Explore the vast range of titles available.

This paper presents a new 3D point cloud classification benchmark data set with over four billion manually labelled points, meant as input for data-hungry (deep) learning methods. We also discuss first submissions to the benchmark that use deep convolutional neural networks (CNNs) as a work horse, which already show remarkable performance improvements over state-of-the-art. CNNs have become the de-facto standard for many tasks in computer vision and machine learning like semantic segmentation or object detection in images, but have no yet led to a true breakthrough for 3D point cloud labelling tasks due to lack of training data. With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks. Our semantic3D.net data set consists of dense point clouds acquired with static terrestrial laser scanners. It contains 8 semantic classes and covers a wide range of urban outdoor scenes: churches, streets, railroad tracks, squares, villages, soccer fields and castles. We describe our labelling interface and show that our data set provides more dense and complete point clouds with much higher overall number of labelled points compared to those already available to the research community. We further provide baseline method descriptions and comparison between methods submitted to our online system. We hope semantic3D.net will pave the way for deep learning methods in 3D point cloud labelling to learn richer, more general 3D representations, and first submissions after only a few months indicate that this might indeed be the case.

This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental principles is to gradually aggregate information over larger and larger image regions, making it hard to disentangle contributions from different pixels. Very recently two extensions of the CNN framework have made it possible to trace the semantic information back to a precise pixel position: deconvolutional network layers undo the spatial downsampling, and Fully Convolution Networks (FCNs) modify the fully connected classification layers of the network in such a way that the location of individual activations remains explicit. We design a FCN which takes as input intensity and range data and, with the help of aggressive deconvolution and recycling of early network layers, converts them into a pixelwise classification at full resolution. We discuss design choices and intricacies of such a network, and demonstrate that an ensemble of several networks achieves excellent results on challenging data such as the ISPRS semantic labeling benchmark, using only the raw data as input.

Surgery is a valuable option for pharmacologically intractable epilepsy. However, significant post-operative improvements are not always attained. This is due in part to our incomplete understanding of the seizure generating (ictogenic) capabilities of brain networks. Here we introduce an in silico , model-based framework to study the effects of surgery within ictogenic brain networks. We find that factors conventionally determining the region of tissue to resect, such as the location of focal brain lesions or the presence of epileptiform rhythms, do not necessarily predict the best resection strategy. We validate our framework by analysing electrocorticogram (ECoG) recordings from patients who have undergone epilepsy surgery. We find that when post-operative outcome is good, model predictions for optimal strategies align better with the actual surgery undertaken than when post-operative outcome is poor. Crucially, this allows the prediction of optimal surgical strategies and the provision of quantitative prognoses for patients undergoing epilepsy surgery.

Forest fires have devastating effects on biodiversity, climate, and humans. Producing detailed and reliable forest fire susceptibility maps is crucial for disaster management. Data-driven machine learning methods can be applied for forest fire susceptibility mapping, and learning data required for this purpose can be obtained from high-resolution satellite imagery along with a fire inventory. In this study, we assessed the performances of Random Forest (RF) and artificial neural network (ANN) classifiers for producing forest fire susceptibility maps of a region in north-east Türkiye covering Trabzon, Gümüşhane, Rize, and Bayburt provinces using freely available Earth observation data and forest inventory provided by the regional directorate. Forest type, EU-DEM v1.1 (25 m), and tree cover density were retrieved from Copernicus Land Monitoring Service. Sentinel-2 images were utilized for calculating spectral indices such as normalized difference vegetation index and modified normalized difference water index to assess surface water and vegetation characteristics. Thus, a total of twelve variables including topographic, anthropogenic, hydrologic, vegetation and land use data were used as input. The RF and ANN illustrated similar prediction performances based on receiver operating characteristics (ROC) area under the curve (AUC) values, which were 0.89 and 0.88, respectively. The RF performed better in terms of overall accuracy and F-1 score. The susceptibility maps with 25 m resolution were also investigated visually. The ANN results predicted higher susceptibility levels and larger areas were found prone to wildfire. Leave-one-out analysis results indicated that elevation was the most influential factor based on the achieved OA.

