 earthquake, the 2022 Lushan M6.1 earthquake and the 2022 Malcolm M6.0 earthquake, and these anomalies indicate migration from the periphery toward the epicenters over time. The synchronous changes are in line with the recognition of previous geomagnetic anomalies with characteristics of high values before an earthquake and gradual recovery after the earthquake. Our study suggests that the pulse amplitude is effective for extracting anomalies in geomagnetic vertical intensity polarization, especially in the presence of nonstationary signals when utilizing observations from multiple station arrays. Our findings highlight the importance of incorporating pulse amplitude analysis into earthquake prediction research on geomagnetic disturbances. [ABSTRACT FROM AUTHOR]

With the continuous advancement of the economy and technology, the number of cars continues to increase, and the traffic congestion problem on some key roads is becoming increasingly serious. This paper proposes a new vehicle information feature map (VIFM) method and a multi-branch convolutional neural network (MBCNN) model and applies it to the problem of traffic congestion detection based on camera image data. The aim of this study is to build a deep learning model with traffic images as input and congestion detection results as output. It aims to provide a new method for automatic detection of traffic congestion. The deep learning-based method in this article can effectively utilize the existing massive camera network in the transportation system without requiring too much investment in hardware. This study first uses an object detection model to identify vehicles in images. Then, a method for extracting a VIFM is proposed. Finally, a traffic congestion detection model based on MBCNN is constructed. This paper verifies the application effect of this method in the Chinese City Traffic Image Database (CCTRIB). Compared to other convolutional neural networks, other deep learning models, and baseline models, the method proposed in this paper yields superior results. The method in this article obtained an F1 score of 98.61% and an accuracy of 98.62%. Experimental results show that this method effectively solves the problem of traffic congestion detection and provides a powerful tool for traffic management. [ABSTRACT FROM AUTHOR]

Unbalanced data in intrusion detection seriously affect the overall performance of intrusion detection methods. This paper proposes an intrusion detection algorithm based on unbalanced learning (ID-UL) for unbalanced learning. It uses two strategies to address the issues brought about by unbalanced data. First, the data grouping strategy based on integrated learning alleviates the extreme data imbalance and avoids the negative impact on imbalanced learning. Meanwhile, to avoid the possible negative impact brought by unbalanced data on the learning procedures of convolutional neural networks, the strategy of assigning weight to the loss function is adopted. Besides, a method for determining the weight value is designed to make the model supervise the learning of attack samples during the training process. Experimental results on the NSL-KDD dataset show that the method in this paper can effectively improve the detection of attack classes, and the overall detection accuracy reaches 81.48%. ID-UL has the same significant effect on other imbalanced datasets. [ABSTRACT FROM AUTHOR]