Browse Articles
Discover research articles across all indexed journals
Comparison of the induction of neutralizing antibodies against Bas congo virus using several vaccine modalities
A hierarchical model for community identification in complex networks through modularity and genetic algorithm
Electrically conductive lignin reinforced PAA/HA scaffolds with enhanced biological activity via polyelectrolyte multilayer coatings for tissue engineering applications
A deep neural network with attention mechanism for flow prediction of compressor blade
Abstract For flow-related design optimization problems, computational fluid dynamics (CFD) simulations are commonly used to predict the flow fields. However, the computational expenses of CFD simulations limit the opportunities for design exploration. Motivated by this tricky issue, a convolutional neural network (CNN) based on U-Net architecture with attention mechanism (AM) is proposed to efficiently learn flow representations from CFD results to shorten the compressor blade design cycle. The proposed model converts the provided shape information and flow conditions into grayscale images to directly predict the expected flow field, saving computational time. An extensive hyper-parameter search is performed to determine the optimal model. Qualitative and quantitative analysis of the results are studied to evaluate the accuracy for the calculation of Mach number distributions. In particular, two new attention mechanisms is developed to preserve the physical consistency of the complex flow field with shock wave. Mach number flow fields under different working conditions are predicted using the proposed model, and the prediction is well consistent with CFD results. Over three orders of magnitude of speedup is achieved at all batch sizes compared to traditional CFD methods, while maintaining low prediction errors.
Medulloblastoma’s master regulators and their association with patients’ risk
Optimizing sustainable blended concrete mixes using deep learning and multi-objective optimization
Abstract The proposed framework unites deep neural networks (DNNs) together with multi-objective optimization for designing environmentally friendly concrete mixes. A DNN model receives training through a wide dataset which includes multiple mix parameters along with curing conditions for accurate compressive strength prediction. The Bayesian hyperparameter tuning technique produces an optimal network configuration which delivers an average $$R^2$$ of 0.936 together with an RMSE of 5.71 MPa during 5-fold cross-validation. The Multi-Objective Particle Swarm Optimization (MOPSO) algorithm finds multiple optimal solutions which simultaneously optimize three competing objectives that include strength maximization and cost minimization and cement reduction. The optimized mix designs surpassed 50 MPa compressive strength through cement reduction of up to 25% which led to a total cost reduction of 15% compared to standard mix designs. The analysis of feature importance shows cement content together with concrete age serve as the main factors that affect strength measurements. The integrated data-driven method provides reliable decision-support tools to practitioners who need cost-effective sustainable mix designs through its identification of feasible trade-offs. The proposed methodology delivers new understandings of green concrete technology through optimal proportion discoveries that boost strength and save costs while decreasing environmental impact for direct application in real construction settings.
Outlier-tolerant relative positioning method based on multi-source information fusion for unmanned aerial vehicles
Abstract Relative positioning is a key technology that needs to be addressed for unmanned aerial vehicles (UAVs) to achieve flight mission involving autonomous aerial refueling, cluster formation and cooperative control. To address the shortcomings of the least squares (LS)-based multi-source information fusion method, such as poor outlier-tolerance, the idea of outlier-tolerance is used to improve the LS method. A novel loss function is proposed by replacing the parabolic function with a piecewise function, and a multi-source information outlier-tolerant relative positioning method based on the novel loss function is established. The simulation results show that the established method has a good outlier tolerance ability, which can avoid the adverse effects of outliers and ensure the reliability of the calculation results without significantly affecting the accuracy of the relative positioning.
Promising clinical tools for specific Alzheimer disease diagnosis from plasma pTau217 and ApoE genotype in a cognitive disorder unit
Intravascular ultrasound assessment of stent edge restenosis mechanisms and treatment outcomes following percutaneous coronary intervention
Author Correction: First observation of genus Komarkiella in Iranian saline soils
Synthesis and application of Cobalt-Silver nanohybrid for antimicrobial wastewater treatment and agricultural productivity enhancement
Abstract 1- This work emphasises the potential of Co@Ag-NPs as an efficient antimicrobial agent. The scientific community has recently shown silver nanohybrids to maintain plural consistency and their potential applications in wastewater treatment. Where these nanohybrids showed highly removing capacity of the three main contaminants (pesticides, microorganisms, and heavy metals) from waste water. The ability of silver and cobalt nanohybrids to inhibit bacteria and fungi that cause illnesses both in vitro and in vivo has made them an outstanding antimicrobial agent. Cobalt-silver nanohybrid particles (Co@AgNPs) have antibacterial properties against both Gram-positive and Gram-negative bacteria, including those that are resistant to multiple drugs. Co@AgNPs have several simultaneous modes of action, and when combined with organic chemicals or medicines that fight bacteria, they have demonstrated a synergistic effect on infections. Because of their unique properties, silver and cobalt nanohybrids can be used in medical and healthcare goods to effectively treat or prevent infections. The preparation and characterization of highly stable cobalt silver nanohybrid (Co@Ag) have been reported. Out of the water samples, four bacterial and seven fungal isolates are identified. Various concentrations of Co@Ag, ranging from 10− 1 to 10− 3, have been seen to impact and produce varying diameters of inhibition zones in bacterial isolates Shigella, Salmonella, E. coli, Pseudomonas aeruginosa and fungal isolates Aspergillus flavus var columnaris, and Aspergillus awamori. Water samples treated with Co@Ag nanoparticles when plated on LB and Czapek Dox agar did not show any growth of bacteria and fungi after five and seven days of incubation, respectively. Furthermore, data demonstrated that shoot and root length and germination percentage of wheat seeds irrigated by treated water increased progressively from 7.5 cm to 9.2 cm, from 9 cm to 11 cm and from 90 to 100%, respectively, as Co@Ag concentrations were elevated from 0 to 10 and 20 mg/l.