Search

To date, accurate building footprint delineation in the surveying, mapping and geographic information system (GIS) communities has been dependent on human labor. In this paper, to address this issue, we propose a concentric loop convolutional neural network (CLP-CNN) method for the automatic segmentation of building boundaries from remote sensing images. The proposed method consists of three components: 1) a boundary detector to extract coarse polygonal boundaries of individual regions of interest; 2) a concentric loop shaped convolutional network with bidirectional pairing loss to fine-tune the vertices of the polygons; and 3) a refinement block, which removes redundant vertices and regularizes the boundaries to polygons at the manual delineation level. We also demonstrate that the proposed CLP-CNN method is applicable to other generic objects in natural images. Experiments on two building datasets confirmed that more than 77%/67% of the building polygons predicted by the proposed method are on par with the manual delineation level, representing a significant saving in the labor cost of manual annotation. In generic object boundary delineation tests performed on the Semantic Boundaries Dataset (SBD), the proposed method outperformed the most recent state-of-the-art methods by at least 3.1% in average precision (AP). Furthermore, compared with other vertex matching methods, the learning process of the proposed method converges faster. The source code will be available at http://gpcv.whu.edu.cn/data.

With the rapid development of computer science and information technology, artificial intelligence (AI) has been developed from theory to application. As a key technology in the modern society, AI is increasingly affecting all aspects of people’s daily lives, including sports training. AI can be considered as an assistive technology to provide specific support to athletes’ physical education training through various means such as data analysis and simulation of training scenarios. Although research on AI is still in the preliminary stage, it is significant to explore how AI can be applied in sports training since this emerging technology could facilitate people’s physical training to some extent. This paper first reviews the existing research on AI applications. Then, based on the fundamental concept and related research results of AI, this study explores three specific cases of AI application in sports training and explains the main principles. This research focuses on discussing the strong relationship between AI technology and physical education training and highlights the advantages of AI, including utilization, convenience, and innovation.

Online classroom teaching is difficult to identify students’ learning status in real time. Therefore, we need to combine intelligent image recognition technology to analyze student status through eye movement features. This study solves the problem of inaccurate positioning of the initial position of the shape model in the process of eyelid matching through machine learning. Moreover, this study improves the algorithm and uses the AK-EYE model based on the combination of ASM algorithm and Kalman filtering to establish a local feature model for each feature point. According to the gray information in the normal direction of the feature point, the local gray information is modeled. After training through the sample set to obtain the state model, the target eye can be searched, and the pose parameters can be determined. Finally, this study designs a control experiment to analyze the performance of the model proposed in this study. The research shows that the algorithm proposed in this paper has a high recognition accuracy and has a practical basis, which can be used as one of the subsequent classroom teaching system algorithms.

The study presented in this paper introduced a new fully automatic three-dimensional building reconstruction method that can generate first level of detail (LoD 1) building models from multi-view aerial images without any assistance from other data. The accuracy and completeness of our reconstructed models have approached that of manually delineated models to a large extent. The presented method consists of three parts: (1) efficient dense matching and Earth surface reconstruction, (2) reliable building footprint extraction and polygon regularization, and (3) highly accurate height inference of building roofs and bases. First, our novel deep learning-based multi-view matching method, composed of a convolutional neural network, gated recurrent convolutions, and a multi-scale pyramid matching structure, is used to reconstruct the digital surface model (DSM) and digital orthophoto map (DOM) efficiently without generating epipolarly rectified images. Second, our three-stage 2D building extraction method is introduced to deliver reliable and accurate building contours. Deep-learning based segmentation, assisted with DSM, is used to segment buildings from backgrounds; and the generated building maps are fused with a terrain classification algorithm to reach better segmentation results. A polygon regularization algorithm and a level set algorithm are thereafter employed to transfer the binary segmentation maps to structured vector-form building polygons. Third, a novel method is introduced to infer the height of building roofs and bases using adaptive local terrain filtering and neighborhood buffer analysis. We tested our method on a large experimental area that covered 2284 aerial images and 782 various types of buildings. Our results as far as correctness and completeness exceeded the results of other similar methods in a between-method comparison by at least 15% for individual 3D building models with many of them comparable to manual delineation results.