With a growing number of patients entering the recovery phase following infection with SARS-CoV-2, understanding the long-term neurological consequences of the disease is important to their care. The neurological complications of post-acute sequelae of SARS-CoV-2 infection (NC-PASC) represent a myriad of symptoms including headaches, brain fog, numbness/tingling, and other neurological symptoms that many people report long after their acute infection has resolved. Emerging reports are being published concerning COVID-19 and its chronic effects, yet limited knowledge of disease mechanisms has challenged therapeutic efforts. To address these issues, we review broadly the literature spanning 2020–2022 concerning the proposed mechanisms underlying NC-PASC, outline the long-term neurological sequelae associated with COVID-19, and discuss potential clinical interventions.

Flood disturbance is one of the major factors impacting riparian vegetation on river floodplains. In this study we use a high-resolution ground-based camera system with near-infrared sensitivity to quantify the immediate response of riparian vegetation in an Alpine, gravel bed, braided river to flood disturbance with the use of vegetation indices. Five large floods with return periods between 1.4 and 20.1 years in the period 2008–2011 in the Maggia River were analysed to evaluate patterns of vegetation response in three distinct floodplain units (main bar, secondary bar, transitional zone) and to compare the sensitivity of seven broadband vegetation indices. The results show both a negative (damage) and positive (enhancement) response of vegetation within 1 week following the floods, with a selective impact determined by pre-flood vegetation vigour, geomorphological setting and intensity of the flood forcing. The spatial distribution of vegetation damage provides a coherent picture of floodplain response in the three floodplain units. The vegetation indices tested in a riverine environment with highly variable surface wetness, high gravel reflectance, and extensive water–soil–vegetation contact zones differ in the direction of predicted change and its spatial distribution in the range 0.7–35.8%. We conclude that vegetation response to flood disturbance may be effectively monitored by terrestrial photography with near-infrared sensitivity, with potential for long-term assessment in river management and restoration projects.

This study aimed to explore the association between the impaired nutritional status and frailty in acute hospitalised elderly patients by using two tools, the MNA®-SF (Mini Nutritional Assessment® short-form) and the SHARE-FI (Frailty Instrument for Primary Care of the Survey of Health, Ageing and Retirement in Europe). Cross-sectional study. Acute hospitalised, community-dwelling elderly patients were recruited at internal medicine wards in Vienna, Austria. 133 men (39%) and women (61%) aged 74 (65–97) years. MNA®-SF was used to investigate malnutrition (<7 points) and patients at risk of malnutrition (8 to 11 points). By using the SHARE-FI, subjects were classified as frail, pre-frail or robust. A factor analysis was applied to identify overlaps between the MNA®-SF and SHARE-FI items. Internal consistency of different dimensions was assessed by using Cronbach's Alpha. Malnutrition or risk of malnutrition was found in 76.7% of the total sample and in 46.8% of robust, in 69.0% of pre-frail, and in 93.0% of frail participants. Frailty or prefrailty was found in 75.9% of the total sample and in 45.1% of the subjects with no risk of malnutrition, in 80.9% of subjects at risk of malnutrition, and in 94.1% of malnourished patients. The two used tools show overlaps in three dimensions: (1) nutrition problems, (2) mobility problems and (3) anthropometric items with a moderate to strong internal consistency (Cronbach's Alpha of 0.670, 0.834 and 0.946, respectively). 64.7% of the total sample (79.5% of frail and 87.9% of malnourished subjects) would participate in a home-based muscle training and nutritional intervention program. This study underlines the association and the overlap between frailty and impaired nutritional status. There is a high readiness to participate in a program to tackle the problems associated with malnutrition and frailty, especially in those, who would benefit most from it.

