Search

Consistency is a significant indicator to measure the correctness of a software system in its lifecycle. It is inevitable to introduce inconsistencies between different software artifacts in the software development process. In practice, developers perform consistency checking to detect inconsistencies, and apply their corresponding repairs to restore consistencies. Even if all inconsistencies can be repaired, how to preserve consistencies in the subsequent evolution should be considered. Consistency management (consistency checking and consistency preservation) is a challenging task, especially in the multi-view model-driven software development process. Although there are some efforts to discuss consistency management, most of them lack the support of formal methods. Our work aims to provide a framework for formal consistency management, which may be used in the practical software development process. A formal model, called a Structure model, is first presented for specifying the overall model-based structure of the software system. Next, the definition of consistency is given based on consistency rules. We then investigate consistency preservation under the following two situations. One is that if the initial system is inconsistent, then the consistency can be restored through repairs. The other is that if the initial system is consistent, then the consistency can be maintained through update propagation. To demonstrate the effectiveness of our approach, we finally present a case study with a prototype tool.

Recently, deep learning-based compressed sensing (CS) has achieved great success in reducing the sampling and computational cost of sensing systems and improving the reconstruction quality. These approaches, however, largely overlook the issue of the computational cost; they rely on complex structures and task-specific operator designs, resulting in extensive storage and high energy consumption in CS imaging systems. In this paper, we propose a lightweight but effective deep neural network based on recurrent learning to achieve a sustainable CS system; it requires a smaller number of parameters but obtains high-quality reconstructions. Specifically, our proposed network consists of an initial reconstruction sub-network and a residual reconstruction sub-network. While the initial reconstruction sub-network has a hierarchical structure to progressively recover the image, reducing the number of parameters, the residual reconstruction sub-network facilitates recurrent residual feature extraction via recurrent learning to perform both feature fusion and deep reconstructions across different scales. In addition, we also demonstrate that, after the initial reconstruction, feature maps with reduced sizes are sufficient to recover the residual information, and thus we achieved a significant reduction in the amount of memory required. Extensive experiments illustrate that our proposed model can achieve a better reconstruction quality than existing state-of-the-art CS algorithms, and it also has a smaller number of network parameters than these algorithms. Our source codes are available at: https://github.com/C66YU/CSRN., Comment: has been accepted to IEEE TETCI

Over the recent years, a number of deep learning approaches are successfully introduced to tackle the problem of image in-painting for achieving better perceptual effects. However, there still exist obvious hole-edge artifacts in these deep learning-based approaches, which need to be rectified before they become useful for practical applications. In this article, we propose an iteration-driven in-painting approach, which combines the deep context model with the backpropagation mechanism to fine-tune the learning-based in-painting process and hence, achieves further improvement over the existing state of the arts. Our iterative approach fine tunes the image generated by a pretrained deep context model via backpropagation using a weighted context loss. Extensive experiments on public available test sets, including the CelebA, Paris Streets, and PASCAL VOC 2012 dataset, show that our proposed method achieves better visual perceptual quality in terms of hole-edge artifacts compared with the state-of-the-art in-painting methods using various context models.

Background Men who have sex with men and women (MSMW) are the most important bridge population for HIV transmission. Condom use plays an important role for HIV infection. However the predictors for condom ues with females are not well characterized. Methods This was a cross-sectional study. Participants were enrolled by four community-based organizations (CBOs) by offline (bathrooms, bars), and online (gay applications, chat room) from April to December 2019. Electronic questionnare was fulfilled after a face-to-face training led by CBOs. We identified predictors of inconsistent condom use with females by creating a risk score based on regression coefficients. We externally validated this score via an independent cross-sectional survey conducted in Zhejiang Province in 2021. A total of 917, 615 MSMW were included in analysis in 2019 and 2021, seperately. Results Among 917 MSMW, 73.2% reported heterosexual behavior in the prior 6 months and 38.3% reported inconsistent condom use with females (ICUF) over that time. Compared with heterosexual/unsure MSMW, bisexual MSMW reported more male and female sex partners, higher proportion of inconsistent condom use with males, less commercial sex with males (p Ptrend Ptrend Conclusions We developed and validated a predictive risk score for ICUF among MSMW; four factors were identified, of which inconsistent condom use with men was the most important. Risk reduction intervention programs should focus on MSM who report inconsistent condom use with males, never heard PEP, having multiple partners and living in local less than 6 months.

Background:Although inactivated COVID-19 vaccines are proven to be safe and effective in the general population, the dynamic response and duration of antibodies after vaccination in the real world should be further assessed.Methods:We enrolled 1067 volunteers who had been vaccinated with one or two doses of CoronaVac in Zhejiang Province, China. Another 90 healthy adults without previous vaccinations were recruited and vaccinated with three doses of CoronaVac, 28 days and 6 months apart. Serum samples were collected from multiple timepoints and analyzed for specific IgM/IgG and neutralizing antibodies (NAbs) for immunogenicity evaluation. Antibody responses to the Delta and Omicron variants were measured by pseudovirus-based neutralization tests.Results:Our results revealed that binding antibody IgM peaked 14–28 days after one dose of CoronaVac, while IgG and NAbs peaked approximately 1 month after the second dose then declined slightly over time. Antibody responses had waned by month 6 after vaccination and became undetectable in the majority of individuals at 12 months. Levels of NAbs to live SARS-CoV-2 were correlated with anti-SARS-CoV-2 IgG and NAbs to pseudovirus, but not IgM. Homologous booster around 6 months after primary vaccination activated anamnestic immunity and raised NAbs 25.5-fold. The neutralized fraction subsequently rose to 36.0% for Delta (p=0.03) and 4.3% for Omicron (p=0.004), and the response rate for Omicron rose from 7.9% (7/89)–17.8% (16/90).Conclusions:Two doses of CoronaVac vaccine resulted in limited protection over a short duration. The inactivated vaccine booster can reverse the decrease of antibody levels to prime strain, but it does not elicit potent neutralization against Omicron; therefore, the optimization of booster procedures is vital.Funding:Key Research and Development Program of Zhejiang Province; Key Program of Health Commission of Zhejiang Province/ Science Foundation of National Health Commission; Major Program of Zhejiang Municipal Natural Science Foundation; Explorer Program of Zhejiang Municipal Natural Science Foundation.

