Features Of Distribution Research Articles

Residual neural network with spatiotemporal attention integrated with temporal self-attention based on long short-term memory network for air pollutant concentration prediction

Accurate prediction of air pollutant concentrations can be effective in controlling and preventing air pollution, which is crucial for both the government's policy response and the public's reasonable ability to avoid air pollution. In this study, we propose a model based on the principle of big data correlation and deep learning techniques for predicting the concentration of air pollutant concentrations. The proposed model, named STARes-SaLSTM, consists of a residual neural network with spatiotemporal attention (STAResNet) and a temporal self-attention based on long short-term memory network (SaLSTM). The spatiotemporal attention module in STAResNet enhances the original input information by weighting it in both spatial and temporal dimensions, meanwhile the features of the spatial distribution of pollutant and meteorological information across many cities are deeply extracted using ResNet. A novel self-attention method known as temporal self-attention is developed to extract the temporal dependency of air pollutants. LSTM is used as a sequence encoder in this temporal attention method to calculate queries, keys, and values to acquire a more comprehensive temporal dependence than is possible with normal self-attention. The STARes-SaLSTM model successfully predicts air pollution concentrations in the target city for the future by extracting spatiotemporal correlation of feature sequence. In comparison to previous neural network models and conventional methods, the model increases the accuracy of pollutant concentration prediction. The suggested prediction model works well for the one to 3 h prediction job, with a root mean square error (RMSE) ranging from 6.716 to 11.648. Furthermore, even for the 1–24 h prediction assignment, we executed multi-scale prediction in the target city and obtained a reasonable performance, with an average RMSE value of 20.576.

Соціально-економічні виклики інтеграції та просторового розподілу внутрішньо переміщених осіб унаслідок війни

The full-scale Russian military aggression against Ukraine launched on February 24, 2022 has led to a massive flow of forced migrants, both external and internal, which is unprecedented and the most massive forced displacement in Europe since World War II. So far, there is a significant inequality of attention to the socio-economic needs of internally displaced persons (IDPs) and refugees, because most activities of international institutions and scientific attention are devoted to the needs and study of refugees, while the needs of IDPs are often “ignored” or understudied in terms of disproportionate spatial distribution of IDPs, challenges of integration into host communities, problems of consolidation of IDPs and local population, etc. The analysis of the existing body of literature on Ukrainian IDPs showed that the study of their current socio-economic situation, problems with integration into host communities and features of spatial distribution is poorly represented for the period of a full-scale Russo-Ukrainian war against the background of a huge body of pre-2022 literature. Taking into account such an insignificant body of literature on post-2022 Ukrainian IDPs, the main tasks of this study are twofold: (1) to fill the gap and expand the spectrum of knowledge about the current socio-economic situation of Ukrainian IDPs and the key problems of their integration into host communities in the conditions of a full-scale Russo-Ukrainian war; (2) analyze positive and negative international practices of IDP integration and develop recommendations for Ukraine. This article is devoted to the analysis of trends and the identification of the main socio-economic challenges of the integration and spatial distribution of Ukrainian IDPs, as well as the development of proposals for using their migration potential for the resilient development of Ukraine and host communities. The novelty of the research lies in the highlighting of positive and negative international practices of IDP integration and, as a result, the necessity of forming long-term solutions regarding the urgent socio-economic needs of Ukrainian IDPs and their spatial placement is emphasized. The dataset of the study was formed on the basis of data from reports of various international organizations and data from official state statistics. To achieve the goal of the article, quantitative methods are used, in particular, descriptive statistics and ranking. It was established that in the global context, Ukraine ranks third in the world by the number of IDPs, and their number is almost 6 million people (7 times more than before the full-scale Russian invasion), which definitely impacts the course of global migration processes. In the national context, it was found that the pattern of the spatial distribution of IDPs within the country indicates that most IDPs gravitate to the regions where the role of the regional centre is performed by one of the five metropolises of Ukraine (not including temporarily occupied Donetsk) — Kyiv, Kharkiv, Odesa, Dnipro and Lviv, which are powerful socio-economic centres and flagships of the country’s settlement system. It was found that the biggest challenges for the socioeconomic integration of IDPs into host communities are high unemployment, financial difficulties in meeting basic needs, housing problems, social stigmatization, as well as conflicts between IDPs and the population of host communities. The analysis showed that the current situation with Ukrainian IDPs requires from the government of Ukraine and the authorities of the host communities not short-term, but longterm solutions to the urgent problems of IDPs: in particular, social housing and proper housing conditions, social protection, avoiding shameful international practices of spatial placement of IDPs and much more.