The sufficient stability criterion of the collisionless ion tearing mode in the magnetotail current sheet, which was first obtained by Lembege and Pellat in 1982, is considered. For many conventional 2D current sheet equilibria, this criterion is satisfied within the WKB approximation, which is commonly interpreted as stability of those equilibria with respect to tearing. However, this is not necessarily the case for equilibria with more than two characteristic spatial scales. An example for substantial tearing destabilization of an equilibrium with accumulation of the magnetic flux at the tailward end of a thin current sheet is presented. Similar equilibria are reported in Geotail and THEMIS observations prior to onsets of magnetospheric substorms and dipolarization fronts associated with bursty bulk flows.

Pathogens, particularly human herpesviruses (HHVs), are implicated as triggers of disease onset/progression in multiple sclerosis (MS) and other neuroinflammatory disorders. However, the time between viral acquisition in childhood and disease onset in adulthood complicates the study of this association. Using nonhuman primates, we demonstrate that intranasal inoculations with HHV-6A and HHV-6B accelerate an MS-like neuroinflammatory disease, experimental autoimmune encephalomyelitis (EAE). Although animals inoculated intranasally with HHV-6 (virus/EAE marmosets) were asymptomatic, they exhibited significantly accelerated clinical EAE compared with control animals. Expansion of a proinflammatory CD8 subset correlated with post-EAE survival in virus/EAE marmosets, suggesting that a peripheral (viral?) antigen-driven expansion may have occurred post-EAE induction. HHV-6 viral antigen in virus/EAE marmosets was markedly elevated and concentrated in brain lesions, similar to previously reported localizations of HHV-6 in MS brain lesions. Collectively, we demonstrate that asymptomatic intranasal viral acquisition accelerates subsequent neuroinflammation in a nonhuman primate model of MS.

Modelling rainfall–runoff in urban areas is increasingly applied to support flood risk assessment, particularly against the background of a changing climate and an increasing urbanization. These models typically rely on high-quality data for rainfall and surface characteristics of the catchment area as model input. While recent research in urban drainage has been focusing on providing spatially detailed rainfall data, the technological advances in remote sensing that ease the acquisition of detailed land-use information are less prominently discussed within the community. The relevance of such methods increases as in many parts of the globe, accurate land-use information is generally lacking, because detailed image data are often unavailable. Modern unmanned aerial vehicles (UAVs) allow one to acquire high-resolution images on a local level at comparably lower cost, performing on-demand repetitive measurements and obtaining a degree of detail tailored for the purpose of the study. In this study, we investigate for the first time the possibility of deriving high-resolution imperviousness maps for urban areas from UAV imagery and of using this information as input for urban drainage models. To do so, an automatic processing pipeline with a modern classification method is proposed and evaluated in a state-of-the-art urban drainage modelling exercise. In a real-life case study (Lucerne, Switzerland), we compare imperviousness maps generated using a fixed-wing consumer micro-UAV and standard large-format aerial images acquired by the Swiss national mapping agency (swisstopo). After assessing their overall accuracy, we perform an end-to-end comparison, in which they are used as an input for an urban drainage model. Then, we evaluate the influence which different image data sources and their processing methods have on hydrological and hydraulic model performance. We analyse the surface runoff of the 307 individual subcatchments regarding relevant attributes, such as peak runoff and runoff volume. Finally, we evaluate the model's channel flow prediction performance through a cross-comparison with reference flow measured at the catchment outlet. We show that imperviousness maps generated from UAV images processed with modern classification methods achieve an accuracy comparable to standard, off-the-shelf aerial imagery. In the examined case study, we find that the different imperviousness maps only have a limited influence on predicted surface runoff and pipe flows, when traditional workflows are used. We expect that they will have a substantial influence when more detailed modelling approaches are employed to characterize land use and to predict surface runoff. We conclude that UAV imagery represents a valuable alternative data source for urban drainage model applications due to the possibility of flexibly acquiring up-to-date aerial images at a quality compared with off-the-shelf image products and a competitive price at the same time. We believe that in the future, urban drainage models representing a higher degree of spatial detail will fully benefit from the strengths of UAV imagery.