Satellite Video Multi-Label Scene Classification With Spatial and Temporal Feature Cooperative Encoding: A Benchmark Dataset and Method.

Satellite video multi-label scene classification predicts semantic labels of multiple ground contents to describe a given satellite observation video, which plays an important role in applications like ocean observation, smart cities, et al. However, the lack of a high-quality and large-scale dataset prevents further improvement of the task. And existing methods on general videos have the difficulty to represent the local details of ground contents when directly applied to the satellite videos. In this paper, our contributions include (1) we develop the first publicly available and large-scale satellite video multi-label scene classification dataset. It consists of 18 classes of static and dynamic ground contents, 3549 videos, and 141960 frames. (2) we propose a baseline method with the novel Spatial and Temporal Feature Cooperative Encoding (STFCE). It exploits the relations between local spatial and temporal features, and models long-term motion information hidden in inter-frame variations. In this way, it can enhance features of local details and obtain the powerful video-scene-level feature representation, which raises the classification performance effectively. Experimental results show that our proposed STFCE outperforms 13 state-of-the-art methods with a global average precision (GAP) of 0.8106 and the careful fusion and joint learning of the spatial, temporal, and motion features are beneficial to achieve a more robust and accurate model. Moreover, benchmarking results show that the proposed dataset is very challenging and we hope it could promote further development of the satellite video multi-label scene classification task.

SSTU: Swin-Spectral Transformer U-Net for hyperspectral whole slide image reconstruction.

Whole Slide Imaging and Hyperspectral Microscopic Imaging provide great quality data with high spatial and spectral resolution for histopathology. Existing Hyperspectral Whole Slide Imaging systems combine the advantages of the techniques above, thus providing rich information for pathological diagnosis. However, it cannot avoid the problems of slow acquisition speed and mass data storage demand. Inspired by the spectral reconstruction task in computer vision and remote sensing, the Swin-Spectral Transformer U-Net (SSTU) has been developed to reconstruct Hyperspectral Whole Slide images (HWSis) from multiple Hyperspectral Microscopic images (HMis) of small Field of View and Whole Slide images (WSis). The Swin-Spectral Transformer (SST) module in SSTU takes full advantage of Transformer in extracting global attention. Firstly, Swin Transformer is exploited in space domain, which overcomes the high computation cost in Vision Transformer structures, while it maintains the spatial features extracted from WSis. Furthermore, Spectral Transformer is exploited to collect the long-range spectral features in HMis. Combined with the multi-scale encoder-bottleneck-decoder structure of U-Net, SSTU network is formed by sequential and symmetric residual connections of SSTs, which reconstructs a selected area of HWSi from coarse to fine. Qualitative and quantitative experiments prove the performance of SSTU in HWSi reconstruction task superior to other state-of-the-art spectral reconstruction methods.

An End-to-End Framework for Joint Denoising and Classification of Hyperspectral Images.

Image denoising and classification are typically conducted separately and sequentially according to their respective objectives. In such a setup, where the two tasks are decoupled, the denoising operation does not optimally serve the classification task and sometimes even deteriorates it. We introduce here a unified deep learning framework for joint denoising and classification of high-dimensional images, and we particularly apply it in the framework of hyperspectral imaging. Earlier works on joint image denoising and classification are very scarce, and to the best of our knowledge, no deep learning models were proposed or studied yet for this type of multitask image processing. A key component in our joint learning model is a compound loss function, designed in such a way that the denoising and classification operations benefit each other iteratively during the learning process. Hyperspectral images (HSIs) are particularly challenging for both denoising and classification due to their high dimensionality and varying noise statistics across the bands. We argue that a well-designed end-to-end deep learning framework for joint denoising and classification is superior to current deep learning approaches for processing HSI data, and we substantiate this by results on real HSI images in remote sensing. We experimentally show that the proposed joint learning framework substantially improves the classification performance compared to the common deep learning approaches in HSI processing, and as a by-product, the denoising results are enhanced as well, especially in terms of the semantic content, benefiting from the classification.

A Novel Low Rank Smooth Flat-Field Correction Algorithm for Hyperspectral Microscopy Imaging.

A flat-field correction method is proposed for multiple measured hyperspectral microscopy imaging in this paper. As the most crucial preprocessing process in quantitative microscopic analysis, flat-field correction solves the uneven illumination caused by vignetting in microscopic images, and guarantees the precision of spatial and spectral information in hyperspectral microscopic imaging. In order to carry out flat-field correction and extract uneven illumination among groups of hyperspectral microscopic data containing hundreds of bands simultaneously, two properties of vignetting have been exploited: i) low-rank property is reflected by little information contained in vignetting; ii) local smoothness can be observed as a gradual change in brightness of vignetting, which is typically equivalent to the sparseness in spatial frequency domain. Combining the two properties above, a novel Low Rank Smooth Flat-field Correction (LRSFC) model modified from common orthogonal basis extraction is proposed, while an optimization is solved based on alternating direction multiplier method (ADMM), obtaining a unique flat-field term with low-rank and smooth properties. Qualitative and quantitative experimental assessments indicate that LRSFC does not add extra cell texture to the extracted flat-field term, whose performance appears prior to other state-of-the-art flat-field correction methods.

