Search

Hyperspectral image (HSI) processing tasks frequently rely on spatial–spectral total variation (SSTV) to quantify the local smoothness of image structures. However, conventional SSTV only considers a sparse structure of gradient maps computed along the spatial and spectral dimensions while neglecting other correlations. To address this limitation, we introduce low-rank guided SSTV (LRSTV), which characterizes the sparsity and low-rank priors of the gradient map simultaneously. First, we verify through numerical tests and theoretical analyses that the gradient tensors are not only sparse but also low-rank. Subsequently, to model the low rankness of the gradient map, we use the tensor average rank to represent the low Tucker rank of gradient tensors. The convex envelope of the tensor average rank is then employed to penalize the rank on the gradient map after the Fourier transform along the spectral dimension. By naturally encoding the sparsity and low-rank priors of the gradient map, LRSTV results in a more accurate representation of the original image. Finally, we demonstrate the effectiveness of LRSTV by integrating it into the HSI processing model, replacing conventional SSTV, and testing it on two public datasets with nine cases of mixed noise and two datasets with realistic noise. The results show that LRSTV outperforms conventional SSTV in terms of accuracy and robustness.

Abstract Maternally inherited diabetes and deafness is a rare genetic disease mainly caused by a point mutation in mitochondrial deoxyribonucleic acid. Lipoprotein lipase gene mutations are associated with familial dyslipidemias, which are difficult to manage. We reported for the first time a case that had both maternally inherited diabetes and severe hyperlipidemia caused by lipoprotein lipase gene mutation (C.347(exon3)G>C) that was resistant to fenofibrate and atorvastatin. We were able to manage the patient’s hyperlipidemia with bezafibrate, and her diabetes was well controlled with insulin. In conclusion, genetic testing is helpful in identifying rare and interesting cases when clinicians suspect inheritable diseases. Additionally, when one fibrate drug is ineffective in treating hyperlipidemia, it might be worthwhile trying another fibrate.

Graph Neural Networks (GNNs) have been intensively studied in recent years because of their promising performance over graph-structural data and have provided assistance in many fields. Recalling recent works on graph neural networks, we found that imposing graph smoothing via Frobenius norm was proven to be effective in the architecture of graph neural networks from the standpoint of the graph signal processing. In this paper, we aim to model the graph smoothness of graph neural networks using a Schatten $p$ -norm with $p$ in the interval $[1,2$ ) to characterize smoothness and propose a novel architecture called Schatten graph neural networks. This architecture stems from a primal-dual solution scheme for a graph signal denoising problem. There is difficulty in solving subproblems with respect to the Schatten $p$ -norm. We propose a fixed point iteration scheme and prove that it tracks with the linear convergence rate with solid mathematical analysis. Extensive experiments demonstrate the effectiveness of the proposed architecture of graph neural networks and their robustness to the graph adversarial attacks.

The remote sensing scene images classification has been of great value to civil and military fields. Deep learning models, especially the convolutional neural network (CNN), have achieved great success in this task, however, they may suffer from two challenges: first, the sizes of the category objects are usually different, but the conventional CNN extracts the features with fixed convolution extractor, which could cause the failure in learning the multiscale features; second, some image regions may not be useful during the feature learning process, therefore, how to guide the network to select and focus on the most relevant regions is crucially vital for remote sensing scene image classification. To address these two challenges, we propose a multiscale attention network (MSA-Network), which integrates a multiscale (MS) module and a channel and position attention (CPA) module to boost the performance of the remote sensing scene classification. The proposed MS module learns multiscale features by adopting various sizes of sliding windows from different depths’ layers and receptive fields. The CPA module is composed of two parts: the channel attention (CA) module and the position attention (PA) one. The CA module learns the global attention features from channel-level, and the PA module extracts the local attention features from pixel-level. Thus, fusing both of those two attention features, the network is apt to focus on the more critical and salient regions automatically. Extensive experiments on UC Merced, AID, NWPU-RESISC45 datasets demonstrate that the proposed MSA-Network outperforms several state-of-the-art methods.

Social identity runs through the whole life of an individual, and it provides a framework to help individuals form a value guide adapted to their survival and development in different social situations and multiple roles. This study aimed to explore the mediating effect of social identity on the relationship between optimism and mental health among 659 Tibetan college students in China. We used the Depression Anxiety and Stress Scales, the Satisfaction with Life Scale, and the Positive Affect Scale and developed a tool to assess optimism, which included three subscales measuring optimistic tendency, pessimistic tendency, and self-efficacy optimism. In addition, we have developed a social identity scale for Tibetan college students in China. Results indicated that the optimism of Tibetan college students in China had a significant positive impact on their mental health and that social identity can affect their optimism to further improve their mental health. These findings provide guidance for implementing psychological interventions aimed at enhancing undergraduates’ mental health.