Two algorithms has been proposed in this paper. One is another scanning t-test of trend change-points in regression slope-coefficients in two phases, along with a coherency analysis of changes between two time series. It is different from the previously published scanning Fmax test of trend changes in two-phase regressions. The second is a fuzzy weighted moving average (FWMA). Then the algorithms were applied to two series of monthly temperature over global land and ocean surfaces for 1850–2018. The applied results show that significant changes in segment trends appeared into two gradations on inter-decadal and intra-decadal scales. All subsample regression models were found to fit well with that data. Global warming got started in April 1976 with a good coherency of warming trends between land and sea. The global warming ‘hiatus’ mainly occurred in the sea cooling from November 2001 to April 2008, but not evinced over land. The ‘land/sea warming contrast’ was detected only in their anomaly series. It disappeared in their standardized differences. We refer to the anomalies in distribution N(0,s) as ‘perceptual’ indicators, while refer to the standardized differences in distribution N(0,1) as ‘net’ indexes.

BackgroundPulmonary tuberculosis (PTB) is a serious chronic communicable disease that causes a significant disease burden in China; however, few studies have described its spatial epidemiological features in students.MethodsData of all notified PTB cases from 2007 to 2020 in the student population were collected in the Zhejiang Province, China using the available TB Management Information System. Analyses including time trend, spatial autocorrelation, and spatial–temporal analysis were performed to identify temporal trends, hotspots, and clustering, respectively.ResultsA total of 17,500 PTB cases were identified among students in the Zhejiang Province during the study period, accounting for 3.75% of all notified PTB cases. The health-seeking delay rate was 45.32%. There was a decreasing trend in PTB notifications throughout the period; clustering of cases was seen in the western area of Zhejiang Province. Additionally, one most likely cluster along with three secondary clusters were identified by spatial–temporal analysis.ConclusionAlthough was a downward trend in PTB notifications among students during the time period, an upward trend was seen in bacteriologically confirmed cases since 2017. The risk of PTB was higher among senior high school and above than of junior high school. The western area of Zhejiang Province was the highest PTB risk settings for students, and more comprehensive interventions should be strengthened such as admission screening and routine health monitoring to improve early identification of PTB.

The human leucocyte antigen (HLA) loci have been widely characterized to be associated with viral infectious diseases using either HLA allele frequency-based association or in silico predicted studies. However, there is less experimental evidence to link the HLA alleles with COVID-19 and other respiratory infectious diseases, particularly in the lung cells. To examine the role of HLA alleles in response to coronavirus and other respiratory viral infections in disease-relevant cells, we designed a two-stage study by integrating publicly accessible RNA-seq data sets, and performed allelic expression (AE) analysis on heterozygous HLA genotypes. We discovered an increased AE pattern accompanied with overexpression of HLA-B gene in SARS-CoV-2-infected human lung epithelial cells. Analysis of independent data sets verified the respiratory virus-induced AE of HLA-B gene in lung cells and tissues. The results were further experimentally validated in cultured lung cells infected with SARS-CoV-2. We further uncovered that the antiviral cytokine IFNβ contribute to AE of the HLA-B gene in lung cells. Our analyses provide a new insight into allelic influence on the HLA expression in association with SARS-CoV-2 and other common viral infectious diseases.

Generative learning in pixel domain has achieved great success in exploiting their correlations in processing images towards desired objectives, yet learning in frequency domain could provide added benefits in exploiting pixel correlations without worrying about their spatial locations and increasing their modeling costs. In this paper, we analyze the spectral bias from a frequency perspective to overcome such limitations and hence propose a dynamic self-adaptive optimization on GAN-based generative learning, leading to a dynamic and generative logo synthesis in DCT domain. To achieve exploitation of all the pixel correlations inside the whole image regardless of their spatial locations, we introduce an approximated DCT transformation and decompose both the input images and the generated images into relatively independent DCT frequency bands. As a result, a new channel of DCT domain generative learning can be established to support the existing pixel domain learning towards improved logo synthesis. Since learning across different frequency band constantly varies, we further propose a dynamic optimization scheme to maximize the effectiveness of contributions from each individual DCT frequency band. Extensive experiments are carried out and the results in comparison with the existing state of the arts illustrate that our proposed achieves significant superiority in terms of both synthesized logo quality, integrity and variety.

In this paper, we propose a portrait relighting method based on deep reinforcement learning (called PR-RL). Our PR-RL model could conduct portrait relighting by sequentially predicting local light editing strokes, and use strokes to conduct dodge and burn operations on the image lightness, simulating image editing by artists using brush strokes. Reinforcement learning with Deep Deterministic Policy Gradient is introduced to design our PR-RL model, defining the action (stroke parameters) in a continuous space, through which a reward can be designed to guide the agent to learn and relight a portrait image like an artist. To optimize the relighting effect, we further enable the reward to be location relevant and hence a coarse-to-fine strategy can be applied to select corresponding actions and maximize the performance of the proposed method. In comparison with the existing efforts, our proposed PR-RL method is locally effective, scale-invariant and interpretable. We apply the proposed method to tasks of portrait relighting based on both SH-lighting and reference images. The experiments show that our PR-RL method outperforms state-of-the-art methods in generating locally effective and interpretable high resolution relighting results for wild portrait images.

In this paper, we propose one novel progressive point cloud upsampling framework to tackle the non-uniform distribution issue during the point cloud upsampling process. Specifically, we design an Up-UNet feature expansion module which is capable of learning the local and global point features via a down-feature operator and an up-feature operator, respectively, to alleviate the non-uniform distribution issue and remove the outliers. Moreover, we design a hybrid loss function considering both the multi-scale reconstruction loss and the rendering loss. The multi-scale reconstruction loss enables each upsampling module to generate a denser point cloud, while the rendering loss via point-based differentiable rendering ensures that the proposed model preserves the point cloud structures. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance in terms of both qualitative and quantitative evaluations.

