Model Results Research Articles

Bayesian geo-additive model to analyze spatial pattern and determinants of maternal mortality in Ethiopia

Background and AimsMaternal mortality is defined as the death of a woman from any cause associated to or made worse by her pregnancy, either during her pregnancy or within 42 days of the pregnancy's termination, regardless of the length of the pregnancy or its location. The objective of this study is to determine the factors influencing maternal mortality as well as to examine the regional distribution of maternal deaths in Ethiopia.MethodThis study was conducted in Ethiopia and the data was basically secondary which is obtained from 2016 Ethiopian Demographic and Health survey (EDHS). The Bayesian Geo-additive regression model is used to identify the major risk factors and spatial effects (spatial pattern) on maternal death in Ethiopia.ResultPregnancy-related problems or childbirth were the cause of death for 1.43% of the 10,009 women in the research, whose ages ranged from 15 to 49. In contrast to the semi-parametric and generalized linear models, the Bayesian Geo-additive regression model is based on the DIC and better fits the data. According to the Bayesian Geo-additive regression model's results, maternal death is significantly affected by the place of delivery, the number of prenatal care visits, marital status, wealth index, mother's age and the number of birth orders. The Afar, Somali, Benishangul Gumuz, and Gambela regions have higher rates of maternal death, according to evidence of geographic variation in a model.ConclusionThe findings of the study revealed that maternal mortality is influenced by numerous social, demographic, and geographic variables. Geographic variations exist in the patterns of maternal mortality.

Residual Pix2Pix networks: streamlining PET/CT imaging process by eliminating CT energy conversion.

Objective
Attenuation correction of PET data is commonly conducted through the utilization of a secondary imaging technique to produce attenuation maps. The customary approach to attenuation correction, which entails the employment of CT images, necessitates energy conversion. However, the present study introduces a novel deep learning-based method that obviates the requirement for CT images and energy conversion.
Methods
This study employs a residual Pix2Pix network to generate attenuation-corrected PET images using the 4033 2D PET images of 37 healthy adult brains for train and test. The model, implemented in TensorFlow and Keras, was evaluated by comparing image similarity, intensity correlation, and distribution against CT-AC images using metrics such as PSNR and SSIM for image similarity, while a 2D histogram plotted pixel intensities. Differences in standardized uptake values (SUV) demonstrated the model's efficiency compared to the CTAC method.
Results
The residual Pix2Pix demonstrated strong agreement with the CT-based attenuation correction, the proposed network yielding MAE, MSE, PSNR, and MS-SSIM values of 3×10-3, 2×10-4, 38.859, and 0.99, respectively. The residual Pix2Pix model's results showed a negligible mean SUV difference of 8×10-4(P-value = 0.10), indicating its accuracy in PET image correction. The residual Pix2Pix model exhibits high precision with a strong correlation coefficient of R2 = 0.99 to CT-based methods. The findings indicate that this approach surpasses the conventional method in terms of precision and efficacy.
Conclusions
The proposed residual Pix2Pix framework enables accurate and feasible attenuation correction of brain F-FDG PET without CT. However, clinical trials are required to evaluate its clinical performance. The PET images reconstructed by the framework have low errors compared to the accepted test reliability of PET/CT, indicating high quantitative similarity.&#xD.

Comparative Analysis of Risk Measure Model in Financial Time Series

Abstract: With the advent of economic globalization, the severity of financial system losses is increased dramatically. To ensure that financial institutions can bear sufficient risk, numerous risk measure models emerge. This paper studies the effectiveness of different models in measuring risks in different regions. The paper uses three approaches: The parametric approach, the Semi-parametric approach, and the non-parametric approach, and seven different models that belong to these approaches to calculate value at risks and expected shortfalls. One-dimensional asset and one-day forecast are applied in the model fitting. Using backtesting of historical daily return series to test if the value at risk and expected shortfall are reliable and models are good to use. The author also introduced a new concept, volatility of deviation in value at risk, as an additional criterion to judge the quality of the model's prediction results. Finally, the most appropriate models are selected to measure the risk levels and analyze the risk situation in different regions.