Highlights • We tested 12 air and 355 surface samples in a hospital for SARS-CoV-2. • Only one air sample taken during the intubation procedure tested positive. • Low level of surface contamination was found, most occurred in high-touch surfaces. • No association was found between surface contamination and patient characteristics., Background Few studies have explored the air and surface contamination by SARS-CoV-2 virus in healthcare settings. Methods We collected air and surface samples from the isolation wards and intensive care units designated for COVID-19 patients. The clinical data and tests result of nasopharyngeal specimens and serum antibodies were also collected from the sampling patients. Results A total of 367 air and surface swabbing samples were collected from the patient care areas of 15 mild and 9 severe/critical COVID-19 patients. Only one air sample taken during the intubation procedure tested positive. High-touch surfaces were slightly more likely contaminated by the RNA of the SARS-CoV-2 virus than low-touch surfaces. Contamination rates was slightly higher near severe/critical patients compared to those near mild patients, although not statistically significant (p

Clubroot is an important disease of cruciferous crops caused by Plasmodiophora brassicae, and pathotypes are classified based on the response of differential hosts. This study was conducted to identify genetic markers able to differentiate pathotypes. Differential expression of genes between pathotype 4 (P4) and pathotype 7 (P7) was assessed according to transcriptome data of molecular marker screening. Among the pathotypes (P2, P4, P5, P7, P9, P10, and P11) tested, six genes were exclusive to P4, dividing the isolates into three types: PBRA_003263 and PBRA_003268 were present in all P4 isolates, PBRA_000003/Novel512 were found in a type of P4 (P4-1), and Novel137/PBRA_005772 were found in another P4 type, P4-2. Amplicons for all six genes were produced for only one isolate, which we named P4-3. This study is the first to establish a molecular identification system for P4 the, predominant pathotype in China. The genes identified might serve as molecular markers for differentiation of P4 from other pathotypes and may also distinguish different types of P4.

The application of the convolutional neural network has shown to greatly improve the accuracy of building extraction from remote sensing imagery. In this paper, we created and made open a high-quality multisource data set for building detection, evaluated the accuracy obtained in most recent studies on the data set, demonstrated the use of our data set, and proposed a Siamese fully convolutional network model that obtained better segmentation accuracy. The building data set that we created contains not only aerial images but also satellite images covering 1000 km2 with both raster labels and vector maps. The accuracy of applying the same methodology to our aerial data set outperformed several other open building data sets. On the aerial data set, we gave a thorough evaluation and comparison of most recent deep learning-based methods, and proposed a Siamese U-Net with shared weights in two branches, and original images and their down-sampled counterparts as inputs, which significantly improves the segmentation accuracy, especially for large buildings. For multisource building extraction, the generalization ability is further evaluated and extended by applying a radiometric augmentation strategy to transfer pretrained models on the aerial data set to the satellite data set. The designed experiments indicate our data set is accurate and can serve multiple purposes including building instance segmentation and change detection; our result shows the Siamese U-Net outperforms current building extraction methods and could provide valuable reference.

An important trend in the personal care industry involves the development of body wash products that not only clean the skin without damage but deposit conditioning ingredients to improve skin barrier function.The objective of this study was to develop skin biomarker measures to quantify the treatment effects of body wash products.We employed analysis of structural proteins (keratin 1,10,11 and involucrin), a natural moisturizing factor (pyrrolidone carboxylic acid) and an inflammatory mediator (IL-1ra/IL-1α) from adhesive discs with dry skin grading, TEWL and capacitance measurements to compare the effects of direct application of petrolatum, a high petrolatum depositing body wash, and a regular body wash on dry leg skin in a standard leg-wash treatment protocol.High depositing body wash and petrolatum had positive effects on stratum corneum barrier function as judged by biomarker analysis, biophysical measurements and skin grading compared to the regular body wash product.The results clearly indicate that a combination of biomarker and biophysical property measurements is effective for determining the skin benefits of moisturizing body wash products.Une tendance importante dans l’industrie des soins personnels inclut le développement de produits de lavage corporel qui non seulement nettoient la peau sans l’endommager, mais déposent des ingrédients de traitement pour améliorer la fonction de la barrière cutanée.L’objectif de cette étude était de développer des mesures de biomarqueurs cutanés permettant de quantifier les effets du traitement des produits de lavage corporel. MÉTHODES: Nous avons utilisé l’analyse de protéines structurelles (kératine 1,10,11 et involucrine), un facteur hydratant naturel (acide carboxylique de pyrrolidone) et un médiateur inflammatoire (IL-1ra/IL-1a) provenant de disques adhésifs avec cotation de la sécheresse cutanée, mesures de perte d’eau transépidermique (transepidermal water loss, TEWL) et de capacitance pour comparer les effets de l’application directe de vaseline, d’un produit de lavage corporel avec dépôt élevé de vaseline et d’un produit de lavage corporel ordinaire sur la peau sèche des jambes, dans un protocole de traitement de lavage des jambes standard. RÉSULTATS: Le produit de lavage corporel à dépôt élevé et la vaseline avaient des effets positifs sur la fonction de barrière de la couche cornée, comme évalué par l’analyse des biomarqueurs, les mesures biophysiques et la cotation de la peau, comparé au produit de lavage corporel ordinaire.Les résultats indiquent clairement qu’une combinaison de mesures des biomarqueurs et des propriétés biophysiques est efficace pour déterminer les bienfaits pour la peau des produits de lavage corporel hydratants.