BackgroundAlthough inactivated COVID-19 vaccines are proven to be safe and effective in the general population, the dynamic response and duration of antibodies after vaccination in the real world should be further assessed.MethodsWe enrolled 1067 volunteers who had been vaccinated with one or two doses of CoronaVac in Zhejiang Province, China. Another 90 healthy adults without previous vaccinations were recruited and vaccinated with three doses of CoronaVac, 28 days and 6 months apart. Serum samples were collected from multiple timepoints and analyzed for specific IgM/IgG and neutralizing antibodies (NAbs) for immunogenicity evaluation. Antibody responses to the Delta and Omicron variants were measured by pseudovirus-based neutralization tests.ResultsOur results revealed that binding antibody IgM peaked 14–28 days after one dose of CoronaVac, while IgG and NAbs peaked approximately 1 month after the second dose then declined slightly over time. Antibody responses had waned by month 6 after vaccination and became undetectable in the majority of individuals at 12 months. Levels of NAbs to live SARS-CoV-2 were correlated with anti-SARS-CoV-2 IgG and NAbs to pseudovirus, but not IgM. Homologous booster around 6 months after primary vaccination activated anamnestic immunity and raised NAbs 25.5-fold. The NAb inhibition rate subsequently rose to 36.0% for Delta (p=0.03) and 4.3% for Omicron (p=0.004), and the response rate for Omicron rose from 7.9% (7/89) to 17.8% (16/90).ConclusionsTwo doses of CoronaVac vaccine resulted in limited protection over a short duration. The homologous booster slightly increased antibody responses to the Delta and Omicron variants; therefore, the optimization of booster procedures is vital.FundingKey Research and Development Program of Zhejiang Province; Key Program of Health Commission of Zhejiang Province/ Science Foundation of National Health Commission; Major Program of Zhejiang Municipal Natural Science Foundation.

Severe fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease worldwide. It can be transmitted from person to person, and the fatality rate is very high. During this study, three SFTS clusters including 12 associated cases were identified in three counties in Zhejiang Province from 2018 to 2020. The median age of the three index patients was 70 years, and that of secondary case patients was 59 years. Of note, the mortality rate of the index patients was 100%. The mortality rate of secondary case patients was 11%. The total secondary attack rate (SAR) was 30% (9/30). The SARs of cluster A, cluster B, and cluster C were 38% (3/8), 21% (3/14), and 38% (3/8), respectively. Additionally, the interval from onset to diagnosis was 4 days. The intervals from disease onset to confirmation of the index cases and secondary cases were 7 days and 4 days, respectively. All secondary case patients had a history of close contact with blood or body fluids of the index patients. These results indicate that SFTS patients should not be discharged until recovery. When SFTS patients die, the corpses should be transferred directly from the hospital to the crematorium for cremation by persons wearing proper protective equipment to prevent virus transmission.

Cholera caused by Vibrio cholerae O139 was first reported in Bangladesh and India in 1992. To determine the genomic epidemiology and origins of O139 in China, we sequenced 104 O139 isolates collected from Zhejiang Province, China, during 1994-2018 and compared them with 57 O139 genomes from other countries in Asia. Most Zhejiang isolates fell into 3 clusters (C1-C3), which probably originated in India (C1) and Thailand (C2 and C3) during the early 1990s. Different clusters harbored different antimicrobial resistance genes and IncA/C plasmids. The integrative and conjugative elements carried by Zhejiang isolates were of a new type, differing from ICEVchInd4 and SXT

Background The World Health Organization (WHO) recommends bedaquiline (BDQ) as a Group A drug for the treatment of multi-drug resistant tuberculosis (MDR-TB) and extensively drug-resistant tuberculosis (XDR-TB). This systematic review and meta-analysis aimed to evaluate the efficacy and safety of BDQ-containing regimens for the treatment of pulmonary TB patients. Methods MEDLINE (PubMed), EBSCO, the Cochrane Central Register of Controlled Trials and CNKI (China National Knowledge Infrastructure) were searched to identify eligible trials until September 8, 2022, for randomized controlled trials (RCTs) and non-randomized studies (NRSs) where BDQ was administered to patients with TB. Outcomes of interest were: (1) efficacy, including the rate of sputum culture conversion at 8 weeks, 24 weeks, and follow-up, and the rate of complete, cure, death, failure, and lost to follow-up at end of the treatment. (2) safety, which includes the incidence of cardiotoxicity, hepatotoxicity, and grade 3–5 adverse events during the treatment. Results A total of 29 articles (N = 23,358) fulfilled the eligibility criteria and were included in the meta-analysis. Compared with the BDQ-unexposed patients, The BDQ-containing regimen improved the rate of sputum conversion in RCTs (24 weeks: RR = 1.27, 95%Cl:1.10 to 1.46, follow-up: RR = 1.33, 95%Cl:1.06 to 1.66) and increased cure rate (RR = 1.60, 95%Cl: 1.13 to 2.26), and it also decreased the failure rate by 0.56 (95%Cl: 0.56 to 0.88). In NRSs, BDQ-containing regimen improved the sputum culture conversion rate (follow-up: RR = 1.53, 95%Cl: 1.07 to 2.20) and the rate of cure (RR = 1.86,95%Cl:1.23 to 2.83), reduced the rate of all-cause death (RR = 0.68, M-H random-effects 95%Cl: 0.48 to 0.97) and failure (RR = 0.57, 95%Cl:0.46 to 0.71). In terms of safety, BDQ-containing regimen administration increased the incidence of cardiotoxicity (RR = 4.54, M-H random-effects 95%Cl: 1.74–11.87) and grade 3–5 adverse events (RR = 1.42, M-H random-effects 95%Cl: 1.17–1.73) in RCTs; NRSs showed cardiotoxicity was associated with BDQ-containing regimen (RR = 6.00, M-H random-effects 95%Cl: 1.32–27.19). In the other outcomes, there was no significant difference between the intervention and control groups. Conclusions RCTs and NRSs data support the efficacy of BDQ for pulmonary TB, but cardiotoxicity and serious adverse events of BDQ were frequent. Overall, there is a lack of comparative data on efficacy and safety. Due to the serious risk of bias and discrepancy, further confirmation is needed.