APPLIED MIXED KERNEL AND FOURIER SERIES MODELLING IN NONPARAMETRIC REGRESSION

There are three nonparametric regression approaches, namely, parametric, nonparametric and semi-parametric regression. Nonparametric regression allows the response variable to follow a different curve from one predictor variable to another. In paired data, the components of predictor variable and the response variable are assumed to follow unknown data patterns, so that they can be approximated by a kernel based regression model and Fourier series. The base components are approximated by kernel functions and Fourier series functions. Error is assumed to be normally distributed with zero mean and constant variance. The aim of this research is to make a kernel-based nonparametric regression model and Fourier series on poverty data in the Province of Bali. The research phase method begins with the introduction of the kernel based nonparametric regression model and the Fourier series. The next step is to study the estimation of the regression curve. The function estimation results are highly dependent on the bandwidth, smoothing and oscillation parameters. The resulting model gives a value of R2=0.6278, means that the used variables can explain the model by 62.78 percent. From the obtained modeling re-sults, the Open Unemployment Rate has a positive effect on the percentage of poor people in Bali. Keywords: Nonparametric Regression; Modeling; Kernel; Fourier Series.

Comparative Analysis of Water Applicability Predictions Explained by The LightGBM Model Using SHAP and LIME

Abstract. This article mainly discusses the application of the LightGBM model to predict water potability for a dataset containing multiple water quality features. The focus of the study is to use two popular model interpretability techniques: SHAP and LIME to explain the model's prediction results. The results show that SHAP can globally explain the feature importance of the entire dataset and provide a deep understanding of the features and model behavior, while LIME provides a detailed explanation of a single prediction through local linear approximation, which is easier to interpret and apply. This article also compares the strengths and limitations of SHAP and LIME in explaining the LightGBM models behavior, demonstrating their applicability and explanatory power in different contexts. In addition, this article also explores the actual application scenarios of water quality prediction and analyzes how interpretability improves model transparency and trust in this field. Through these analyses, the article provides practical suggestions on how to choose appropriate model interpretation methods in reality.

Evaluating Impact of Experiential Marketing Activities on Repurchase Intention: Testing Mediating and Moderating Model on Apparel Industry.

This examination is giving critical data to the backers of Pakistan's private universities in understanding clients' necessities more significantly to add to the improvement of their business. The data is collected through surveys. The pieces of information have been inspected through expansive outlines, using a structure and factors that are simply uniquely crafted to the fascinating necessities of Pakistan. In the consistent review, gathers created utilizing existing hypotheses, produce speculations, embrace structures for data plan and perform tests to show the proposed hypothesis. The clothing business is the essential unit of assessment all through the assessment of these elements. Our assessment is quantitative and besides embraces an objective strategy. The model size 250 and the assigned people is from clothing industry of Pakistan. Firstly, we utilize descriptive statistics to scrutinize the respondents' characteristics and outcomes. Additionally, we centre around the appraisal of the assessment model's results. Finally, we examine the insightful significance and hypothesis testing of the model. This total technique engages us to secure significant encounters into the data, which can be used to seek after informed decisions and drive accomplishment. Additionally, while the current study used a survey method, qualitative data such as customers' opinions and the nature of products could be added through open-ended questions to provide more in-depth insights. In conclusion, our study provides valuable insights into the relationship between issue identification and social media engagement, perceived corporate identification, and loyalty towards a company. Future research can build upon these findings to explore additional factors and expand the scope of the study. This specific research framework is never been used earlier in Pakistan’s Apparel industry. The originality and significance is to use Positive E-Wom as moderator in Pakistani market.

The impact of obesity on chronic diseases: type 2 diabetes, heart disease, and high blood pressure

Obesity is a risk factor for several chronic diseases, including type 2 diabetes, heart disease, and high blood pressure. Developing models of obesity and its complications allows for close monitoring of these epidemics, informing the creation of effective control strategies. This research focuses on presenting an endemic model of obesity and its health complications, taking into account, social factors and relationships among people in society. The term epidemic is related to the influence of the health lifestyle of obese people on healthy individuals. The transmission of obesity and its complications is through peer pressure to consume fast food and acquire bad eating habits from relatives and friends. So, in our model, the effect of these factors is expressed with parameters β i . We demonstrate theoretically the asymptotic local stability of disease-free equilibrium and the asymptotic local stability of endemic equilibrium, proving the existence and uniqueness of the solution to the obesity model and its complications. To confirm the model's theoretical results, we conduct numerical simulations to study the impact of variation in social factor parameters on the diseases studied.