A deep learning-based method for the prediction of temporal lobe injury in patients with nasopharyngeal carcinoma

PurposeTo establish a deep learning-based model to predict radiotherapy-induced temporal lobe injury (TLI). Materials and methodsSpatial features of dose distribution within the temporal lobe were extracted using both the three-dimensional convolution (C3D) network and the dosiomics method. The Minimal Redundancy-Maximal-Relevance (mRMR) method was employed to rank the extracted features and select the most relevant ones. Four machine learning (ML) classifiers, including logistic regression (LR), k-nearest neighbors (kNN), support vector machines (SVM) and random forest (RF), were used to establish prediction models. Nested sampling and hyperparameter tuning methods were applied to train and validate the prediction models. For comparison, a prediction model base on the conventional D0.5cc of the temporal lobe obtained from dose volume (DV) histogram was established. The area under the receiver operating characteristic (ROC) curve (AUC) was utilized to compare the predictive performance of the different models. ResultsA total of 127 nasopharyngeal carcinoma (NPC) patients were included in the study. In the model based on C3D deep learning features, the highest AUC value of 0.843 was achieved with 5 features. For the dosiomics features model, the highest AUC value of 0.715 was attained with 1 feature. Both of these models demonstrated superior performance compared to the prediction model based on DV parameters, which yielded an AUC of 0.695. ConclusionThe prediction model utilizing C3D deep learning features outperformed models based on dosiomics features or traditional parameters in predicting the onset of TLI. This approach holds promise for predicting radiation-induced toxicities and guide individualized radiotherapy.

Innovative interpretable AI-guided water quality evaluation with risk adversarial analysis in river streams considering spatial-temporal effects

Water security remains a critical issue given the looming threats of industrial pollution, necessitating comprehensive assessments of water quality to address seasonal fluctuations and influential factors while formulating effective strategies for decision makers. This study introduces a novel approach for evaluating water quality within a complex riverine zone in South Korea: Han River that encompasses five river streams situated at each junction of North and South streams (including Gyeongan Stream) that ultimately leading towards Paldang Lake. By utilizing the monthly water characteristic data from the year 2013–2022 across 14 different locations, the significant seasonal trends and potential influences on water quality are identified. The water quality here is calculated with the proposed method of sub-index water quality index (s-WQI). A combinatorial prediction approach of s-WQI for each location is conducted through a collective of data preprocessing approaches including Hampel filtering and feature selection in prior to the machine learning predictions. In return, light gradient boosting (LGB) is the most accurate predictor by outperforming other prediction algorithms, especially through LGB-Pearson and LGB-Spearman combinations for North and South stream intersections, and LGB-Pearson for Paldang Lake. To further evaluate the robustness of this evaluation and extending the results to a foreseeable scenario, a seasonal based Monte-Carlo Simulation with 10,000 attempts targeting the water characteristic distributions obtained from each location considered are carried out to identify the risk bounds within. The results are further interpreted with SHAP analysis on identifying the contributions of each water characteristics towards the water quality through local and global spectrum. This research yields practical implications, offering tailored strategies for water quality enhancement and early warning systems. The integration of AI-based prediction and feature selection underscores the transformative potential of computational techniques in advancing data-driven water quality assessments, shaping the future of environmental science research.

Research on Intelligent Navigation System Based on Aerospace Big Data Traffic System

This paper studies the navigation technology of the On-Orbit Servicing Spacecraft (OSS) and proposes an overall solution for the OSS navigation system. The composition of the OSS satellite navigation simulation system and simulation supporting environment are studied. Then a new SSUKF navigation filter is proposed based on the hyper spherical distributed feature sampling point transform algorithm (SSUT) and the non-scanning Kalman filter (UKF). The numerical simulation of the OSS system is studied based on MATLAB/RTW. Finally, the SSUKF algorithm and the conventional UKF algorithm are simulated digitally. The effectiveness and advanced nature of the hybrid Kalman filter applied to spacecraft autonomous navigation are verified.