Healthcare workers (HCWs) are at a high risk for latent tuberculosis infection (LTBI) because of occupational exposure, and the attitudes and behaviors of frontline tuberculosis (TB)-related HCWs toward preventive treatment of LTBI in eastern China remain unknown. This study aimed to explore the attitudes and actual behaviors of TB-related HCWs toward TB preventive treatment (TPT) and to analyze the relevant factors influencing the attitudes of HCWs. A stratified random sample of 28 TB-designated hospitals was selected in Zhejiang Province, China. All TB-related HCWs in the selected hospitals were recruited to answer questionnaires and were tested for LTBI by the TB interferon gamma release assay. TPT use was assessed two years after the survey. Univariate analysis and binary logistic regression models were used to analyze the factors influencing the TPT intention of HCWs. A total of 318 TB-related HCWs were recruited from 28 TB-designated hospitals; 62.3% of them showed positive attitudes toward TPT, while the rest were reluctant to treat positive LTBI prophylactically. binary logistic regression analysis revealed that the factors influencing the attitudes of HCWs were mainly education level, household income, history of alcohol consumption, and workplace. The IGRA test found that 35.2% (112/318) of HCWs tested positive for LTBI. Most people refused treatment because of drug side effects, followed by the belief that treatment was ineffective, wanting to wait until the onset of the disease, and that it was too much trouble to take the medication. According to the results of a follow-up survey, only one of these HCWs underwent TPT, and the consistency rate of attitudes and behaviors was 36.6% (41/112). This study reveals different attitudes toward TPT among TB-associated HCWs in eastern China and a large gap between attitudes and actual action. The management of HCWs with LTBI still needs further strengthening.

BackgroundOwing to the coronavirus disease 2019 (COVID-19) pandemic and the emergency use of different types of COVID-19 vaccines, there is an urgent need to consider the effectiveness and persistence of different COVID-19 vaccines.MethodsWe investigated the immunogenicity of CoronaVac and Covilo, two inactivated vaccines against COVID-19 that each contain inactivated severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The levels of neutralizing antibodies to live SARS-CoV-2 and the inhibition rates of neutralizing antibodies to pseudovirus, as well as the immunoglobulin (Ig)G and IgM responses towards the spike (S) and nucleocapsid (N) protein of SARS-CoV-2 at 180 days after two-dose vaccination were detected.ResultsThe CoronaVac and Covilo vaccines induced similar antibody responses. Regarding neutralizing antibodies to live SARS-CoV-2, 77.9% of the CoronaVac vaccine recipients and 78.3% of the Covilo vaccine recipients (aged 18–59 years) seroconverted by 28 days after the second vaccine dose. Regarding SARS-CoV-2-specific antibodies, 97.1% of the CoronaVac vaccine recipients and 95.7% of the Covilo vaccine recipients seroconverted by 28 days after the second vaccine dose. The inhibition rates of neutralizing antibody against a pseudovirus of the SARS-CoV-2 Delta variant were significantly lower compared with those against a pseudovirus of wildtype SARS-CoV-2. Associated with participant characteristics and antibody levels, persons in the older age group and with basic disease, especially a chronic respiratory disease, tended to have lower anti-SARS-CoV-2 antibody seroconversion rates.ConclusionAntibodies that were elicited by these two inactivated COVID-19 vaccines appeared to wane following their peak after the second vaccine dose, but they persisted at detectable levels through 6 months after the second vaccine dose, and the effectiveness of these antibodies against the Delta variant of SARS-CoV-2 was lower than their effectiveness against wildtype SARS-CoV-2, which suggests that attention must be paid to the protective effectiveness, and its persistence, of COVID-19 vaccines on SARS-CoV-2 variants.

Supervised deep learning techniques have achieved success in many computer vision tasks. However, most deep learning methods are data hungry and rely on a large number of labeled data in the training process. This work introduces an unsupervised deep clustering framework and studies the discovery of knowledge from a set of unlabeled data samples. Specifically, we propose a new network structure for both representation learning and GMM (Gaussian Mixture Model)-based representation modeling. In the training process of our proposed network, we not only adjust the Gaussian components to better model the distribution of representations, but also adjust the data representations towards their associating Gaussian centers to provide more adaptive support for the GMM. In this way, we take the data representations as the supervisory signal for the update of the GMM parameters and the GMM as the supervisory signal for the update of the representations, yet keeping the entire deep clustering as unsupervised. Consequently, we train the network based on an objective function with two learning targets. With the first target, we learn a GMM to model the representations properly and make each Gaussian component to be compact as much as possible. With the second target, we improve the inter-cluster distance by adapting the cluster centers to be further away from their neighbors. Thus, the training procedure simultaneously improves the intra-cluster compactness and inter-cluster separability for all the evolved clusters. Experimental results on eight datasets show that the proposed method can improve the clustering performance in comparison with the existing state of the art techniques.

In recent years, deep learning has attracted substantial research attention for video restoration. Among the existing contributions, the single-frame based approaches purely rely on one reference frame and neglect the rest neighboring frames when enhancing a target frame. By contrast, the multi-frame based contributions exploit temporal information in a sliding window and the existing recurrent design only employ a single preceding enhanced frame. It is intuitive to exploit both multiple original neighboring frames and the preceding enhanced frames for video quality enhancement. In this paper, we propose a Recurrent video quality Enhancement framework with Multi-granularity frame-fusion and frame Difference based attention (REMD). Firstly, we devise a three-dimensional convolutional neural network based encoder-decoder fusion model, which fuses multiple frames in multi-granularity. Secondly, severe compression artifacts tend to emerge on the edges and textures of the compressed frames. We propose a frame difference based spatial attention method to intensify the edges and textures of motioning regions. Finally, a recurrent sliding window design is conceived for exploiting the temporal information in preceding enhanced frames and subsequent neighboring frames. Experiments demonstrate that our method achieves superior performance in comparison to the state-of-the-art contributions with substantially reduced spatial and computational complexity.