In this work, a novel automatic 3D building reconstruction approach is proposed to extract accurate LoD1 building models from multi-view aerial images. The proposed approach consists of three main parts. The first step is to generate digital surface models (DSMs) from aerial images, which is implemented with the Smart3D software and can be replaced by other open-source multi-view stereo (MVS) algorithms as well. The second step is to produce structured 2D building footprints using combined deep learning and regularization. The initial building segmentation maps are obtained by the multi-scale aggregation fully convolutional network (MA-FCN), which takes both the images and DSM as input, through supervised learning. The initial segmentation maps are further refined with another segmentation maps that are derived from the DSM. After that, the contour extraction and regularization technology are applied to produce structured building footprints. In the last step, the elevations of the top and base of each individual building are reliably estimated by adopting an adaptive terrain generation approach and the neighbourhood buffer analysis. The georeferenced building footprint polygons and the elevations of building top and base form the watertight LoD1 building models. The qualitative and quantitative evaluations in Jinghai District, Tianjin, China demonstrate the robustness and effectiveness of the proposed approach.

Both long non-coding RNA (lncRNA) RMRP and heat shock protein (HSP) 70 have been known to play crucial roles in inflammation. The present study investigated the roles of lncRNA RMRP and HSP70 protein 4 (HSPA4) in lipopolysaccharide (LPS)-induced sepsis. The C57BL/6 mice were treated with LPS, following which the cardiomyocytes were isolated for in vitro experiments. Further, a cardiac muscle cell line, HL-1 was transfected with plasmids expressing RMRP and HSPA4, si-NC, si-HSPA4, miR-1-5p mimic, and controls in vitro. Cell apoptosis, mitochondrial membrane potential (MMP), and levels of intracellular reactive oxygen species (ROS), mRNAs, and proteins were detected in the transfected mice tissues and cells. The LPS treatment significantly reduced the expression levels of RMRP, MMP, and mitochondrial cytochrome C. Moreover, it enhanced the cardiomyocyte apoptosis, intracellular ROS levels, cytoplasm cytochrome C levels, and the expression of caspase-3 and caspase-9 and nuclear factor κB (NF-κB) p65 subunit. The predicted RMRP-miR-1-5p-HSPA4 network was validated by co-transfection experiments in vitro in HL-1 cells. The transfection of miR-1-5p-treated cells with pcDNA-RMRP enhanced the levels of the protein HSPA4; however, no change at the mRNA level was observed. Moreover, miR-1-5p mimic attenuated the protective effect of pcDNA-HSPA4 against LPS-induced mitochondrial damage and apoptosis. In addition, we observed that silencing of HSPA4 increased the expression of nuclear p65; however, this effect could be reversed by co-transfection with pcDNA-RMRP. The lncRNA RMRP axis acts as a sponge for miR-1-5p. RMRP inhibits LPS-induced apoptosis of cardiomyocytes and mitochondrial damage by suppressing the post-transcriptional regulatory function of miR-1-5p on HSPA4. We believe that RMRP exhibits therapeutic potential for LPS-induced myocardial dysfunction both in vitro and in vivo.