Features of fume distribution in the working zone during arc welding with various covered electrodes

Features of fume distribution in the working zone during arc welding with various covered electrodes

Computer Vision-Based Estimation of The Effects of Vibration in Slipform Paving

Slipform paving is a complex multistep process encompassing concrete pouring, vibration, consolidation, correction, and curing. One of the most critical aspects in the process is that the frequency and duration of vibration can influence the distribution of coarse aggregate particles in the cured concrete. However, there is still a fundamental lack of methodologies to formally characterize the interrelationships between vibration characteristics and the quality of the cured pavement. This study aims to address this issue by proposing a novel toolset for the assessment of the spatial features of coarse aggregate distribution in doweled pavements. This system is based on paver consolidation simulations and employs computer vision as the primary tool for analysis. The experimental protocol, recently developed by the authors, employs coarse aggregate particles color-coded by gradation to aid in recognizing the distribution of different granulometric sizes within the specimens. High-resolution, two-dimensional digital images obtained from cured specimens were used to analyze aggregate characteristics, orientation, and dispersion, with particular emphasis on quantifying the effect of the distance from the vibrator head on such parameters. The results showed that the proposed digital imaging processing techniques were capable of quantitatively characterizing the distribution of coarse aggregate particles in the specimens. Moreover, novel metrics were proposed to characterize the quality of the consolidation based on the digital image data.

Алгоритми цифрової обробки кореляційних функцій у течешукачах

The article is devoted to the processing of cross-correlation functions. The need for this processing is due to a wide variety of interference conditions for searching for leaks in underground pipelines. Interference often significantly distorts the appearance of correlation functions and makes it difficult to accurately determine the coordinates of damage for pipeline repairs. Various approaches to combating these distortions are considered, depending on the available information about the characteristics of interference and leakage noise. Such features as the characteristic delay of the correlation function, which often corresponds to an interference burst and features of the frequency distributions of interference and leakage noise. An algorithm for extracting the leak coordinate from the correlation function as the coordinate of the source of a broadband signal by orthogonal decomposition of the CCF is considered. This problem is solved on the basis of classical approaches to the synthesis of shaping and synthesis of matched filters. The connection between the results obtained is shown. Thus, two approaches were used: one has the main goal of suppressing interference, without directly determining the coordinates of leaks, the other, on the contrary, is focused primarily on the selection of useful correlation of leak noises. In real-life conditions, it is advisable to combine both approaches due to the variety of acoustic environments encountered.

Effect of Enhanced Grain Refinement in Friction Welded SUS316L Alloy

To investigate the solid state weldability on SUS316L alloy, this work was carried out. Friction welding as a solid state welding was introduced and conducted at a rotation speed of 2,000 rpm and a friction pressure of 25 MPa on tube typed specimens. After this work, the grain boundary characteristic distributions such a grain size, shape and misorientation angle of the welds were clarified by electron backscattering diffraction method. The application of friction welding on SUS316L resulted in a significant refinement of the grain size in the weld zone (6.03 μm) compared to that of the base material (57.55 μm). Despite the grain refinement, the mechanical properties of the welds indicate relatively low or similar to the base material. These mechanical properties are due to dislocation density in the initial material and grain refinement in the welds.

Bayesian federated inference for estimating statistical models based on non-shared multicenter data sets.

Identifying predictive factors for an outcome of interest via a multivariable analysis is often difficult when the data set is small. Combining data from different medical centers into a single (larger) database would alleviate this problem, but is in practice challenging due to regulatory and logistic problems. Federated learning (FL) is a machine learning approach that aims to construct from local inferences in separate data centers what would have been inferred had the data sets been merged. It seeks to harvest the statistical power of larger data sets without actually creating them. The FL strategy is not always efficient and precise. Therefore, in this paper we refine and implement an alternative Bayesian federated inference (BFI) framework for multicenter data with the same aim as FL. The BFI framework is designed to cope with small data sets by inferring locally not only the optimal parameter values, but also additional features of the posterior parameter distribution, capturing information beyond what is used in FL. BFI has the additional benefit that a single inference cycle across the centers is sufficient, whereas FL needs multiple cycles. We quantify the performance of the proposed methodology on simulated and real life data.

