Search

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site’s data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare. Federated learning, a method for training artificial intelligence algorithms that protects data privacy, was used to predict future oxygen requirements of symptomatic patients with COVID-19 using data from 20 different institutes across the globe.

In solar heating, ventilation, and air conditioning (HVAC), communications are designed to create new 3D mathematical models that address the flow of rotating Sutterby hybrid nanofluids exposed to slippery and expandable seats. The heat transmission investigation included effects such as copper and graphene oxide nanoparticles, as well as thermal radiative fluxing. The activation energy effect was used to investigate mass transfer with fluid concentration. The boundary constraints utilized were Maxwell speed and Smoluchowksi temperature slippage. With the utilization of fitting changes, partial differential equations (PDEs) for impetus, energy, and concentricity can be decreased to ordinary differential equations (ODEs). To address dimensionless ODEs, MATLAB’s Keller box numerical technique was employed. Graphene oxide Copper/engine oil (GO-Cu/EO) is taken into consideration to address the performance analysis of the current study. Physical attributes, for example, surface drag coefficient, heat move, and mass exchange are mathematically processed and shown as tables and figures when numerous diverse factors are varied. The temperature field is enhanced by an increase in the volume fraction of copper and graphene oxide nanoparticles, while the mass fraction field is enhanced by an increase in activation energy.

Selection of the number of neurons in different layers of an artificial neural network (ANN) is a key decision-making step involved in its successful training. Although the number of neurons in the input layer is decided by the number of input parameters, and similarly, in the output layer the number of neurons is fixed by the output parameters, however, the number of neurons in the hidden layer is not fixed, whereby the overall efficiency of the ANN depends upon the correct modeling of the realistic scenario in the form of a neural network. Concrete can be mixed in a huge variety of methods and compositions to achieve a specific or a combination of specific results. These results have been observed to repeat and follow patterns. Furthermore, for several types of concrete mixes, only actual physical trial data are available with no mix design method; this makes achieving different required results very complex and expensive task. Having an ANN to be able to predict a concrete mix to handle such variations will save a lot of time and money and will prove to be a universal mix design tool. A thorough analysis for deciding the number of neurons for mix design of concrete has been carried out in this research. The results of neural networks for a varying number of neurons and layers have been correlated. The data for a number of concrete mixes were sorted and normalized. Properties of concrete constituents like specific gravity of cement, coarse and fine aggregates, dry density of coarse and fine aggregates, cement type, type of mineral admixture, water-to-cement ratio, type and temperature of curing and hardened properties like compressive strength, modulus of elasticity and tensile strength were taken as input parameters. The contents of constituents of concrete such as water content, cement content, coarse aggregates content, fine aggregates content and content of mineral admixtures are regarded as output parameters. For 17 inputs and 5 outputs, it has been discovered that simple neural network with single or double hidden layers performed better that 3 or more such layers.

The fluvial knickzones, a geomorphic marker of erosion, climate, and tectonics has received much interest in the topographic developmental studies in the recent past. Nevertheless, examining their spatial distribution in passive margins has not been well documented especially for the drainage basins in the humid tropical climatic systems. Here in this study, we presented the spatial distribution of knickzones in the three river basins of Western Ghats, India, namely Chaliyar, Pambar and Muthirapuzha basins. Because the conventional method of knickzone identification using topographic maps or field readings is laborious, we employed a 30 m digital elevation model and TopoToolBox, a Matlab© based tool to extract the knickpoints in the study area. A total of 356 knickpoints were identified by analyzing ~ 2670 km of river network, and the knickzone frequency is estimated as 0.13 km−1. The average height of the knickzones is found to be 83 m, and majority of the knickpoints are located closest to the headwaters. Although we noticed that the streams underlying metamorphic lithology tends to have the highest knickzone frequency, but it can be also attributed to the fact that metamorphic rocks are the most dominant rock type in the study area. The high amount of knickzone frequency in the study area thus may be the result of coupled climatic control caused by heavy summer rainfall, bed rock erosion triggered by high grade metamorphism, and also the local base level changes as indicated by the clustered knickpoints in the stream heads.