Mathematical modeling of Ethiopia's energy demand by sectors and energy types, with forecasts for the next 30 years

Due to the scarcity of economic resources, it is vital to optimize everything so that the supply and demand lines intersect in an optimized quantity, with no shortage or surplus of a provided item or service. Energy supply contains both surplus and shortage, thus estimating the amount of projected energy demand is a key work that must be completed. The objective of this paper is generating a mathematical model based on the actual data for thirty years forecasting. To create a mathematical model using actual data from the last fifteen years, a model that can represent the past trend and be used for future forecasting. This study provides a general overview of Ethiopia's current energy requirement with different energy type as well as sector-specific energy demand and estimates for different economic growth scenarios up to 2052. This model was created using a linear regression polynomial fit through Origin graphic and analysis software, and an econometric model was also applied. GDP was utilized as an independent variable in the economic model to determine the trend of energy consumption. Another input-output model is also used for multilinear regression to evaluate the change of four variables, GDP, population growth, urbanization growth rate, and general inflation rate, which was quantitatively linked with total energy requirement using Weka software. The mathematical model developed through linear and multilinear regression has been validated by using a different assumption on GDP growth based on past growth rate as low, medium and high growth rate and using the mathematical formula to generate an energy demand trend that can be compared with the actual trend; as a result, all the mathematical model that are generated has been found to be valid for the purpose of the intended work. Based on the generated mathematical model and different GDP growth rate scenario as low, medium, business as usual (BAU) and high a future energy demand was forecasted up to 2052 for thirty years. The model's results can help energy planners ensure that the country's supply capacity keeps up with predicted energy demand growth.

Drilling Rate of Penetration Prediction Based on CBT-LSTM Neural Network.

Due to the uncertainty of the subsurface environment and the complexity of parameters, particularly in feature extraction from input data and when seeking to understand bidirectional temporal information, the evaluation and prediction of the rate of penetration (ROP) in real-time drilling operations has remained a long-standing challenge. To address these issues, this study proposes an improved LSTM neural network model for ROP prediction (CBT-LSTM). This model integrates the capability of a two-dimensional convolutional neural network (2D-CNN) for multi-feature extraction, the advantages of bidirectional long short-term memory networks (BiLSTM) for processing bidirectional temporal information, and the dynamic weight adjustment of the time pattern attention mechanism (TPA) for extracting crucial information in BiLSTM, effectively capturing key features in temporal data. Initially, data are denoised using the Savitzky-Golay filter, and five correlation coefficient methods are employed to select input features, with principal component analysis (PCA) used to reduce model complexity. Subsequently, a sliding window approach transforms the time series into a two-dimensional structure to capture dynamic changes, constructing the model input. Finally, the ROP prediction model is established, and search methods are utilized to identify the optimal hyperparameter combinations. Compared with other neural networks, CBT-LSTM demonstrates superior performance metrics, with MAE, MAPE, RMSE, and R2 values of 0.0295, 0.0357, 9.3101%, and 0.9769, respectively, indicating the highest predictive capability. To validate the model's robustness, noise was introduced into the training data, and results show stable performance. Furthermore, the model's predictive results for other wells achieved R2 values of 0.95, confirming its strong generalization ability. This method provides a new solution for ROP prediction in real-time drilling operations, assisting drilling engineers in better planning their operations and reducing drilling cycles.

A Multiscale Mathematical Model for the Fetal Blood Circulation of the Second Half of Pregnancy.