Gender specific distortions, entrepreneurship and misallocation

Women account for a small share of all business owners and a small share of the market in India's manufacturing sector. To account for these patterns, I estimate the extent of gender-specific distortions to operating a business using firm-level data. Feeding these estimates that differ across gender into a standard framework of heterogeneous producers replicates key features of the firm size distribution, on aggregate and across gender. While women face high entry barriers into entrepreneurship, they have modest impacts on female market shares when there are sharp differences in distortions across gender along the intensive margin of entrepreneurship. Policies that promote female entrepreneurship are effective, yet have only modest impacts on aggregate productivity. These findings are not unique to India, and apply across a broader set of countries.

A Discrete Version of the Half-Logistic Distribution Based on the Mimicking of the Probability Density Function

We introduce a count distribution obtained as a discrete analogue of the continuous half-logistic distribution. It is derived by assigning to each non-negative integer value a probability proportional to the corresponding value of the density function of the parent model. The main features of this new distribution, in particular related to its shape, moments, and reliability properties, are described. Parameter estimation, which can be carried out resorting to different methods including maximum likelihood, is discussed, and a numerical comparison of their performances, based on Monte Carlo simulations, is presented. The applicability of the proposed distribution is proved on two real datasets, which have been already fitted by other well-established count distributions. In order to increase the flexibility of this counting model, a generalization is finally suggested, which is obtained by adding a shape parameter to the continuous one-parameter half-logistic and then applying the same discretization technique, based on the mimicking of the density function.

Validation of a Eulerian–Lagrangian numerical algorithm for simulating ultra-coarse particles transported in horizontal and vertical hydraulic pipes

Investigation on the characteristics of coarse and ultra-coarse particles transported in hydraulic conveying pipe is essential to design hydraulic conveying system with high efficiency and reliability. However, the modeling of the particles with a finite size larger than the mesh for fluid discretization is intractable, because the unresolved point-particle methods are difficult to converge in the calculation and the particle-resolved methods cannot afford the computational cost for engineering problem. A numerical algorithm based on the Eulerian–Lagrangian framework is developed to simulate such two-phase flows. The solvers of the computational fluid dynamics (CFD) and the discrete element method (DEM) are coupled through an in-house developed interface code. In the code, a diffusion-based averaging method is employed to smooth the contributions of large particle in the particle volume fraction, the interphase forces and the interactions between turbulence and particles. The interpolation of fluid velocity is also improved so that the calculations of the interphase forces are more accurate. The authenticity of the numerical algorithm is validated against available experimental results. The validating scenarios are the millimeter- and centimeter-sized particles conveyed in both horizontal and vertical pipes under various conveying speeds and particle concentrations. The results show the numerical algorithm can simulate large particles in the fine CFD meshes. More importantly, some distinct features in the particle distribution and the characteristics of turbulence in the experiments are well reproduced by the simulations.

Factors affecting the place of death in patients with liver cancer in China, 2013–2020: A population-based study

BackgroundDespite the country's substantial liver cancer burden, there is limited research on the factors influencing the place of death (POD) of patients with liver cancer in China. This study aimed to delineate POD distribution among patients with liver cancer, identify the factors associated with hospital deaths, and offer valuable insights for the government to develop healthcare policies. MethodsData from 2013 to 2020 were obtained from the National Mortality Surveillance System (NMSS) of China. This analysis focused on the distribution of POD among individuals who succumbed to liver cancer. Variations in characteristic distributions across different categories were evaluated using a chi-squared test. We also applied a multilevel logistic regression analysis to identify the factors associated with hospital liver cancer deaths. The proportional change in variance was computed to evaluate the contributions of different factors in the model. ResultsFrom 2013 to 2020, the NMSS reported a total of 608,789 liver cancer-related deaths, of which 440,079 (72.29%) died at home, and 158,291 (26.00%) died in the hospital. Home remained the preferred POD among patients with liver cancer. The results demonstrated that female patients, aged between 0 and 14 years, of Han ethnicity, living in urban areas, unmarried, highly educated, and either employed in a professional, staff, or civil servant capacity, or retired patients tended to end their lives in the hospital. ConclusionsIn China, home continues to be the predominant POD for patients with liver cancer, with demographic and socioeconomic factors significantly influencing whether a hospital is their POD. Enhancing healthcare policymakers' understanding of the factors influencing the place of death for patients with liver cancer may assist in creating a more equitable distribution of healthcare resources and providing a variety of choices for minorities with distinct preferences for end-of-life care.

