With complex building composition and imaging condition, urban areas show versatile characteristics in remote sensing optical images. It demonstrates that multiple features should be utilized to ...characterize urban areas. On the other hand, since levels of development in neighboring areas are not statistically independent, the features of each urban area site depend on those of neighboring sites. In this paper, we present a multiple conditional random fields (CRFs) ensemble model to incorporate multiple features and learn their contextual information. This model involves two aspects: one is to use a CRF as the base classifier to automatically generate a set of CRFs by changing input features, and the other is to integrate the set of CRFs by defining a conditional distribution. The model has some distinct merits: each CRF component models a kind of feature, so that the ensemble model can learn different aspects of training data. Moreover, it lets the ensemble model search in a wide solution space. The ensemble model can also avoid the well-known overfitting problem of a single CRF, i.e., the many features may cause the redundancy of irrelevant information and result in counter-effect. Experiments on a wide range of images show that our ensemble model produces higher detection accuracy than single CRF and is also competitive with recent results in urban area detection.
The 2019-nCoV is officially called SARS-CoV-2 and the disease is named COVID-19. This viral epidemic in China has led to the deaths of over 1800 people, mostly elderly or those with an underlying ...chronic disease or immunosuppressed state. This is the third serious Coronavirus outbreak in less than 20 years, following SARS in 2002–2003 and MERS in 2012. While human strains of Coronavirus are associated with about 15% of cases of the common cold, the SARS-CoV-2 may present with varying degrees of severity, from flu-like symptoms to death. It is currently believed that this deadly Coronavirus strain originated from wild animals at the Huanan market in Wuhan, a city in Hubei province. Bats, snakes and pangolins have been cited as potential carriers based on the sequence homology of CoV isolated from these animals and the viral nucleic acids of the virus isolated from SARS-CoV-2 infected patients. Extreme quarantine measures, including sealing off large cities, closing borders and confining people to their homes, were instituted in January 2020 to prevent spread of the virus, but by that time much of the damage had been done, as human-human transmission became evident. While these quarantine measures are necessary and have prevented a historical disaster along the lines of the Spanish flu, earlier recognition and earlier implementation of quarantine measures may have been even more effective. Lessons learned from SARS resulted in faster determination of the nucleic acid sequence and a more robust quarantine strategy. However, it is clear that finding an effective antiviral and developing a vaccine are still significant challenges. The costs of the epidemic are not limited to medical aspects, as the virus has led to significant sociological, psychological and economic effects globally. Unfortunately, emergence of SARS-CoV-2 has led to numerous reports of Asians being subjected to racist behavior and hate crimes across the world.
•The 2019-nCoV is officially called SARS-CoV-2, and is the cause of the disease named COVID-19.•COVID-19 is the third severe epidemic caused by coronaviruses in the past 20 years.•It is believed that the SARS-CoV-2 virus originated from bats, based on genomic sequencing.•While human strains of Coronavirus are associated with about 15% of cases of the common cold, the SARS-CoV-2 is far more deadly, with a mortality rate around 2.3%.•As of February 19th, 2020, there have been 75,282 confirmed cases and 2012 deaths worldwide.•Lessons learned from SARS in 2003 resulted in faster determination of the nucleic acid sequence and a more robust quarantine strategy.•Extreme quarantine measures, including sealing off large cities, closing borders and confining people to their homes are critical to stemming spread of the virus.•Pyroptosis, a novel form of inflammatory cell death, is a possible mechanism for the increased virulence of the SARS-CoV-2.
The global death toll from coronavirus disease (COVID-19) virus as of May 12, 2020, exceeds 286,000. The risk factors for death were attributed to advanced age and comorbidities but have not been ...accurately defined.
To report the clinical features of 85 fatal cases of COVID-19 in two hospitals in Wuhan.
Medical records were collected of 85 fatal cases of COVID-19 between January 9, 2020, and February 15, 2020. Information recorded included medical history, exposure history, comorbidities, symptoms, signs, laboratory findings, computed tomographic scans, and clinical management.
The median age of the patients was 65.8 years, and 72.9% were male. Common symptoms were fever (78 91.8%), shortness of breath (50 58.8%), fatigue (50 58.8%), and dyspnea (60 70.6%). Hypertension, diabetes, and coronary heart disease were the most common comorbidities. Notably, 81.2% of patients had very low eosinophil counts on admission. Complications included respiratory failure (80 94.1%), shock (69 81.2%), acute respiratory distress syndrome (63 74.1%), and arrhythmia (51 60%), among others. Most patients received antibiotic (77 90.6%), antiviral (78 91.8%), and glucocorticoid (65 76.5%) treatments. A total of 38 (44.7%) and 33 (38.8%) patients received intravenous immunoglobulin and IFN-α2b, respectively.