Tasks of COVID-19 prevention and control management teams at primary health care facilities in mainland China: a nationwide online cross-sectional survey.

BACKGROUND: This research aimed to investigate the tasks performed by Coronavirus Disease 2019(COVID-19) prevention and control management teams at primary healthcare (PHC) facilities during COVID-19 pandemic across the mainland China. METHODS: An online survey was performed and COVID-19 prevention and control management teams at PHC facilities were invited to participate in this research. The top 7 most important tasks in the three different periods of COVID-19 containment were selected and ranked. Participations of tasks were surveyed. RESULTS: A total of 998 valid responses (an effective rate of 99.11%) were collected. The respondents were divided into Group A (≤5 respondents within each PHC facility, n1 = 718) and Group B (> 5 respondents within each PHC facility, n2 = 280). The consensus was selected from top 7 most important tasks including screening at travel centers/intervals and screening at entry centers, at-home/centralized quarantine management, transferring, pre-examination/triage and fever sentinel surveillance clinic/fever clinic. Pre-examination/triage and fever sentinel surveillance clinic/fever clinic works became more significant in the regular prevention and control period. Adjusted analysis found that team members of Group A with a college, undergraduate college and graduate school educational background were less involved in pre-examination/triage works (aOR: 0.28; 95%CI: 0.09-0.86, P = 0.026; aOR: 0.30; 95%CI: 0.10-0.90, P = 0.031; aOR: 0.21; 95%CI: 0.05-0.82, P = 0.024). Those who were over the median age were twice more likely to be engaged in managing fever sentinel surveillance of clinic/fever clinic visitors (aOR: 2.18; 95%CI: 1.16-4.08, P = 0.015). Those being specialized in nursing and other specialties were less likely to participate in fever sentinel surveillance of clinic/fever clinic works (aOR: 0.44; 95%CI: 0.24-0.81, P = 0.009; aOR: 0.30; 95%CI: 0.16-0.58, P < 0.001). Those came from central and western China were less likely to participate in centralized quarantine management (aOR: 0.61; 95%CI: 0.38-0.98, P = 0.042; aOR: 0.64; 95%CI: 0.42-0.97, P = 0.037). Team members came from central and western China were twice less likely to participate in screening at travel centers/intervals (aOR: 1.75; 95%CI: 1.14-2.70, P = 0.011; aOR: 1.63; 95%CI: 1.07-2.48, P = 0.024). CONCLUSION: In mainland China, team members of COVID-19 prevention and control at PHC facilities are mainly responsible for screening, quarantine, transferring and monitoring during the COVID-19 pandemic. Pre-examination/triage and the fever sentinel surveillance clinic/fever clinic were gradually valued. Team members with lower educational background are competent in pre-examination/triage works, but more experienced general practitioners are more likely to be in charge of fever sentinel surveillance clinic/fever clinics work. The necessity of COVID-19 prevention and control management teams to participate in screening at travel centers/intervals is subjected to further discussions.

Prevention and control of COVID-19 by primary health care facilities in China: a field-survey-based qualitative study in three typical cities.

BACKGROUND: During the coronavirus disease 2019 (COVID-19) containment, primary health care (PHC) facilities inChina played an important role in providing both healthcare and public care services to community populations. The tasks of COVID-19 containment facilitated by PHC facilities were different among different regions and during different periods of COVID-19 pandemic. We sought to investigate the gaps on task participation, explore existing problems and provide corresponding solutions. METHODS: Semi-structured face-to-face interviews with COVID-19 prevention and control management teams of PHC facilities were conducted. Purposive stratified sampling was used and 32 team members of 22 PHC facilities were selected from Wuhan (as high-risk city), Shanghai (as medium-risk city) and Zunyi (as low-risk city). Framework analysis was employed to analyze the transcribed recordings. RESULTS: The main tasks of PHC facilities during the early period of the pandemic included assisting in contact tracing and epidemiological investigation, screening of populations at high-risk at travel centers/internals, house-by-house, or pre-examination/triage within PHC facilities; at-home/ centralized quarantine management; the work of fever sentinel clinics. Further analyses revealed the existing problems and suggestions for improvement or resolutions. Regular medical supply reserves were recommended because of the medical supply shortage during the pre-outbreak period. Temporarily converted quarantine wards and centralized quarantine centers could be used to deal with pressures on patients' treatment and management of the febrile patients. Only after strict evaluation of nucleic acid testing (NAT) results and housing conditions, decision on quarantine at-home or centralized quarantine centers could be made. Settings of fever sentinel clinics at PHC facilities allowed fever patients with no COVID-19 infection risks for treatment without being transferred to fever clinics of the designed secondary hospitals. Psychological intervention was sometimes in need and really helped in addressing individuals' mental pressures. CONCLUSIONS: During the COVID-19 containment, PHC facilities in China were responsible for different tasks and several problems were encountered in the working process. Accordingly, specific and feasible suggestions were put forward for different problems. Our findings are highly beneficial for healthcare teams and governments in handling similar situations.