Herein the reaction mechanism and the origin of stereoselectivity of asymmetric hydrogenation of oximes to hydroxylamines catalyzed by the cyclometalated iridium (III) complexes with chiral substituted single cyclopentadienyl ligands (Ir catalysts A1 and B1) under acidic condition were unveiled using DFT calculations. The catalytic cycle for this reaction consists of the dihydrogen activation step and the hydride transfer step. The calculated results indicate that the hydride transfer step is the chirality-determining step and the involvement of methanesulfonate anion (MsO−) in this reaction is of importance in the asymmetric hydrogenation of oximes catalyzed by A1 and B1. The calculated energy barriers for the hydride transfer steps without an MsO− anion are higher than those with an MsO− anion. The differences in Gibbs free energies between TSA5−1fR/TSA5−1fS and TSB5−1fR/TSB5−1fS are 13.8/13.2 (ΔΔG‡ = 0.6 kcal/mol) and 7.5/5.6 (ΔΔG‡ = 1.9 kcal/mol) kcal/mol for the hydride transfer step of substrate protonated oximes with E configuration (E−2a−H+) with MsO− anion to chiral hydroxylamines product R−3a/S−3a catalyzed by A1 and B1, respectively. According to the Curtin–Hammet principle, the major products are hydroxylamines S−3a for the reaction catalyzed by A1 and B1, which agrees well with the experimental results. This is due to the non-covalent interactions among the protonated substrate, MsO− anion and catalytic species. The hydrogen bond could not only stabilize the catalytic species, but also change the preference of stereoselectivity of this reaction.

Multi-view clustering has been deeply explored since the compatible and complementary information among views can be well captured. Recently, the low-rank tensor representation-based methods have effectively improved the clustering performance by exploring high-order correlations between multiple views. However, most of them often express the low-rank structure of the self-representative tensor by the sum of unfolded matrix nuclear norms, which may cause the loss of information in the tensor structure. In addition, the amount of effective information in all views is not consistent, and it is unreasonable to treat their contribution to clustering equally. To address the above issues, we propose a novel weighted low-rank tensor representation (WLRTR) method for multi-view subspace clustering, which encodes the low-rank structure of the representation tensor through Tucker decomposition and weights the core tensor to retain the main information of the views. Under the augmented Lagrangian method framework, an iterative algorithm is designed to solve the WLRTR method. Numerical studies on four real databases have proved that WLRTR is superior to eight state-of-the-art clustering methods.

Optimism, cultural adaptation, and mental health are distinct but associated concepts. An optimistic personality assists in maintaining mental health, and people with optimistic personality traits have better health than those with pessimistic personality traits. It has also been argued that (home or host) cultural factors influence the ability to adapt to individual social contexts and that interactions with individuals from different cultural backgrounds can help reduce social difficulties. Culture has a very important influence on the mental health of Tibetan college students, like other college students. This study aimed to investigate the initial mechanism of the potential influence of optimism on individuals’ mental health and cultural adaptability to/integration with mainstream culture. A total of 1027 Tibetan college students from four universities in western China were recruited for the study. The tools used included an instrument developed by the authors and used for the first time here to assess optimism, as well as the Depression Anxiety Stress Scales (DASS-21), Satisfaction with Life Scale (SWLS), and Positive Affect Scale (PAS). Optimism influenced mental health in the present study. The results were as follows: (1) cultural adaptability played a moderating role in the relationship between self-efficacy optimism and depression (β = 0.193, p < 0.01); (2) the moderating role of cultural adaptability in the relationship between optimism and positive emotions was not clear (p > 0.05); and (3) cultural adaptability moderated the relationship between self-efficacy optimism and life satisfaction (β = 0.286, p < 0.01). Thus, optimism and mental health are closely related, and cultural adaptability significantly affects the effect of self-efficacy in regulating depression and life satisfaction among Tibetan college students in China.

Background/foreground separation has become an inevitable step in numerous image/video processing applications, such as image/video inpainting, anomaly detection, motion segmentation, augmented reality, and so on. Recent low-rank based approaches, such as robust principal component analysis separating a data matrix into a low-rank matrix with a sparse matrix, have achieved encouraging performance. However, these approaches usually need relatively high computation cost, mainly due to calculation of full or partial singular value decomposition of large matrices. On the other hand, the nuclear norm is widely exploited as a convex surrogate of the original rank function, while it is not a tighter envelope of the original rank function. To address these above-mentioned issues, this paper proposes a fast background/foreground separation algorithm in which the low-rank constraint is solved by a matrix factorization scheme, thus heavily reducing the computation cost. We further adopt two non-convex low-rank approximations to improve the robustness and flexibility of the traditional nuclear norm. In comparison with the state-of-the-art low-rank reconstruction methods, experimental results on challenging data sets, which contain different real data sets, show our superior performance in both image clarity and computation efficiency.

Reconstruction of highly accelerated dynamic magnetic resonance imaging (MRI) is of crucial importance for the medical diagnosis. The application of general robust principal component analysis (RPCA) to MRI can increase imaging speed and efficiency. However, conventional RPCA makes use of nuclear norm as convex surrogate of the rank function, whose drawbacks have been mentioned in plenty of literature. Recently, nonconvex surrogates of the rank function in RPCA have been widely investigated and proved to be tighter rank approximation than nuclear norm by the massive experimental results. Motivated by this, we propose a nonconvex alternating direction method based on nonconvex rank approximation to reconstruct dynamic MRI data from undersampled $k-t$ space data. We solve the associated nonconvex model by the alternating direction method and difference of convex programming. The convergence analysis provided guarantees the effectiveness of our algorithm. Experimental results on cardiac perfusion and cardiac cine MRI data demonstrate that our method outperforms the state-of-the-art MRI reconstruction methods in both image clarity and computation efficiency.