Search

The structure information of hyperspectral image (HSI) is well-characterized by tensors, surpassing the capabilities of traditional compressive sensing reconstruction models based on vectors and matrices. Tensor decomposition has been integrated with other regularizations in the model-based reconstruction algorithms to capture more priors. However, the existing tensor decomposition fails to achieve the best low-rank approximation. The effectiveness of model-based reconstruction methods can be promoted. In this article, a subspace-based model utilizing spectral quadratic variation regularized autoweighted tensor ring (TR) decomposition is proposed to explore the multiple-layer spatial–spectral priors of HSI. The original HSI is decomposed into the feature image and spectral basis to explore the first-layer spectral low-rankness. To capture the second-layer low-rank prior, TR decomposition is applied to obtain the effective low-rankness approximation and low computational complexity. The tensor nuclear norm is employed to describe underlying structure priors of the TR factors, which address the deficiency in tensor rank robustness and enhance the reconstruction quality. An autoweighted mechanism is utilized to account for the varying contributions of different TR factors to the low-rank approximation. Moreover, embedding spectral quadratic variation into subspace decomposition enhances spectral smoothness and continuity. Alternating minimization is used to optimize the spectral basis and feature HSI. Through comparative experiments on three datasets, the superiority of the proposed model is demonstrated.

Deep-learning-based methods are increasingly being applied in hyperspectral image unmixing (HSU) tasks, among which the transformer model has shown superior performance and faster processing speed. However, recently proposed transformer-based HSU models are limited to single-scale feature learning, while ignoring the learning and interaction of image features at multiple different scales. To overcome this limitation, we propose a multiscale visual transformer network using a convolution crossing attention (CCA) (MSCC-ViT) model. MSCC-ViT aims to extract feature information from hyperspectral images (HSI) at different scales and effectively fuse them, allowing the model to simultaneously recognize parts of HSI with similar spectral features and distinguish parts with different features. In general, MSCC-ViT first utilizes a multiscale feature extraction module composed of 2-D–3-D convolutional layers to preliminarily extract HSI information, which is then input into a multiscale transformer to learn information at different scales. A CCA module is used for multiscale information fusion. Finally, the decoder utilizes a simple convolutional layer to restore the original image. The model was tested on one simulated dataset and three real datasets, and the results proved the superiority of the proposed model.

BackgroundCerebral vasospasm (CV) can cause inflammation and damage to neuronal cells in the elderly, leading to dementia.PurposeThis study aimed to investigate the genetic mechanisms underlying dementia caused by CV in the elderly, identify preventive and therapeutic drugs, and evaluate their efficacy in treating neurodegenerative diseases.MethodsGenes associated with subarachnoid hemorrhage and CV were acquired and screened for differentially expressed miRNAs (DEmiRNAs) associated with aneurysm rupture. A regulatory network of DEmiRNAs and mRNAs was constructed, and virtual screening was performed to evaluate possible binding patterns between Food and Drug Administration (FDA)-approved drugs and core proteins. Molecular dynamics simulations were performed on the optimal docked complexes. Optimally docked drugs were evaluated for efficacy in the treatment of neurodegenerative diseases through cellular experiments.ResultsThe study found upregulated genes (including WDR43 and THBS1) and one downregulated gene associated with aneurysm rupture. Differences in the expression of these genes indicate greater disease risk. DEmiRNAs associated with ruptured aortic aneurysm were identified, of which two could bind to THBS1 and WDR43. Cromolyn and lanoxin formed the best docking complexes with WDR43 and THBS1, respectively. Cellular experiments showed that cromolyn improved BV2 cell viability and enhanced Aβ42 uptake, suggesting its potential as a therapeutic agent for inflammation-related disorders.ConclusionThe findings suggest that WDR43 and THBS1 are potential targets for preventing and treating CV-induced dementia in the elderly. Cromolyn may have therapeutic value in the treatment of Alzheimer’s disease and dementia.

To exploit the spectral-spatial information of hyperspectral image (HSI) and achieve higher the detection accuracy, a novel multiple spectral-spatial representation based on tensor decomposition method is proposed for HSI anomaly detection (AD) in this article. First, tensor decomposition is employed to separate the original HSI dataset into anomalous tensor from background tensor to, respectively, utilize the priors of background and anomaly. Then, the segmented smoothing prior is characterized by l0-l1 hybrid total variation regularization for the spatial dimensions of the background tensor, which can not only complement the image details but also fully consider the global spectral-spatial structure. Moreover, the low-rank prior is represented with truncated nuclear norm regularization for the spectral dimension of the background tensor to make full utilization of global information in the background and reduce data redundancy. Next, l2,1-norm regularization is applied to characterize the sparse prior for the anomaly tensor, which is beneficial to inscribe the local spectral structure of each image element. Finally, all these priors are fuses to model a unified convex optimization problem and obtain the final results by alternating direction method of multipliers, which can fully explore the discriminative spectral-spatial priors and improve the AD accuracy significantly. Experiments carried out on several real data indicate that our presented method reaches excellent performance in comparison to a few advanced AD methods.