The Features of Demersal Fish Seasonal Distribution on the Pacific Shelf off the Northern Kuril Islands

The Features of Demersal Fish Seasonal Distribution on the Pacific Shelf off the Northern Kuril Islands

Features of Distribution and Transfusion Significance of Erythrocyte Blood Groups according to ABO, Rh, Kell Systems in the Population of the Baranovichi Region of Belarus

Features of Distribution and Transfusion Significance of Erythrocyte Blood Groups according to ABO, Rh, Kell Systems in the Population of the Baranovichi Region of Belarus

Investigation of multi-scale flow structures and combustion characteristics in a cavity-enhanced circular scramjet

This study delves into the investigation of multi-scale flow structures and combustion characteristics in a cavity-enhanced circular scramjet operating under a Mach-4.5 freestream flow condition with a total temperature of 2200 K and a total pressure of 164 kPa. To achieve this, a hybrid large-eddy/Reynolds-averaged Navier-Stokes method, coupled with a pressure-corrected Flamelet/Progress Variable model, is employed and validated. The combustion flow field shows abundant small- and medium-scale flow structures induced by compressibility and combustion heat release. Vorticity alteration is found to be mainly caused by these factors, with the volumetric expansion term and baroclinic term serving as the primary driving terms. The whole combustion process is characterized by zoning and multi-scale features in spatial, temporal, heat release and species distribution, arising from differences in fuel-air mixing state and chemical reaction rates in the flow field. The injection-formed bow shock and the cavity ramp-formed compression wave interact intensively with the fuel plume, enriching the turbulent structures and strongly coupling with the chemical reaction process. The cavity not only promotes fuel-air mixing and combustion, but also facilitate the rapid transition from the laminar-like flame to thickened turbulent combustion. Statistical analysis reveals that the combustion heat release is predominantly governed by the scramjet mode and the diffusion flames, and further demonstrates the multi-scale flow and chemical reaction characteristics. Most of the combustion flow field is observed to be governed by fast chemistry, primarily in the corrugated flamelet regime, while some slow chemistry zones are also identified, lying in the distributed reaction zone regime.

Optimal design of hybrid renewable energy sources with battery storage using an efficient weighted mean of vectors algorithm

An improved algorithm called mINFO is developed, based on the modification of the original weIghted meaN oF vectOrs Optimizer (INFO). In this article, to enhance the original INFO method, an improved version called mINFO is presented by incorporating the sine-cosine function and balancing exploration/exploitation strategy through the control randomization parameter. This suggested mINFO algorithm is applied to obtain the optimal size design of two hybrid renewable power sources (HRPS), the first configuration consists of the photovoltaic (PV)/biomass system (BS)/fuel cells (FC) and the second configuration consists of the PV/BS/battery storage units. This HRPS are designed to generate the power needed to meet the loads supply on the campus of Aswan University in the Sahary region of Aswan city, Egypt. The proposed mINFO approach is developed to avoid the weaknesses of the original INFO method by enhancing the balance between the exploration and exploitation phases and preventing the conventional INFO method from getting stuck in local minima. In order to prove the efficiency and robust search capabilities of the developed mINFO algorithm, the mINFO algorithm is tested by using 10 IEEE CEC’20 test suites and its results are compared with the original INFO method and other well-known optimization algorithms. The proposed mINFO algorithm achieved the first rank in terms of the Friedman mean rank-sum test over F2, F3, F4, F6, F9, and F10, and the second rank after the original INFO algorithm over F1 and F7. Boxplot analysis is also used to show the features of data distribution. For the majority of functions, the boxplots generated by the mINFO algorithm have the narrowest ranges of values out of all comparison algorithms. As a result, for the majority of test functions, the mINFO algorithm shows more promise than its competitors. The main objectives of the suggested HRPS are to minimize energy cost (EC), excess energy (EXE), and maximize the power system's reliability (LPSP). By applying the mINFO algorithm to find the optimal sizing for the two configurations proposed in this study and by comparing the mINFO results with other algorithms such as the original INFO, Particle Swarm optimization (PSO), Runge Kutta optimization (RUN), Sooty Tern Optimization Algorithm (STOA), and Gray Wolf optimization (GWO). The proposed mINFO method shows the best results for the two suggested configurations compared to the other algorithms used by studying the systems for 100 iterations and 50 times run. For the PV/BS/battery units, the best optimal solution has achieved after 36 iterations with the lowest EC with 0.11676275 $/kWh, net present cost (NPC) with 3,420,036 $, EXE with 0.090282 and LPSP with 0.0419687649, while for the PV/BS/FC units, the optimal solution has achieved after 11 iterations with the minimal EC with 0.17996701 $/kWh, NPC with 5,271,318 $, EXE with 0.150022 and LPSP with 0.07598679.