Visual perception plays an important role when underwater robots carry out missions under the sea. However, the quality of images captured by visual sensors is often affected by underwater environment conditions. Image super-resolution is an effective way to enhance the resolution of underwater images. In this paper, we propose a novel method for underwater image super-resolution. The proposed method uses CNNs with channel-wise attention to learn a mapping from low-resolution images to high-resolution images. And a progressive training strategy is used to deal with large scaling factors (e.g. 4x and 8x) of super-resolution. We name our method as Progressive Attentional Learning (PAL). Experiments on a recently published underwater image super-resolution dataset, USR-248 [11], show the superiority of our method over other state-of-the-art methods.

To compare the clinical effect of prophylactic cervical cerclage and therapeutic cervical cerclage on pregnancy outcome and operative factors in cervical insufficiency pregnant women. A retrospective study was conducted between June 2014 and September 2016 in a maternity ward, which included women who have had a single pregnancy and have been carried out a McDonald cerclage. All maternal medical records were reviewed. The efficacy of cerclage for preventing late foetal loss was assessed using multivariable logistic regression analysis. The results showed that there were significant associations between cerclage operations and pregnancy outcomes in the duration of pregnancy prolongation in terms of live births, gestation age, live birth and cesarean section rate. In prophylactic cervical cerclage, compared with therapeutic cervical cerclage, cervical length before surgery was significantly longer (32.7 ± 5.8 vs 19.9 ± 7.3 mm, p

Development of this in vivo confocal Raman spectroscopic method enables the direct measurement of water, proteins, and lipids with depth resolution in human subjects. This information is very important for skin-related diseases and characterizing skin care product performance. This protocol illustrates a method for confocal Raman spectra collection and the subsequent analysis of the spectral dataset leveraging chemometrics. The goal of this method is to establish a standard protocol for data collection and provide general guidance for data analysis. Preprocessing (e.g., removal of outlier spectra) is a critical step when processing large datasets from clinical studies. As an example, we provide guidance based on prior knowledge of a dataset to identify the types of outliers and develop specific strategies to remove them. A principal component analysis is performed, and the loading spectra are compared with spectra from reference materials to select the number of components used in the final multivariate curve resolution (MCR) analysis. This approach is successful for extracting meaningful information from a large spectral dataset.

MiSH, which is based on the skin microbiome, can quantitatively assess pediatric skin health across cohorts from distinct countries over large geographic distances. Moreover, the index can identify a risk-prone skin state and compare treatment effect in children, suggesting applications in diagnosis and patient stratification., A quantitative and objective indicator for skin health via the microbiome is of great interest for personalized skin care, but differences among skin sites and across human populations can make this goal challenging. A three-city (two Chinese and one American) comparison of skin microbiota from atopic dermatitis (AD) and healthy pediatric cohorts revealed that, although city has the greatest effect size (the skin microbiome can predict the originated city with near 100% accuracy), a microbial index of skin health (MiSH) based on 25 bacterial genera can diagnose AD with 83 to ∼95% accuracy within each city and 86.4% accuracy across cities (area under the concentration-time curve [AUC], 0.90). Moreover, nonlesional skin sites across the bodies of AD-active children (which include shank, arm, popliteal fossa, elbow, antecubital fossa, knee, neck, and axilla) harbor a distinct but lesional state-like microbiome that features relative enrichment of Staphylococcus aureus over healthy individuals, confirming the extension of microbiome dysbiosis across body surface in AD patients. Intriguingly, pretreatment MiSH classifies children with identical AD clinical symptoms into two host types with distinct microbial diversity and treatment effects of corticosteroid therapy. These findings suggest that MiSH has the potential to diagnose AD, assess risk-prone state of skin, and predict treatment response in children across human populations. IMPORTANCE MiSH, which is based on the skin microbiome, can quantitatively assess pediatric skin health across cohorts from distinct countries over large geographic distances. Moreover, the index can identify a risk-prone skin state and compare treatment effect in children, suggesting applications in diagnosis and patient stratification.