Doppler ultrasound is a commonly used method to assess hemodynamics of the fetal cardiovascular system and to monitor the well-being of the fetus. Indices based on the velocity profile are often used for diagnosis. However, precisely linking these indices to specific underlying physiology factors is challenging. Several influences, including wave reflections, fetal growth, vessel stiffness, and resistance distal to the vessel, contribute to these indices. Understanding these data is essential for making informed clinical decisions. Mathematical models can be used to investigate the relation between velocity profiles and physiological properties. This study presents a mathematical model designed to simulate velocity wave propagation throughout the fetal cardiovascular system, facilitating the assessment of factors influencing velocity-based indices. The model combines a one-fiber model of the heart with a 1D wave propagation model describing the larger vessels of the circulatory system and a lumped parameter model for the microcirculation. Fetal growth from 20 to 40 weeks of gestational age is incorporated by adjusting cardiac and circulatory parameter settings according to scaling laws. The model's results, including cardiac function, cardiac output distribution, and volume distribution, show a good agreement with literature studies for a growing healthy fetus from 20 to 40 weeks. In addition, Doppler indices are simulated in various vessels and agree with literature as well. In conclusion, this study introduces a novel closed-loop 0D-1D mathematical model that has been verified against literature studies. This model offers a valuable platform for analyzing factors influencing velocity-based indices in the fetal cardiovascular system.

Automated detection of motion artifacts in brain MR images using deep learning.

Quality assessment, including inspecting the images for artifacts, is a critical step during magnetic resonance imaging (MRI) data acquisition to ensure data quality and downstream analysis or interpretation success. This study demonstrates a deep learning (DL) model to detect rigid motion in T1-weighted brain images. We leveraged a 2D convolutional neural network (CNN) trained on motion-synthesized data for three-class classification and tested it on publicly available retrospective and prospective datasets. Grad-CAM heatmaps enabled the identification of failure modes and provided an interpretation of the model's results. The model achieved average precision and recall metrics of 85% and 80% on six motion-simulated retrospective datasets. Additionally, the model's classifications on the prospective dataset showed 93% agreement with the labeling of a radiologist a strong inverse correlation (-0.84) compared to average edge strength, an image quality metric indicative of motion. This model is aimed at inline automatic detection of motion artifacts, accelerating part of the time-consuming quality assessment (QA) process and augmenting expertise on-site, particularly relevant in low-resource settings where local MR knowledge is scarce.

Automated counting and classifying Daphnia magna using machine vision

Daphnia magna (D. magna) is a model organism widely used in aquatic ecotoxicology research due to its sensitivity to environmental changes. The survival and reproduction rates of D. magna are easily affected by toxic environments. However, their small size, fragility, and transparency, especially in neonate stages, make them challenging to count accurately. Traditionally, counting adult and neonate D. magna relies on manual separation and visual observation, which is not only tedious but also prone to inaccuracies. Previous attempts to aid counting with optical sensors have faced issues such as inducing stress damage due to vertical movement and an inability to distinguish between adults and neonates. With the advancement of deep learning technologies, our study employs a simple light source culture device and utilizes the Mask2Former model to analyze D. magna against the background. Additionally, the U-Net model is used for comparative analysis. We also applied OpenCV technology for automatic counting of adult and neonate D. magna. The model's results were compared against manual counting performed by experienced technicians. Our approach achieves an average relative accuracy of 99.72 % for adult D. magna and 98.30 % for neonate. This method not only enhances counting accuracy but also provides a fast and reliable technique for studying the survival and reproduction rates of D. magna as a model organism.

Transient pressure prediction in large-scale underground natural gas storage: A deep learning approach and case study

Large-scale underground natural gas storage (UNGS) facilities typically allocate only one month annually for well shut-in to facilitate pressure build-up. This limited well shut-in period affects the subsequent pressure measurements and evaluation of gas storage capacity. This study proposes a novel workflow to directly predict the transient pressure behavior of UNGS during pressure build-up without requiring additional well shut-in operations. The proposed workflow uses the gas injection-withdrawal rate as a dynamic input feature for a deep learning model, with reservoir pressure as the output feature. An enhanced WA-BiLSTM model integrates multiple physical mechanisms and advanced optimization algorithms. The model achieves mean squared error (MSE) of 2 × 10-3, which is less than 5 % of traditional model's results. Field data from the largest Hutubi UNGS exhibit a prediction accuracy of 99.0 % during the well shut-in phase. High-precision prediction results with low MSE ensure the reliability of pressure derivative data. By analyzing the predicted pressure data, the actual gas storage volume is 104.75 × 108 m3, accounting for 97.9 % of the facility's designated storage capacity.