This paper proposes a collaborative deep reinforcement learning model for automatic image cropping (called CDRL-IC). By modeling image cropping as a decision-making process of reinforcement learning, our model could generate optimal cropping result in a few moving and zooming steps. An image with good composition is a comprehensive result by considering the relative importance of objects and also the spatial organization of visual elements. Therefore, emotion attention information which indicates the relationship and importance between objects is applied together with contextual information of color image for image cropping. In order to sufficiently use the emotion attention map and the color image, they are processed by two collaborative agents. The two agents make their primary learning separately and then share information through an information interaction module for making joint action prediction. In order to efficiently evaluate the cropping quality in the reward function, weighted Intersection Over Union (WIoU) is designed by integrating emotion attention map in the traditional IoU. Our CDRL-IC model is tested on a variety of datasets for both image cropping and thumbnail generation. The experiments show that our CDRL-IC model outperforms state-of-the-art methods on these benchmark datasets.

While current research on multimedia is essentially dealing with the information derived from our observations of the world, internal activities inside human brains, such as imaginations and memories of past events etc., could become a brand new concept of multimedia, for which we coin as “brain-media”. In this paper, we pioneer this idea by directly applying natural images to stimulate human brains and then collect the corresponding electroencephalogram (EEG) sequences to drive a deep framework to learn and visualize the corresponding brain activities. By examining the relevance between the visualized image and the stimulation image, we are able to assess the performance of our proposed deep framework in terms of not only the quality of such visualization but also the feasibility of introducing the new concept of “brain-media”. To ensure that our explorative research is meaningful, we introduce a dually conditioned learning mechanism in the proposed deep framework. One condition is analyzing EEG sequences through deep learning to extract a more compact and class-dependent brain features via exploiting those unique characteristics of human brains such as hemispheric lateralization and biological neurons myelination (neurons importance), and the other is to analyze the content of images via computing approaches and extract representative visual features to exploit artificial intelligence in assisting our automated analysis of brain activities and their visualizations. By combining the brain feature space with the associated visual feature space of those images that are candidates of the stimuli, we are able to generate a combined-conditional space to support the proposed dual-conditioned and lateralization-supported GAN framework. Extensive experiments carried out illustrate that our proposed deep framework significantly outperforms the existing relevant work, indicating that our proposed does provide a good potential for further research upon the introduced concept of “brain-media”, a new member for the big family of multimedia. To encourage more research along this direction, we make our source codes publicly available for downloading at GitHub. 1 1 https://github.com/aneeg/LS-GAN .

Light field imaging, originated from the availability of light field capture technology, offers a wide range of applications in the field of computational vision. The capability of predicting salient objects of light fields remains technologically challenging due to its complicated geometry structure. In this paper, we propose a light field salient object detection approach that formulates the geometric coherence among multiple views of light fields as graphs, where the angular/central views represent the nodes and their relations compose the edges. The spatial and disparity correlations between multiple views are effectively explored through multi-scale graph neural networks, enabling the more comprehensive understanding of light field content and more representative and discriminative saliency features generation. Moreover, a multi-scale saliency feature consistency learning module is embedded to enhance the saliency features. Finally, an accurate salient object map is produced for the light field based upon the extracted features. In addition, we establish a new light field salient object detection dataset (CITYU-Lytro) that contains 817 light fields with diverse contents and their corresponding annotations, aiming to further promote the research on light field salient object detection. Quantitative and qualitative experiments demonstrate that the proposed method performs favorably compared with the state-of-the-art methods on the benchmark datasets.

Thirty-four Escherichia coli isolates from 91 ready-to-eat lettuce packages, obtained from local supermarkets in Northern California, were genotyped by multilocus sequence typing, tested for susceptibility to antimicrobial agents, and screened for β-lactamase genes. We found 15 distinct sequence types (STs). Six of these genotypes (ST1198, ST2625, ST2432, ST2819, ST4600, and ST5143) have been reported as pathogens found in human samples. Twenty-six (76%) E. coli isolates were resistant to ampicillin, 17 (50%) to ampicillin/sulbactam, 8 (23%) to cefoxitin, and 7 (20%) to cefuroxime. blaCTX-M was the most prevalent β-lactamase gene, identified in eight (23%) isolates. We identified a class A broad-spectrum β-lactamase SED-1 gene, blaSED, reported by others in Citrobacter sedlakii isolated from bile of a patient. This study found that fresh lettuce carries β-lactam drug-resistant E. coli, which might serve as a reservoir for drug-resistance genes that could potentially be transmitted to pathogens that cause human infections.

The spike (S), a homotrimer glycoprotein, is the most important antigen target in the research and development of SARS-CoV-2 vaccine. There is no doubt that fully simulating the advanced structure of this homotrimer in the subunit vaccine development strategy is the most likely way to improve the immune protective effect of the vaccine. In this study, the preparation strategies of S protein receptor-binding domain (RBD) trimer, S1 region trimer, and ectodomain (ECD) trimer nanoparticles were designed based on ferritin nanoparticle self-assembly technology. The Bombyx mori baculovirus expression system was used to prepare these three nanoparticle vaccines with high expression levels in the silkworm. The immune results of mice show that the nanoparticle vaccine prepared by this strategy can not only induce an immune response by subcutaneous administration but also effective by oral administration. Given the stability of these ferritin-based nanoparticles vaccine, easy-to-use and low-cost oral immunization strategy can make up for the vaccination blind areas caused by the shortage of ultralow-temperature equipment and medical resources in underdeveloped areas. And the oral vaccine is also a very potential candidate to cut off the spread of SARS-CoV-2 in domestic and farmed animals, especially in stray and wild animals.