In this depictive study of 85 fatal cases of COVID-19, most cases were males aged over 50 years with noncommunicable chronic diseases. The majority of the patients died of multiple organ failure. Early onset of shortness of breath may be used as an observational symptom for COVID-19 exacerbations. Eosinophilopenia may indicate a poor prognosis. A combination of antimicrobial drugs did not offer considerable benefit to the outcome of this group of patients.
Ship detection from remote sensing imagery is very important, with a wide array of applications in areas such as fishery management, vessel traffic services, and naval warfare. This paper focuses on ...the issue of ship detection from spaceborne optical images (SDSOI). Although advantages of synthetic-aperture radar (SAR) result in that most of current ship detection approaches are based on SAR images, disadvantages of SAR still exist, such as the limited number of SAR sensors, the relatively long revisit cycle, and the relatively lower resolution. With the increasing number of and the resulting improvement in continuous coverage of the optical sensors, SDSOI can partly overcome the shortcomings of SAR-based approaches and should be investigated to help satisfy the requirements of real-time ship monitoring. In SDSOI, several factors such as clouds, ocean waves, and small islands affect the performance of ship detection. This paper proposes a novel hierarchical complete and operational SDSOI approach based on shape and texture features, which is considered a sequential coarse-to-fine elimination process of false alarms. First, simple shape analysis is adopted to eliminate evident false candidates generated by image segmentation with global and local information and to extract ship candidates with missing alarms as low as possible. Second, a novel semisupervised hierarchical classification approach based on various features is presented to distinguish between ships and nonships to remove most false alarms. Besides a complete and operational SDSOI approach, the other contributions of our approach include the following three aspects: 1) it classifies ship candidates by using their class probability distributions rather than the direct extracted features; 2) the relevant classes are automatically built by the samples' appearances and their feature attribute in a semisupervised mode; and 3) besides commonly used shape and texture features, a new texture operator, i.e., local multiple patterns, is introduced to enhance the representation ability of the feature set in feature extraction. Experimental results of SDSOI on a large image set captured by optical sensors from multiple satellites show that our approach is effective in distinguishing between ships and nonships, and obtains a satisfactory ship detection performance.
Despite much advance obtained in hyperspectral image sensors, they are still very sensitive to the noise, and thus cause the captured data to carry enough noise to degrade the classification results. ...The traditional approach first resorts to image denoising and then feeds the denoised image into a classifier. However, such a straightforward approach, treating denoising and classification separately, suffers greatly from neglecting their impacts on each other. This paper presents a new simultaneous denoising and classification method in the pursuit of cleanest image for optimal classification in the sense of given task evaluation measures. To obtain this objective, we develop a hybrid conditional random field (CRF) (for denoising) and multinomial logistic regression (MLR) (for classification) model at first, and then to train the proposed hybrid model, we propose a new joint learning method, which can effectively capture the impacts of denoising on classification, or vice versa, the effects of classification on denoising. Through the proposed joint learning method, the CRF and MLR, and thus the denoising and classification procedure, can be tightly combined. Moreover, the proposed joint learning method can directly optimize a large class of application specific performance measures including both the linear measures, such as the overall accuracy, and the nonlinear measures, such as kappa statistics. Meanwhile, the consistency between the criteria of model learning and model application has the potential to obtain the denoised image, which is at its best for optimal classification in the sense of the given measure. The extensive experiments of simultaneous denoising and classification tasks are conducted in both simulated and real noisy conditions to test our jointly learned model, which are shown to outperform the conventional methods of treating the two tasks independently.
Denoising of hyperspectral imagery in the domain of imaging spectroscopy by conditional random fields (CRFs) is addressed in this work. For denoising of hyperspectral imagery, the strong dependencies ...across spatial and spectral neighbors have been proved to be very useful. Many available hyperspectral image denoising algorithms adopt multidimensional tools to deal with the problems and thus naturally focus on the use of the spectral dependencies. However, few of them were specifically designed to use the spatial dependencies. In this paper, we propose a multiple-spectral-band CRF (MSB-CRF) to simultaneously model and use the spatial and spectral dependencies in a unified probabilistic framework. Furthermore, under the proposed MSB-CRF framework, we develop two hyperspectral image denoising algorithms, which, thanks to the incorporated spatial and spectral dependencies, can significantly remove the noise, while maintaining the important image details. The experiments are conducted in both simulated and real noisy conditions to test the proposed denoising algorithms, which are shown to outperform the popular denoising methods described in the previous literatures.