The Tunisian Central Bank’s Efficiency Benchmarks: A Dynamic Approach

The topic of banking performance and efficiency has received considerable attention, yet there is a noticeable gap in examining the performance and efficiency of central banks. Moreover, there is a scarcity of studies on central bank efficiency. This paper aims to investigate the factors that influenced the efficiency of the Central Bank of Tunisia from 2000 to 2020, using an Autoregressive Distributed Lag Model. The appropriate econometric methodology was first established to achieve this goal, after which the model's results were presented and interpreted. The study's findings indicate that the Tunisian Central Bank’s efficiency is influenced by several macroeconomic (inflation, public deficit, growth rate), international (exchange rate, foreign debt), and political variables (political and government instability, conflict of interest), each with a varying degree of impact. Interestingly, the transition of the Central Bank of Tunisia from a dependent to an independent institution in 2016 did not yield a notable change in efficiency.Copyright© 2024 The Author(s). This article is distributed under the terms of the license CC-BY 4.0., which permits any further distribution in any medium, provided the original work is properly cited.

Information model for assessing the impact of tactical material procurement risks on order fulfillment in make-to-order manufacturing

Manufacturing businesses are showing increased interest in the issue of supply risks for materials and components. In recent decades, numerous studies and reviews have been published on the subject of supply chain risks. However, most research examines the global impact of risks on business as a whole and proposes a multi-level procedure for identifying, assessing, and developing risk mitigation measures, which should be carried out in advance with the involvement of specialists and experts. Nevertheless in maketo-order manufacturing, it is important to assess the risks of material supply for individual production orders, at the same time taking into account constant changes in production state and supply chains. The problem of assessing the risks of material supply gets even more complicated at enterprises with a high mix of manufactured products. To solve the above-mentioned problems, the authors propose an automated model for risks evaluation. The model is implemented as a component of the enterprise's information system (ERP) and uses data from the technological, production, inventory, and logistics modules to calculate the probability of deviation in order fulfillment time from the planned schedule due to potential disruptions in material supply chains. When executing the model, it analyzes the production's material requirements in both volumetric and calendar terms, inventory levels, and the condition of supply channels. The risks of delayed delivery for each material are expressed as the standard deviation of the delivery date from the planned date and are calculated by composing the risks for segments (elements) of the supply chain, the risks for which are, in turn, calculated based on performance data accumulated in the logistics module, with the possibility of introducing correction coefficients and expert evaluations. The overall risk of order material supply is determined by summing up the delivery risks of individual materials, expressed as the corresponding standard deviations. The model's results can be used for managerial decision-making in production and procurement or for communicating expected order fulfillment times to customers. The model has been tested at an enterprise in the electrical engineering industry.

Financial technology, wealth threshold, and wealth inequality in China

This study developed a theoretical model to examine the impact of financial technology (fintech) on wealth inequality from a wealth threshold perspective. The model's numerical simulation results suggest that fintech exerted an inverted U-shaped impact on wealth inequality. Empirical test results based on China Household Finance Survey panel data and fintech index data confirmed this finding. The impact varied across regions and among groups with differing education levels and financial literacy.

Fate and transport of ten plant protection products of emerging concern in a coastal lagoon: Application and evaluation of a multimedia level III fugacity model

Multimedia fugacity models are effective tools for studying the environmental behaviour and occurrence of contaminants of emerging concern (CECs) and assessing associated risks, especially when experimental data is limited. These models describe processes controlling chemical partitioning, transport, and reactions in environmental media using mathematical statements based on the concept of fugacity.To aid in identifying and prioritizing CECs for future local monitoring, we present here the application of a level III multimedia fugacity model assuming non-equilibrium between compartments and steady-state conditions. This model estimated predicted environmental concentrations (PECs), persistence, distribution, and transport of ten plant protection products (PPPs) in the Venice Lagoon, a complex coastal environment under high anthropogenic pressure.The model was evaluated through uncertainty and sensitivity analysis using the Monte Carlo approach and by comparing PECs with PPP concentrations measured during four sampling campaigns. Results showed good agreement with field data, with the highest concentrations in water and sediments estimated for glyphosate, followed by imidacloprid, metaflumizone, and triallate. The model indicated accumulation of all investigated PPPs in sediments. For most chemicals, advection outflow and degradation in the water column were the main removal mechanisms, while volatilization was significant only for oxadiazon and triallate.Sensitivity and uncertainty analysis revealed that degradation rates, organic carbon/water partitioning coefficients (KOC), and parameters describing air-water interactions had the strongest influence on the model's results, followed by inputs accounting for sediment sinking and resuspension. The lack of data on PPP degradation in brackish waters accounted for most of the uncertainty in model results.This work shows how a relatively simple multimedia model can offer new insights into the environmental behaviour of PPPs in a complex transitional waterbody such as the Venice lagoon, providing useful data for the identification of the CECs to be prioritised in future local monitoring efforts.