IntroductionSevere fever with thrombocytopenia syndrome (SFTS) is an emerging infectious disease, and the number of cases has increased in recent years in Zhejiang Province, China. However, whether the seasonal distribution, geographic distribution, and demographic characteristics of SFTS have changed with the increase of incidence was unclear.Materials and MethodsData on SFTS cases in Zhejiang Province and tick density in Daishan County from 2011 to 2019 were collected. The changing epidemiological characteristics of SFTS including seasonal distribution, geographical distribution, and demographic features were analyzed using descriptive statistical methods, Global Moran's I, local Getis-Ord Gi* statistic, and spatial scan statistic.ResultsA total of 463 SFTS cases including 53 (11.45%) deaths were reported from 2011 to 2019 in Zhejiang Province, and the annual number of cases showed increasing tendency. SFTS cases were reported in almost half of the counties (40/89) of Zhejiang Province. Elderly farmers accounted for most cases and the proportion of farmers has increased. Most cases (81.21%) occurred during April and August. The interval from illness onset to confirmation was significantly shortened (Z = 5.194, p < 0.001). The majority of cases were reported in Zhoushan City from 2011 to 2016, but most cases were reported in Taizhou City since 2017.DiscussionWe observed dynamic changes in the seasonal distribution, geographical distribution, and demographic features of SFTS, and comprehensive intervention measures, such as clearance of breeding sites, killing of tick adults, and health education should be strengthened in farmers of the key areas according to the changed epidemiological characteristics.

Despite the implementation of health education and free condom distribution for decades, the HIV/AIDS epidemic among older adults in China shows no sign of declining. This study aims to identify HIV transmission patterns and pathways in a rural county area and provide insight for developing effective HIV prevention strategies among older adults. Epidemiological field surveys combined with phylogenetic analysis were used to identify potential HIV transmission linkage in one rural county with a rapidly increasing HIV epidemic among older adults. A total of 160 HIV-positive individuals and their HIV-positive sexual partners diagnosed between 2015 and 2018 were recruited. Among them, 69.4% (

Although supervised deep representation learning has attracted enormous attentions across areas of pattern recognition and computer vision, little progress has been made towards unsupervised deep representation learning for image clustering. In this paper, we propose a deep spectral analysis network for unsupervised representation learning and image clustering. While spectral analysis is established with solid theoretical foundations and has been widely applied to unsupervised data mining, its essential weakness lies in the fact that it is difficult to construct a proper affinity matrix and determine the involving Laplacian matrix for a given dataset. In this paper, we propose a SA-Net to overcome these weaknesses and achieve improved image clustering by extending the spectral analysis procedure into a deep learning framework with multiple layers. The SA-Net has the capability to learn deep representations and reveal deep correlations among data samples. Compared with the existing spectral analysis, the SA-Net achieves two advantages: (i) Given the fact that one spectral analysis procedure can only deal with one subset of the given dataset, our proposed SA-Net elegantly integrates multiple parallel and consecutive spectral analysis procedures together to enable interactive learning across different units towards a coordinated clustering model; (ii) Our SA-Net can identify the local similarities among different images at patch level and hence achieves a higher level of robustness against occlusions. Extensive experiments on a number of popular datasets support that our proposed SA-Net outperforms 11 benchmarks across a number of image clustering applications., Comment: arXiv admin note: text overlap with arXiv:2009.05235

Background Clostridioides difficile resistant to macrolide-lincosamide-streptogramin B (MLSB) has not been reported in China. Methods In a cross-sectional study in two tertiary hospitals, C. difficile isolates from stool specimens from community-onset, hospital-associated diarrheal patients were analyzed for toxin genes, genotype, and antibiotic resistance, and the patients' clinical charts were reviewed. Results A total of 190 (15.2%) isolates (102 A+B+ and 88 A-B+) from 1250 community acquired (CA) patients were recovered and all were susceptible to vancomycin and metronidazole. High-level resistance (minimum inhibitory concentration > 128 mg/L) to erythromycin and clindamycin was recorded in 77.9% and 88.4% of the tested isolates, respectively. Furthermore, 89.3% (159/178) of the isolates resistant to MLSB carried the erythromycin resistance methylase gene (ermB). The statistically significant factors associated with C. difficile infection (CDI) induced by A-B+ isolates with MLSB resistance included a severity score of >2 (odds ratio [95% confidence interval], 7.43 [2.31-23.87]) and platelet count (cells × 109 cells/L) < 100 [5.19 (1.58-17.04)]. The proportion of A-B+ increased with enhanced CDI severity (x2 = 21.62, P < 0.001), which was significantly higher than that of ermB-positive A+B+ in severity score of 4 (x2 = 8.61, P = 0.003). The average severity score of ermB-positive isolates was significantly higher than that of ermB-negative isolates in A-B+ (Z = -2.41, P = 0.016). Conclusion The ermB-positive A-B+C. difficile with MLSB resistance is described for the first time as a potential epidemic clone inducing severe CDI in CA diarrheal patients in Eastern China.

In this paper, we devise a saliency prediction model for stereoscopic videos that learns to explore saliency inspired by the component-based interactions including spatial, temporal, as well as depth cues. The model first takes advantage of specific structure of 3D residual network (3D-ResNet) to model the saliency driven by spatio-temporal coherence from consecutive frames. Subsequently, the saliency inferred by implicit-depth is automatically derived based on the displacement correlation between left and right views by leveraging a deep convolutional network (ConvNet). Finally, a component-wise refinement network is devised to produce final saliency maps over time by aggregating saliency distributions obtained from multiple components. In order to further facilitate research towards stereoscopic video saliency, we create a new dataset including 175 stereoscopic video sequences with diverse content, as well as their dense eye fixation annotations. Extensive experiments support that our proposed model can achieve superior performance compared to the state-of-the-art methods on all publicly available eye fixation datasets.