Hyperspectral images exhibit strong dependencies across spatial and spectral neighbors, which have been proved to be very useful for hyperspectral image classification. State-of-the-art hyperspectral ...image classification algorithms use the dependencies in a heuristic way or in probabilistic frameworks but impose unreasonable assumptions on observed data. In this paper, we formulate a conditional random field (CRF) to replace such heuristics and unreasonable assumptions for the classification of hyperspectral images. Moreover, because of avoiding explicit modeling of the observed data, the proposed method can incorporate the classification of hyperspectral images with different statistics characteristics into a unified probabilistic framework. Since the usual classification task for hyperspectral images needs the proposed CRF to be trained on local samples, available global training methods cannot be directly used. Under piecewise training framework, this paper develops an efficient local method to train the CRF. It is efficiently implemented through separated trainings of simple classifiers defined by corresponding potentials. However, the independent classifier trainings may lead to over-counting problems during inference. So we further propose a strategy to combine the independently trained models to obtain final CRF model. Experiments on real-world hyperspectral data show that our algorithm is competitive with the most recent results in hyperspectral image classification.
Objective
To update evidence‐based recommendations for the treatment of patients with ankylosing spondylitis (AS) and nonradiographic axial spondyloarthritis (SpA).
Methods
We conducted updated ...systematic literature reviews for 20 clinical questions on pharmacologic treatment addressed in the 2015 guidelines, and for 26 new questions on pharmacologic treatment, treat‐to‐target strategy, and use of imaging. New questions addressed the use of secukinumab, ixekizumab, tofacitinib, tumor necrosis factor inhibitor (TNFi) biosimilars, and biologic tapering/discontinuation, among others. We used the Grading of Recommendations, Assessment, Development and Evaluation methodology to assess the quality of evidence and formulate recommendations and required at least 70% agreement among the voting panel.
Results
Recommendations for AS and nonradiographic axial SpA are similar. TNFi are recommended over secukinumab or ixekizumab as the first biologic to be used. Secukinumab or ixekizumab is recommended over the use of a second TNFi in patients with primary nonresponse to the first TNFi. TNFi, secukinumab, and ixekizumab are favored over tofacitinib. Co‐administration of low‐dose methotrexate with TNFi is not recommended, nor is a strict treat‐to‐target strategy or discontinuation or tapering of biologics in patients with stable disease. Sulfasalazine is recommended only for persistent peripheral arthritis when TNFi are contraindicated. For patients with unclear disease activity, spine or pelvis magnetic resonance imaging could aid assessment. Routine monitoring of radiographic changes with serial spine radiographs is not recommended.
Conclusion
These recommendations provide updated guidance regarding use of new medications and imaging of the axial skeleton in the management of AS and nonradiographic axial SpA.
In this paper, the impacts of interface traps on tunneling FET (TFET) are examined in terms of different trap energies and distributions, charge neutrality level (CNL), and effects of random trap ...fluctuation, in comparison with MOSFET. It is found that the V th shifts and subthreshold swing (SS) degradation induced by interface traps in TFET and MOSFET have the same trends, but the impacts on I ON are different because of the novel conduction mechanism of TFETs when compared with MOSFETs. Moreover, nTFET is intrinsically more immune (or susceptible) to V th shift induced by acceptor(or donor-) type interface traps than nMOSFET. Therefore, reducing the potential degradation induced by the interface traps can be achieved by optimizing the position of CNL. The results indicate that nTFET is more immune to the V th shift than nMOSFET with CNL below a critical energy. In addition, the trap-induced SS degradation of TFET is severer than MOSFET in electrostatics. Moreover, it is found that the I ON , V th , and IOFF fluctuations in nMOSFET and nTFET are also dependent on the position of CNL. With CNL below the critical energy, the I ON fluctuation and V th fluctuation of nTFET are smaller than those of nMOSFET. The results are helpful for the interface optimization of TFETs.
This paper proposes to improve the classification accuracy of hyperspectral data with support vector machines (SVMs) by using stacked generalization (stacking) as well as the complementary ...information of magnitude and shape feature spaces. Stacking is a method to combine multiple classifiers by learning a meta-level (or level-1) classifier from the outputs of base-level (or level-0) classifiers (estimated via cross-validation). In the processing of hyperspectral data, magnitude features are the radiance values at different sensor bands, whereas shape features are the differences in direction rather than the magnitude of the spectral signatures. In particular, the proposed method is as follows: (1) SVMs trained in magnitude and shape feature spaces are adopted as level-0 classifiers (termed as level-0 SVMs); (2) outputs (decision values) of the level-0 SVMs are used as inputs (termed as meta-level features) of level-1 classifier, since the decision values contain much more information than class labels; (3) level-1 classifier adopts SVMs (level-1 SVMs) trained in the meta-level feature space. In addition, we also discuss the possibility of reducing the number of level-0 SVMs by meta-level feature selection and present one simple solution. Experiments on a benchmark hyperspectral data set demonstrate that our method significantly outperforms the methods with the single feature space and other combining methods, namely, simple voting, absolute maximum decision value, and stacking with class labels.