The process of diagnosis, intervention, conservation, restoration and maintenance of built cultural heritage requires complete and accurate knowledge about tangible as well as intangible aspects of their past and present. Comprehensive and precise knowledge about built cultural heritage structures, their functionality, location, environment and any sudden disturbance needs to be digitized for long lasting preservation of the resource. Discrepancy or scarcity of information can lead to errors and even irrecoverable damages. Both human and natural disasters are destroying cultural heritage objects, buildings and sites which have great value and significance in human history. This paper is aimed to provide a comprehensive discussion of state of the art knowledge representation and knowledge management solutions, specifically designed for improving built cultural heritage information preservation. This paper suggests that semantic digitization of built cultural heritage data is the best way forward. Traditional standards in built heritage metadata schemas lack the description of key aspects of 3-D modeling while, 3-D modeling standards such as geographical information system (GIS) and building information modeling (BIM) do not provide sufficient representation of historical data related to a built heritage (BH) structure. This paper proposes a model for representing architectural as well as historical data relevant to a BH site, using semantic web technologies and building information modeling standards.

Silybum marianum, commonly known as Milk thistle, is a popular herbal supplement used for the treatment of jaundice and liver cirrhosis worldwide. Here we established methods for somatic embryogenesis and comparative metabolite profiling of the different growth phases during embryogenesis in S. marianum. Highest embryogenic potential was observed for calli previously derived from petiole explants on Schenk and Hildebrandt medium containing 2.5 mg l−1 2,4-dichlorophenoxyacetic acid (2,4-D) and 1.5 mg l−1 N6-benzyladenine (BA). Somatic embryos (SE) were induced when embryogenic calli with pre-embryoid masses (PEMs) were subcultured on same media as used for induction of embryogenic callus. Highest number of somatic embryos (46 somatic embryo per callus) was observed at 1.5 mg l−1 2,4-D and 1.5 mg l−1 BA, however ½ strength MS medium showed optimal response for maturation followed by germination of somatic embryos at 1.5 mg l−1 GA3. Metabolite profiles from developmental stages of non-embryogenic callus (NEC), PEMs, SE and embryos germinating into intact plantlets (GSE) were obtained using Electro spray ionization mass spectrometry ESI/MS. Principal component analysis (PCA) was carried out to identify key metabolites in different growth phases during somatic embryogenesis. The loading scatter plots enabled the detection of several bin masses responsible for separating samples from different growth stages. Based on the values of % total ions count and average intensity of selected bins in all biological samples, putatively known metabolites were obtained from in-house bin program. Amino acids associated with various biosynthetic pathways like arginine, asparagine and serine were abundantly detected in GSE, while they were detected at decreased intensities in NEC. However, tryptophan was measured with increased signals in SE when compared to other growth phases. Glucose, fructose and fructose-6-phosphate were mostly accumulated in NEC; however they were detected with lowest intensities in GSE. Moreover, sucrose and significant secondary metabolites like cinnamic acid, kaempferol, quercetin, myricetin, linolenic acid, and 5-enolpyruvyl-shikimate-3-phosphate were found at higher amount in SE when compared to other embryogenic phases.

Peptic ulcer owes its pathological features to disregulated oxido-nitrosative and necrotic changes in gastrointestinal mucosa. Xanthium strumarium L. is a ubiquitous, abundant herb possessing an array of pharmacological properties. In view of anti-inflammatory and antioxidant activity of Xanthium strumarium L., the present investigation was designed to unravel its antiulcer potential in pylorus ligation induced gastric ulcer in laboratory animals. X. srtumarium L. leaves were extracted by refluxing with 95 % ethanol to obtained X. srtumarium L. ethanolic extract (XSEE). After 1 h pretreatment period of XSEE (100, 200 and 400 mg/kg) gastric ulcer was induced by ligation of pylorus portion of stomach. Various parameters including volume of gastric fluid, pH of gastric fluid, free as well as total acidity were measured in the gastric fluid whereas ulcer area, ulcer index, mucin content, superoxide dismutase, myeloperoxidase, nitric oxide, total calcium, histamine level, membrane bound inorganic phosphate (Na-K-ATPase), TNF-α level, DNA fragmentation were determined in the gastric tissue. Pretreatment with XSEE (200 and 400 mg/kg) significantly and dose dependently (P