Background It acknowledged that skin care is an important part of atopic dermatitis therapy. However, clinical evidences are limited for the best bathing practices, especially the skin health performance of cleansing products on children's atopic dermatitis skin. Methods A randomised controlled clinical study was conducted in China among 4- to 18-year-old children with mild-to-moderate atopic dermatitis to evaluate the skin health effect of three cleansing systems (a mild synthetic bar, an ultra-mild body wash with lipids, and an ultra-mild body wash with lipids and zinc pyrithione) by measuring SCORing of Atopic Dermatitis (SCORAD), consumption of topical corticosteroid and the characteristics of microbiome. Results Increased Staphylococcus aureus abundance and decreased microbial diversity were observed in atopic dermatitis lesion sites compared with healthy control sites. After 4 weeks of treatment, all three treatments showed clinically important improvement from baseline in SCORAD. Four-week corticosteroid consumption was significantly lower for the two body wash groups than the bar group. A significant decrease in S. aureus abundance and increase in microbial diversity were observed in the lesion sites for the two body wash formulas, while the microbial diversity was statistically insignificant for the mild cleansing bar group. However, there were no incremental benefits provided by the body wash formulas based on the assessment of SCORAD. Conclusions These results demonstrated the safety and efficacy of using the investigational body wash formulas with lipids in reducing the needs for corticosteroid and improving the healthy composition of skin microbiome vs. the mild synthetic bar soap.

Confocal Raman has been widely used for measuring the water concentration profile inside skin to calculate clinical end points, such as stratum corneum thickness. In this article, multivariate curve resolution was applied to resolve the pure components contained in high frequency (2500-4000 cm-1) in vivo confocal Raman data. Three components were identified by comparing with reference spectra of materials in skin. These three components are water, protein, and lipid. The score values associated with these three components were transformed to mass ratio by leveraging the response factors for protein and lipid in a calibration model utilizing the pure material spectra. The concentration profiles for protein and lipid as a function of depth across the stratum corneum are utilized as new clinical end points. Results from an in vivo study with individuals who experience atopic dermatitis symptoms successfully demonstrated a statistical difference between Raman spectra from nonlesion and lesion skin sites. Trends in the depth profiles of the skin components are consistent with previous literature reports.

In this paper, from the perspective of humanism, aiming at the existing buildings in the modern commercial space, the problem of the trap of consumerism, as well as lack of humanistic care in landscape and architecture, the landscape renovation design is carried out. We explored the people psychological experience in the commercial landscape, tried to integrate interactive elements, new materials, various energy savings and other methods into the commercial landscape, so as to improve the relationship between the commercial landscape and people, replace passive appreciation with landscape subjective initiative, further improve the harmonious man-machine environment, and build a beautiful and harmonious landscape environment.

Due to good biocompatibility and mechanical properties, magnesium (Mg) and its alloys are considered as promising degradable materials for orthopedic applications. However, the rapid degradation rate of the magnesium-based implants in vivo has become the main limitation hindering their applications. We report here the successful fabrication of the nano-whisker/wire-like hydroxyapatite (nHA) coatings on Mg alloy (ZK60) substrates for controlling the biodegradation of Mg alloy while improving its cytocompatibility for orthopedic applications, using a simple one-step hydrothermal treatment process in aqueous solution. The formation mechanism of HA coatings on Mg substrate is discussed in details. The surface morphology and microstructure of the coatings can be regulated by varying the deposition time. The biodegradation of ZK60 alloy was greatly restrained by the nano-whisker/wire-like HA coatings. Improved cytocompatibility was observed in nano-whisker/wire-like HA coated ZK60 samples and the cytotoxicity of ZK60 samples coated for 2 and 2.5 h are in grade 1. Results indicate that coatings with nano-whisker/wire-like HA are promising for improving the in vitro biodegradation and cytocompatibility properties of Mg-based orthopedic implants and devices.

Clubroot disease is an important disease on cruciferous crops caused by Plasmodiophora brassicae infections. The pathotypes have been classified based on the reactions of differential hosts. However, molecular markers of particular pathotypes for P. brassicae are limited. In this study, we found five genetic markers in association with different pathotypes. Different gene expression patterns among different pathotypes (P4, P7, P9, and P11) were assayed according to the transcriptome data. The assay indicated that molecular markers PBRA_007750 and PBRA_009348 could be used to distinguish P11 from P4, P7, and P9; PBRA_009348 and Novel342 could distinguish P9 from P4, P7, and P11; and PBRA_008439 and Novel342 could represent a kind of P4. Polymerase chain reaction cycles ranging from 25 to 30 were able to identify the predominant pathotype in general. Therefore, these molecular markers would be a valuable tool to identify and discriminate pathotypes in P. brassicae population.