Over the past decade, “content-based” multimedia systems have realized success. By comparison, brain imaging and classification systems demand more efforts for improvement with respect to accuracy, generalization, and interpretation. The relationship between electroencephalogram (EEG) signals and corresponding multimedia content needs to be further explored. In this paper, we integrate implicit and explicit learning modalities into a context-supported deep learning framework. We propose an improved solution for the task of brain imaging classification via EEG signals. In our proposed framework, we introduce a consistency test by exploiting the context of brain images and establishing a mapping between visual-level features and cognitive-level features inferred based on EEG signals. In this way, a multimodal approach can be developed to deliver an improved solution for brain imaging and its classification based on explicit learning modalities and research from the image processing community. In addition, a number of fusion techniques are investigated in this work to optimize individual classification results. Extensive experiments have been carried out, and their results demonstrate the effectiveness of our proposed framework. In comparison with the existing state-of-the-art approaches, our proposed framework achieves superior performance in terms of not only the standard visual object classification criteria, but also the exploitation of transfer learning. For the convenience of research dissemination, we make the source code publicly available for downloading at GitHub ( https://github.com/aneeg/dual-modal-learning ).

Steganographer detection is to detect culprit users, who attempt to hide confidential information with steganography, among many innocent users. By incorporating the knowledge of true embedding probability map that illustrates the probability distribution of embedding messages in the corresponding image, content-adaptive steganography and steganalysis have made great progress. Unfortunately, true embedding probability map is inappropriate for steganographer detection method due to the significant challenges that the steganographic algorithm and the embedding payload are usually unknown in the task of steganographer detection. In this paper, we propose a novel content-adaptive selective steganographer detection method incorporated with learning-based embedding probability estimation. The embedding probability estimation is first formulated as a pixel-wise segmentation and recognition problem and is integrated into multi-class dilated residual learning model to extract the discriminative features. In the end, the steganographer is identified by local factor outlier with the selective strategy. Extensive experiments demonstrate that the estimated embedding probability map shows robustness against different steganographic algorithms and different payloads. From our experiments, we also find that the proposed content-adaptive selective steganographer detection framework integrated by the estimated embedding probability map achieves low detection error rates in both spatial and frequency domains.

To evaluate China's current rifampin-resistant tuberculosis (RR-TB) screening strategy from stakeholders' perspectives, the perceptions, attitudes, and interests of 245 stakeholders from three eastern, central, and western China provinces on RR-TB screening strategies, were investigated through stakeholder survey and interview. The attitudes toward three RR-TB screening strategies were statistically different: inclination to choose who to screen (Z = 98.477; P < 0.001), funding for rapid diagnostic technology screening either by reimbursed health insurance or directly subsidized financial assistance (Z = 4.142, P < 0.001), and respondents' attitude during RR-TB screening implementation levels (Z = 2.380, P = 0.017). In conclusion, RR-TB screening scope could be expanded by applying rapid diagnostic technologies. Provinces with different economic status could adjust their screening policies accordingly.

Motion video recognition has been well explored in applications of computer vision. In this paper, we propose a novel video representation, which enhances motion recognition in videos based on SURF (Speeded-Up Robust Features) and two filters. Firstly, the detector scheme of SURF is used to detect the candidate points of the video because it is an efficient faster local feature detector. Secondly, by using the optical flow field and trajectory, the feature points can be filtered from the candidate points, which enables a robust and efficient extraction of motion feature points. Additionally, we introduce a descriptor, called MoSURF (Motion Speeded-Up Robust Features), based on SURF (Speeded-Up Robust Features), HOG (Histogram of Oriented Gradient), HOF (Histograms of Optical Flow), MBH(Motion Boundary Histograms), and trajectory information, which can effectively describe motion information and are complementary to each other. We evaluate our video representation under action classification on three motion video datasets namely KTH, YouTube, and UCF50. Compared with state-of-the-art methods, the proposed method shows advanced results on all datasets.

Clostridioides difficile sequence type (ST) 37 (ribotype 017) is one of the most prevalent genotypes circulating in China. However, its genomic evolution and virulence determinants were rarely explored. Whole-genome sequencing, phylogeographic and phylogenetic analyses were conducted for C. difficile ST37 isolates. The 325 ST37 genomes from six continents, including North America (n = 66), South America (n = 4), Oceania (n = 7), Africa (n = 9), Europe (n = 138) and Asia (n = 101), were clustered into six major lineages, with region-dependent distributions, harbouring an array of antibiotic-resistance genes. The ST37 strains from China were divided into four distinct sublineages, showing five importation times and international sources. Isolates associated with severe infections exhibited significantly higher toxin productions, tcdB mRNA levels, and sporulation capacities (P

Domain adaptation techniques learn transferable knowledge from a source domain to a target domain and train models that generalize well in the target domain. Unfortunately, a majority of the existing techniques are only applicable to scenarios that the target-domain data in the task of interest is available for training, yet this is not often true in practice. In general, human beings are experts in generalization across domains. For example, a baby can easily identify the bear from a clipart image after learning this category of animal from the photo images. To reduce the gap between the generalization ability of human and that of machines, we propose a new solution to the challenging zero-shot domain adaptation (ZSDA) problem, where only a single source domain is available and the target domain for the task of interest is not accessible. Inspired by the observation that the knowledge about domain correlation can improve our generalization ability, we explore the correlation between source domain and target domain in an irrelevant knowledge task ([Formula: see text]-task), where dual-domain samples are available. We denote the task of interest as the question task ([Formula: see text]-task) and synthesize its non-accessible target-domain as such that these two tasks have the shared domain correlation. In order to realize our idea, we introduce a new network structure, i.e., conditional coupled generative adversarial networks (CoCoGAN), by extending the coupled generative adversarial networks (CoGAN) into a conditioning model. With a pair of coupling GANs, our CoCoGAN is able to capture the joint distribution of data samples across two domains and two tasks. For CoCoGAN training in a ZSDA task, we introduce three supervisory signals, i.e., semantic relationship consistency across domains, global representation alignment across tasks, and alignment consistency across domains. Experimental results demonstrate that our method can learn a suitable model for the non-accessible target domain and outperforms the existing state of the arts in both image classification and semantic segmentation.