National brands versus store brands: retailer fight against national brands to improve store brands via a dynamic discount pricing strategy

Today, there is a lot of competition between competitors in the market of different products. The level of complexity of relationships and behavior of active players in the market has also increased. So that a manufacturer and retailer work together to increase the profit of the supply chain through the sale of products. On the other hand, the retailer and the manufacturer as competitors are competing with each other to sell more of their products. This issue has increased the complexity of the relationship between retailers and manufacturers. This study aims to explore how retailers can strengthen the self-introduced store brand (SB) and resist the pressures of manufacturers by using dynamic discount pricing (DDP) strategy. Numerical examples are proposed to clearly explain the validity and applicability of the model. Based on the managerial insights developed by analyzing the model's results, we evaluated the influences of DDP strategy on the retail prices and demands of national brands (NB) and SB and the profit of the retailer and the manufacturer. We found that discounts on the manufacturer's product by the retailer increase the demand for both NB and SBs. An increase in demand leads to an increase in the profits of manufacturers and retailers. However, the increase in the manufacturer's profit does not compensate for the decrease in his market share. In other words, the introduction of an SB always causes damage to the manufacturer, but the amount of damage depends on various factors. These findings offer manufacturers and retailers useful insights and help them adopt effective marketing strategies.

Susceptibility assessment of multi-hazards using random forest—back propagation neural network coupling model: a Hangzhou city case study

As the demand for regional geological disaster risk assessments in large cities continues to rise, our study selected Hangzhou, one of China’s megacities, as a model to evaluate the susceptibility to two major geological hazards in the region: ground collapse and ground subsidence. Given that susceptibility assessments for such disasters mainly rely on knowledge-driven models, and data-driven models have significant potential for application, we proposed a high-accuracy Random Forest—Back Propagation Neural Network Coupling Model. By using nine evaluation factors selected based on field surveys and expert recommendations, along with disaster data, the model's predictive results indicate a 3–40% improvement in model performance metrics such as AUC, accuracy, precision, recall, and F1-score, compared to single models and traditional SVM and logistic regression models. Ultimately, using the predictive results of this model, we created susceptibility maps for individual disasters and developed a muti-hazards susceptibility map by employing the expert weight discrimination method and the overlay evaluation method. Furthermore, we discussed the feature importance in the prediction process. Our study validated the feasibility of using advanced machine learning models for urban geological disaster assessment, providing a replicable template for other cities.

Defensive resource allocation in terrorism conflict management based on graph model with relative preferences

In real-world counterterrorism activities, it is usually difficult for the defender and the attacker to accurately know the private information of the each other such as valuations of targets. Instead, players may only know the relative preference on the target valuations from the adversary. In the conflict analysis, graph model is a powerful tool for dealing with relative preferences. This paper studies the defensive resource allocation in terrorism conflict management with incomplete information by establishing a graph model. To solve the model, we divide the conflict states into two types and discuss the conditions under which these two types of states are at equilibrium. Furthermore, we study how the defender should optimally allocate the resource to achieve two goals: (i) achieving a certain Nash equilibrium state desired by the defender; and (ii) minimizing the total loss from an attack in equilibrium. Subsequently, we conduct several numerical analyses: (i) analyzing the effects of both players' investment effectiveness on the optimal defense loss; (ii) comparing our model's results with those obtained using three classical decision methods, revealing that the defense loss in our model is lower; and (iii) presenting a case study to illustrate the applicability of the proposed model. This paper provides novel insights on how to efficiently allocate defensive resource when the defender and attacker know only the relative preference of the adversary on target valuations.