Neural networks have been widely applied in hyperspectral unmixing in the past few years. However, most networks only focus on extracting the spectral information or local spectral–spatial correlation of a single pixel. In order to further explore the spectral–spatial information of hyperspectral images (HSIs) and improve the effective use of spatial information in unmixing tasks, an end-to-end semisupervised unmixing network is proposed in this article. At the encoder, the dual branch network performs convolution operations along the spatial dimension and the spectral dimension, respectively, to realize the separated extraction of global spatial and spectral information; the spectral–spatial attention residual module then fuses the separated spectral–spatial features into the joint spectral–spatial information. The encoder is to realize mapping from high-dimensional spectral data to latent abundance representations. The decoder is a simple linear fully connected layer whose weight is fixed to a known spectral library to complete the reconstruction of the HSI. Experiments on two synthetic datasets and two real datasets demonstrate the superior performance of the proposed method, and prove the effectiveness of considering global spatial information in the unmixing task.

Convolutional neural networks (CNN) has been widely used in the research of multispectral image compression, but they still face the challenge of extracting spectral feature effectively while preserving spatial feature with integrity. In this article, a novel spectral-spatial feature extraction method is proposed with polydirectional CNN (SSPC) for multispectral image compression. First, the feature extraction network is divided into three parallel modules. The spectral module is employed to obtain spectral features along the spectral direction independently, and simultaneously, with two spatial modules extracting spatial features along two different spatial directions. Then all the features are fused together, followed by downsampling to reduce the size of the feature maps. To control the tradeoff between the rate loss and the distortion, the rate-distortion optimizer is added to the network. In addition, quantization and entropy encoding are applied in turn, converting the data into bit stream. The decoder is structurally symmetric to the encoder, which is convenient for structuring the framework to recover the image. For comparison, SSPC is tested along with JPEG2000 and three-dimensional (3-D) SPIHT on the multispectral datasets of Landsat-8 and WorldView-3 satellites. Besides, to further validate the effectiveness of polydirectional CNN, SSPC is also compared with a normal CNN-based algorithm. The experimental results show that SSPC outperforms other methods at the same bit rates, which demonstrates the validity of the spectral-spatial feature extraction method with polydirectional CNN.

The aim of this study is to determine the relationship between occupants’ emotional attitude, decision behavior, and environmental cognition toward window seats and learning efficiency and the mechanism of this relationship in public spaces (represented by academic libraries). Surveys were delivered to the academic library of Shanghai Jiao Tong University. A total of 280 valid face-to-face interview questionnaires was collected and analyzed for correlation and validation of theoretical models. The results show that learning experience, as a mediator of learning efficiency, has a significant impact on the model of occupants’ attitude toward window seat consumption. The impact mechanism was determined, and it indicated that in order to improve the learning efficiency of occupants, indoor re-planning should be carried out to improve the seat satisfaction and occupancy rate. This study introduces the concepts of service design and architectural consumption and constructs an occupant emotional consumption context with the window seat as the consumption product. In addition, it also has guiding value for seat reallocation in public buildings in the COVID-19 era. This theoretical framework provides a direction for the simulation of future construction consumption behavior.

Although most of deep-learning-based hyperspectral image (HSI) classification methods achieve great performance, there still remains a challenge to utilize small-size training samples to remarkably enhance the classification accuracy. To tackle this challenge, a novel two-branch spectral–spatial-feature attention network (TSSFAN) for HSI classification is proposed in this paper. Firstly, two inputs with different spectral dimensions and spatial sizes are constructed, which can not only reduce the redundancy of the original dataset but also accurately explore the spectral and spatial features. Then, we design two parallel 3DCNN branches with attention modules, in which one focuses on extracting spectral features and adaptively learning the more discriminative spectral channels, and the other focuses on exploring spatial features and adaptively learning the more discriminative spatial structures. Next, the feature attention module is constructed to automatically adjust the weights of different features based on their contributions for classification to remarkably improve the classification performance. Finally, we design the hybrid architecture of 3D–2DCNN to acquire the final classification result, which can significantly decrease the sophistication of the network. Experimental results on three HSI datasets indicate that our presented TSSFAN method outperforms several of the most advanced classification methods.