Bayesian NMR petrophysical characterization

Identification of reservoir rock types is necessary for the exploration and recovery of oil and gas. It involves determining the petrophysical properties of rocks such as porosity and permeability which play a significant role in developing reservoir models, estimating the volumes of oil and gas reserves, and planning production methods. Nuclear magnetic resonance (NMR) technology is a fast and accurate tool for petrophysical rock characterization. The distributions of relaxation times (T2 distributions) offer valuable insights into the distribution of pore sizes in rocks, and these distributions are closely linked to important petrophysical parameters like porosity, permeability, and bound fluid volume (BFV).This work introduces a Bayesian estimation method for analyzing NMR data. The Bayesian approach uses prior knowledge of T2 distributions in the form of the prior mean and covariance. The Bayesian approach combines prior knowledge with observed data to obtain improved estimation. We use the Bayesian estimation method where prior information regarding the rock sample type, for example shale, is available.The estimators were evaluated on decay data simulated from synthesized distributions that replicate the features of experimental T2 distributions of three types of reservoir rocks. We compared the performance of the Bayesian method with two existing methods using porosity, bound fluid volume (BFV) geometric mean (T2LM) and root mean square error (RMSE) of the estimated T2 distribution as evaluation criteria. Additional experiments were carried out using experimental T2 distributions to validate the results.The performance of the Bayesian methods was also tested using mismatched priors.The experimental results illustrate that the Bayesian estimator outperforms other estimators in estimating the T2 distribution. The Bayesian method also outperforms the ILT method in estimating derived petrophysical properties except in cases where the noise level is below 0.1 and the T2 distributions are associated with short relaxation times.

Joint Demosaicing and Denoising for Spike Camera

As a neuromorphic camera with high temporal resolution, spike camera can capture dynamic scenes with high-speed motion. Recently, spike camera with a color filter array (CFA) has been developed for color imaging. There are some methods for spike camera demosaicing to reconstruct color images from Bayer-pattern spike streams. However, the demosaicing results are bothered by severe noise in spike streams, to which previous works pay less attention. In this paper, we propose an iterative joint demosaicing and denoising network (SJDD-Net) for spike cameras based on the observation model. Firstly, we design a color spike representation (CSR) to learn latent representation from Bayer-pattern spike streams. In CSR, we propose an offset-sharing deformable convolution module to align temporal features of color channels. Then we develop a spike noise estimator (SNE) to obtain features of the noise distribution. Finally, a color correlation prior (CCP) module is proposed to utilize the color correlation for better details. For training and evaluation, we designed a spike camera simulator to generate Bayer-pattern spike streams with synthesized noise. Besides, we captured some Bayer-pattern spike streams, building the first real-world captured dataset to our knowledge. Experimental results show that our method can restore clean images from Bayer-pattern spike streams. The source codes and dataset are available at https://github.com/csycdong/SJDD-Net.