Income Inequality and Global Political Polarization: The Economic Origin of Political Polarization in the World.

Both income inequality and political polarization have increased dramatically in much of the world over the past few decades. One might wonder how these two phenomena correlate with each other. Are there any striking similarities in the correlated patterns of income inequality and polarization across the globe? More importantly, how can improved equality in income distribution contribute to mitigate political polarization? Although the potential polarizing effects of income inequality is a growing concern, the evidence provided by the existing literature, however, has been mixed and incomplete. This research seeks to address the shortcomings of the current scholarship by using the repeated cross-sectional data from six waves of the World Values Survey from 1990 to 2020, to investigate whether and how widened income inequality and growing political polarization are linked globally. The findings indicate that there is a positive and statistically significant cross-country association between levels of income inequality and political polarization. The results remain robust to different specifications. This research has the potential for advancing the study of linkages between income inequality and its political consequences.

Tuning gelation kinetics and mechanical rigidity of ß-hairpin peptide hydrogels via hydrophobic amino acid substitutions.

Self-assembling peptide hydrogels with faster gelation kinetics and higher mechanical rigidity are favorable for their practical applications. A design strategy to control the folding, self-assembly, and hydrogelation of ß-hairpin peptides via hydrophobic amino acid substitutions has been explored in this study. Isoleucine has higher hydrophobicity and stronger propensity for ß-sheet hydrogen bonding than valine. After the valine residues of MAX1 (VKVKVKVKV(D)PPTKVKVKVKV-NH2) were replaced with isoleucines, oscillatory rheometry and circular dichroism (CD) spectroscopy characterizations indicated that the variants had clearly faster self-assembly and hydrogelation rates and that the resulting gels displayed higher mechanical stiffness. Transmission electron microscopy (TEM) indicated the parent MAX1 and its variants all formed networks of long and entangled fibrils with the similar diameters of ∼3 nm, suggesting little effect of hydrophobic substitutions on the self-assembled morphology. The MAX1I8 (IKIKIKIKV(D)PPTKIKIKIKI-NH2) hydrogel showed the fastest gelation rate (within 5 min) and the highest gel rigidity with the series, supporting the homogeneous cell distribution within its 3D scaffold. In addition, the MAX1I8 hydrogel showed quick shear-thinning and rapid recovery upon cessation of shear strain, and the MTT and immunological assays indicated its low cytotoxicity and good biocompatibility. These features are highly attractive for its widespread use in 3D cell culturing and regenerative medical treatments.

Controllable stabilization of poly(N-isopropylacrylamide)-based microgel films through biomimetic mineralization of calcium carbonate.

Two types of thermoresponsive microgels, poly(N-isopropylacrylamide) (PNIPAM) microgels and poly(N-isopropylacrylamide-co-acrylic acid) (PNIPAMAC) microgels were synthesized and used as templates for the mineralization of amorphous calcium carbonate (ACC) by diffusion of CO(2) vapor under ambient conditions. Thermosensitive PNIPAM/CaCO(3) hybrid macroscopic hydrogels and micrometer-sized PNIPAMAC/CaCO(3) hybrid microgels were controllably obtained and different mineralization mechanistic processes were proposed. The impact of the loaded CaCO(3) on the size, morphology, stability, and thermosensitivity of the microgels was also analyzed. PNIPAM/CaCO(3) hybrid macrogels had a slight decrease in thermoresponsive phase transition temperature, while PNIPAMAC/CaCO(3) hybrid microgels showed a clear increase in phase transition temperature. The difference reflected different amount and location of ACC in the gel network, causing different interactions with polymer chains. The PNIPAMAC/CaCO(3) microgels formed stable monolayer films on bare silica wafers and glass coverslips upon drying. The microgel films could facilitate the attachment and growth of 3T3 fibroblast cells and their subsequent detachment upon temperature drop from 37 °C to the ambient condition around 20 °C, thus, offering a convenient procedure for cell harvesting.