Cryptococcus neoformans (Cn) is an important opportunistic pathogen in the immunocompromised people, including AIDS patients, which leads to fatal cryptococcal meningitis with high mortality rate. Previous researches have shown that HIV-1 gp41-I90 ectodomain can enhance Cn adhesion to and invasion of brain microvascular endothelial cell (BMEC), which constitutes the blood brain barrier (BBB). However, little is known about the role of HIV-1 gp41-I90 in the monocyte transmigration across Cn-infected BBB. In the present study, we provide evidence that HIV-1 gp41-I90 and Cn synergistically enhance monocytes transmigration across the BBB in vitro and in vivo. The underlying mechanisms for this phenomenon require further study. In this study, the enhancing role of HIV-1 gp41-I90 in monocyte transmigration across Cn-infected BBB was demonstrated by performed transmigration assays in vitro and in vivo. Our results showed that the transmigration rate of monocytes are positively associated with Cn and/or HIV-1 gp41-I90, the co-exposure (HIV-1 gp41-I90 + Cn) group showed a higher THP-1 transmigration rate (P < 0.01). Using CD44 knock-down HBMEC or CD44 inhibitor Bikunin in the assay, the facilitation of transmigration rates of monocyte enhanced by HIV-1 gp41-I90 was significantly suppressed. Western blotting analysis and biotin/avidin enzyme-linked immunosorbent assays (BA-ELISAs) showed that Cn and HIV-1 gp41-I90 could increase the expression of CD44 and ICAM-1 on the HBMEC. Moreover, Cn and/or HIV-1 gp41-I90 could also induce CD44 redistribution to the membrane lipid rafts. By establishing the mouse cryptococcal meningitis model, we found that HIV-1 gp41-I90 and Cn could synergistically enhance the monocytes transmigration, increase the BBB permeability and injury in vivo. Collectively, our findings suggested that HIV-1 gp41-I90 ectodomain can enhance the transmigration of THP-1 through Cn-infected BBB, which may be mediated by CD44. This novel study enlightens the future prospects to elaborate the inflammatory responses induced by HIV-1 gp41-I90 ectodomain and to effectively eliminate the opportunistic infections in AIDS patients.

With the rapid development of remote sensing technology, change detection (CD) methods based on remote sensing images have been widely used in land resource planning, disaster monitoring, and urban expansion, among other fields. The purpose of CD is to accurately identify changes on the Earth’s surface. However, most CD methods focus on changes between the pixels of multitemporal remote sensing image pairs while ignoring the coupled relationships between them. This often leads to uncertainty about edge pixels with regard to changing objects and misclassification of small objects. To solve these problems, we propose a CD method for remote sensing images that uses a coupled dictionary and deep learning. The proposed method realizes the spatial-temporal modeling and correlation of multitemporal remote sensing images through a coupled dictionary learning module and ensures the transferability of reconstruction coefficients between multisource image blocks. In addition, we constructed a differential feature discriminant network to calculate the dissimilarity probability for the change area. A new loss function that considers true/false discrimination loss, classification loss, and cross-entropy loss is proposed. The most discriminating features can be extracted and used for CD. The performance of the proposed method was verified on two well-known CD datasets. Extensive experimental results show that the proposed method is superior to other methods in terms of precision, recall, F₁-score, , and .

Deep networks-based models have achieved excellent performances in various applications for extracting discriminative feature representations by convolutional neural networks (CNN) or recurrent neural networks (RNN). However, CNN or RNN may not work when handling data without temporal/spatial structures. Therefore, finding a new technique to extract features instead of CNN or RNN is a necessity. Gradient Boosted Decision Trees (GBDT) can select the features with the largest information gain when building trees. In this paper, we propose an architecture based on the ensemble of decision trees and neural network (NN) for multiple machine learning tasks, e.g., classification, regression, and ranking. It can be regarded as an extension of the widely used deep-networks-based model, in which we use GBDT instead of CNN or RNN. This architecture consists of two main parts: (1) the decision forest layers, which focus on learning features from the input data, (2) the fully connected layers, which focus on distilling knowledge from the decision forest layers. Powered by these two parts, the proposed model could handle data without temporal/spatial structures. This model can be efficiently trained by stochastic gradient descent via back-propagation. The empirical evaluation results of different machine learning tasks demonstrate the the effectiveness of the proposed method.

Single-image super-resolution (SISR) is a resolution enhancement technique and is known as an ill-posed problem. Motivated by the idea of pan-sharping, we propose a novel variational model for SISR. The structure tensor of the input low-resolution image is exploited to obtain the gradient of an imaginary panchromatic image. Then, by constraining the gradient consistency, the image edges and details can be better recovered during the procedure of restoration of high-resolution images. Besides, we resort to the nonlocal sparse and low-rank regularization of image patches to further improve the super-resolution performance. The proposed variational model is efficiently solved by ADMM-based algorithm. We do extensive experiments in natural images and remote sensing images with different magnifying factors and compare our method with three classical super-resolution methods. The subjective visual impression and quantitative evaluation indexes both show that our method can obtain higher-quality results.

Obtaining overlap/grouping functions from a given pair of overlap/grouping functions is an important method of generating overlap/grouping functions, which can be viewed as a binary operation on the set of overlap/grouping functions. In this paper, firstly, we studied closures of overlap/grouping functions w.r.t. ⊛-composition. In addition, then, we show that these compositions are order preserving. Finally, we investigate the preservation of properties like idempotency, migrativity, homogeneity, k-Lipschitz, and power stable.

This paper introduces the concept of equivalence operators based on overlap and grouping functions where the associativity property is not strongly required. Overlap functions and grouping functions are weaker than positive and continuous t-norms and t-conorms, respectively. Therefore, these equivalence operators do not necessarily satisfy certain properties, such as associativity and the neutrality principle. In this paper, two models of fuzzy equivalence operators are obtained by the composition of overlap functions, grouping functions and fuzzy negations. Their main properties are also studied.