In learning-based image processing a model that is learned in one domain often performs poorly in another since the image samples originate from different sources and thus have different distributions. Domain adaptation techniques alleviate the problem of domain shift by learning transferable knowledge from the source domain to the target domain. Zero-shot domain adaptation (ZSDA) refers to a category of challenging tasks in which no target-domain sample for the task of interest is accessible for training. To address this challenge, we propose a simple but effective method that is based on the strategy of domain shift preservation across tasks. First, we learn the shift between the source domain and the target domain from an irrelevant task for which sufficient data samples from both domains are available. Then, we transfer the domain shift to the task of interest under the hypothesis that different tasks may share the domain shift for a specified pair of domains. Via this strategy, we can learn a model for the unseen target domain of the task of interest. Our method uses two coupled generative adversarial networks (CoGANs) to capture the joint distribution of data samples in dual-domains and another generative adversarial network (GAN) to explicitly model the domain shift. The experimental results on image classification and semantic segmentation demonstrate the satisfactory performance of our method in transferring various kinds of domain shifts across tasks.

Background The upsurge in HIV infections among students is a matter of particular concern. However, few studies have explored the epidemiological characteristics including the risky sexual networking of HIV-infected students in Zhejiang province, China. Methods Using the provincial surveillance data of HIV-infected students, we conducted a retrospective epidemiology study to describe the epidemiological characteristics of 628 newly diagnosed cases from 2011 to 2016 and detailed information of 124 cases from 2015 to 2016. Spatial analyses were conducted using ArcGIS software, and statistical analyses were performed using SPSS software. Results A total of 628 cases of HIV/AIDS were diagnosed among students in Zhejiang Province, China between 2011 and 2016. The cases showed an overall increasing trend over time, while the proportions of students with HIV disease status, cases diagnosed by HIV voluntary counseling and testing (VCT), and cases of homosexual transmission remained stable over time. Significant spatial heterogeneity in the cases was seen at the county level. Detailed data on 124 HIV-positive individuals collected from the local Center for Disease Control and Prevention (CDC) from 2015 and 2016, showed that the majority of them (85.5%,) engaged in homosexual behavior, and 93.4% had sex with casual partners. These partners included not only social members, but also other students. Online dating applications represented the most common means of seeking and communicating with homosexual partners. The level of awareness regarding the risk of HIV infection, and the amount coverage of face-to-face education towards students were both low. Conclusions HIV infections among students were characterized by increasing trend and spatial clustering in Zhejiang Province between 2011 and 2016, with homosexual sexual activity being the main mode of infection. Interventions are urgently required to prevent HIV infection in this population by increasing awareness of the disease. HIV testing programs and information regarding disease prevention specifically through online dating applications are needed.

COVID-19 is threatening the health of the entire human population. In order to control the spread of the disease, epidemiological investigations should be conducted, to trace the infection source of each confirmed patient and isolate their close contacts. However, the analysis on a mass of case reports in epidemiological investigation is extremely time-consuming and labor-intensive. This paper presents an end-to-end framework for automatic epidemiological case report analysis and inference, in which a Tuple-based Multi-Task Neural Network (TMT-NN) is designed and implemented for jointly recognizing epidemiological entities and relations from case reports, and an epidemiological knowledge graph and its corresponding inference engine are built to uncover the infection modes, sources and pathways. Preliminary experiments demonstrate the promising results, and we published a real data set of COVID-19 epidemiological investigation corpora at Github, as well as contributing our COVID-19 epidemiological knowledge graph to the open community OpenKG.cn.

The coronavirus disease 2019 (COVID-19) broke out in early December 2019 in Wuhan, China and escalated into a global pandemic. There is an urgent need to understand the biology of SARS-CoV-2. In this letter, we report the isolation and characterization of seven isolates of SARS-CoV-2. Results show that our viruses have 99% sequence identity with published virus sequences. In addition, all viruses grew well in Vero cells, and one of the viruses had a deletion mutation after short passage. These results shall facilitate the understanding of the characteristics of SARS-CoV-2 in vitro.

While the recently reported deep photo style transfer [1] has shown improved results in photographic style transfer, it is found sensitive to spatial differences in the semantic segmentation of the inputs when applied to head portraits. The stylized image could incur ghost shadows when the segmented regions between the input image and the style reference image are spatially different. To minimize such a risk and reduce the influence of spatial differences between the input image and the style image, we introduce a spatial transformation strategy in this paper before style transfer. By maximizing the normalized cross-correlation of the feature maps, we propose to apply a series of affine transformations to the reference image and use those spatially-transformed images as the style reference to achieve a robust style transfer, when the semantically segmented regions of both the input image and the reference image are used as inputs to the pre-trained convolutional neural network. Consequently, the incurred ghost shadows can be minimized or eliminated. Experiments show that the proposed can perform well even when the semantic segmentation of the two images have large spatial differences, achieving significant level of robustness compared with the existing benchmark [1].

There has been growing interest in developing more effective algorithms for matrix data classification. At present, most of the existing vector-based classifications involve vectorization process, which results in two main problems. First, the underlying structural information is disregarded. Second, the vectorization of a matrix incurs the creation of a vector with potentially very high dimensionality, which may lead to over-fitting when the number of training data is small. To avoid such problems, we propose a new matrix-based regression algorithm for classification, in which the input matrices to be classified are directly used to learn two regression matrices for each order of the input matrix. To further explore the discrimination information, we add a joint ${\ell _{2,1}}$ -norm on two regression matrices, which endows the algorithm optimized regression rank by uncovering common sparse columns in the two regression matrices. To further boost the classification performance, we incorporate a semisupervised learning process, which leverages both labeled and unlabeled data to enhance the training process. Experiments on public benchmark datasets show that our method outperforms a number of the existing state-of-the-art classification methods even when only few labeled training samples are provided.