CD73, an ectonucleotidase, participates in the regulation of immune responses by controlling the conversion of extracellular AMP to adenosine. In this study, we investigated whether any type of brain cells, especially neuroglia cells, exhibit altered CD73 expression, localization or activity upon experimental autoimmune uveitis (EAU) induction and whether altered CD73 manipulates the activation of effector T cells that interact with such cell types. First, the amount of cell membrane-exposed CD73 was detected by flow cytometry in various types of brain cells collected from either naïve or EAE mice. Compared to that in astrocytes from naïve control mice, the amount of membrane-bound CD73 was significantly decreased in astrocytes from EAE mice, while no significant differences were detected in other cell types. Thereafter, wild-type and CD73-/- astrocytes were used to study whether CD73 influences the function of inflammatory astrocytes, such as the production of cytokines/chemokines and the activation of effector T cells that interact with astrocytes. The results indicated that the addition of exogenous AMP significantly inhibited cytokine/chemokine production by wild type astrocytes but had no effect on CD73-/- astrocytes and that the effect of AMP was almost completely blocked by the addition of either a CD73 inhibitor (APCP) or an adenosine receptor A1 subtype (ARA1) antagonist (DPCPX). Although the addition of AMP did not affect CD73-/- astrocytes, the addition of adenosine successfully inhibited their cytokine/chemokine production. The antigen-specific interaction of astrocytes with invading CD4 cells caused CD73 downregulation in astrocytes from mice that underwent EAE induction. Collectively, our findings support the conclusion that, upon EAE induction, likely due to an interaction with invading CD4+ cells, astrocytes lose most of their membrane-localized CD73; this inhibits the generation of adenosine in the local microenvironment. As adenosine has anti-inflammatory effects on astrocytes and CNS-infiltrating effector T cells in EAE, the downregulation of CD73 in astrocytes may be considered a pro-inflammatory process for facilitating the pathogenesis of EAE.

Recently, the rapid development of multispectral imaging technology has received great attention from many fields, which inevitably involves the image transmission and storage problem. To solve this issue, a novel end-to-end multispectral image compression method based on spectral–spatial feature partitioned extraction is proposed. The whole multispectral image compression framework is based on a convolutional neural network (CNN), whose innovation lies in the feature extraction module that is divided into two parallel parts, one is for spectral and the other is for spatial. Firstly, the spectral feature extraction module is used to extract spectral features independently, and the spatial feature extraction module is operated to obtain the separated spatial features. After feature extraction, the spectral and spatial features are fused element-by-element, followed by downsampling, which can reduce the size of the feature maps. Then, the data are converted to bit-stream through quantization and lossless entropy encoding. To make the data more compact, a rate-distortion optimizer is added to the network. The decoder is a relatively inverse process of the encoder. For comparison, the proposed method is tested along with JPEG2000, 3D-SPIHT and ResConv, another CNN-based algorithm on datasets from Landsat-8 and WorldView-3 satellites. The result shows the proposed algorithm outperforms other methods at the same bit rate.

Spatiotemporal simulation of tourist town growth is important for research on land use/cover change under the influence of urbanization. Many scholars have shown great interest in the unique pattern of driving urban development with tourism development. Based on the cellular automata (CA) model, we simulated and predicted the spatiotemporal growth of Sanpo town in Hebei Province, using the tourism urbanization growth model. Results showed that (1) average annual growth rate of the entire region was 1.5 Ha2 per year from 2005 to 2010, 4 Ha2 per year from 2010 to 2015, and 2.5 Ha2 per year from 2015 to 2020; (2) urban growth rate increased yearly, with regional differences, and had a high degree of correlation with the Euclidean distance of town center, traffic route, attractions, and other factors; (3) Gougezhuang, an important village center in the west of the town, demonstrated traffic advantages and increased growth rate since 2010; (4) Magezhuang village has the largest population in the region, so economic advantages have driven the development of rural urbanization. It showed that CA had high reliability in simulating the spatiotemporal evolution of tourist town, which assists the study of spatiotemporal growth under urbanization and rational protection of tourism resources.

Land use patch generalization is the key technology to achieve multiscale representation. We research patches and achieve the following. (1) We establish a neighborhood analysis model by taking semantic similarity between features as the prerequisite and accounting for spatial topological relationships, retrieve the most neighboring patches of a feature using the model for data combination, and thus guarantee the area of various land types in patch combination. (2) We establish patch features using nodes at the intersection of separate feature buffers to fill the bridge area to achieve feature aggregation and effectively control nonbridge area deformation during feature aggregation. (3) We simplify the narrow zones by dividing them from the adjacent feature buffer area and then amalgamating them into the surrounding features. This effectively deletes narrow features and meets the area requirements, better generalizes land use features, and guarantees simple and attractive maps with appropriate loads. (4) We simplify the feature sidelines using the Douglas-Peucker algorithm to effectively eliminate nodes having little impact on overall shapes and characteristics. Here, we discuss the model and algorithm process in detail and provide experimental results of the actual data.

Neural networks have greatly promoted the development of hyperspectral unmixing (HU). Most data-driven deep networks extract features of hyperspectral images (HSIs) by stacking convolutional layers to achieve endmember extraction and abundance estimation. Some model-driven networks have strong interpretability but fail to mine the deep feature. We propose a variable-iterative fully convolutional neural network (VIFCNN) for sparse unmixing, combining the characteristics of these two networks. Under the model-driven iterative framework guided by sparse unmixing by variable splitting and augmented lagrangian (SUnSAL), a data-driven spatialspectral feature learning module and a spatial information updating module are introduced to enhance the learning of data information. Experimental results on synthetic and real datasets show that VIFCNN significantly outperforms several traditional unmixing methods and two deep learning--based methods. On real datasets, our method improves signal-to-reconstruction error by 17.38%, reduces abundance root-mean-square error by 25.24%, and reduces abundance spectral angle distance by 31.40% compared with U-ADMM-BUNet. [ABSTRACT FROM AUTHOR]