R2 Index Research Articles

The uterine artery resistivity index is affected by embryo resorption rate at canine pregnancy diagnosis

The uterine artery resistivity index (RI) obtained by Doppler ultrasonography has become a common method in evaluating uterine blood flow during pregnancy for assessing canine fetal and placental conditions. During pregnancy, embryonic vesicle resorptions can be observed by ultrasound and have been found to increase with the aging of the dam. The RI is higher during induced abortion in bitches, while its relationship with early embryo resorptions is not yet clearly defined. The aim of this study was to evaluate whether the uterine artery's haemodynamics at pregnancy diagnosis are related to embryo resorption rates and other pregnancy and dam parameters. The ultrasound examinations were performed 25 ± 4 days post-ovulation (between days 21 and 29). During the examinations, the animals were in lateral recumbency, and both uterine horns were scanned to determine the number and viability of embryos and resorption sites. The left uterine artery was visualized, and the RI was determined. The breed, weight, reproductive anamnesis, and age of the animals were recorded. Forty-four bitches were included, weighing 2.8–39.2 kg, for 50 pregnancy diagnoses performed at ages ranging from 18 to 88 months. Bitches were allocated to different size groups according to their body weight and breed: Medium (M, 10–40.0 kg), Small (S, 5–9.9 kg), and Toy (XS, <5 kg). A linear regression was used to model the RI as the outcome, with size group and age of the dam (above or below the median value), litter size (sum of viable embryos and resorptions), gestational age (days post-ovulation), parity (multiparous vs. primiparous), cystic endometrial hyperplasia (present or not), and either the percentage of resorptions (on litter size) or simply their presence as predictors. The overall model was statistically significant (P = 0.029), with an R2 index of 0.296. A significant relationship with the response was found for gestational age (P = 0.012) and percentage of resorptions (P = 0.045). No significant relationships were found for the other parameters. As reported in the literature, as gestational age increased, RI decreased. Embryo resorptions were observed in 17/50 (34.0 %) pregnancies. As the percentage of resorption sites within the pregnancy increased, the RI also increased. Conversely, the simple presence or absence of resorption sites had no statistically significant effect on the RI. This study describes, for the first time, a significant impact of embryonic resorptions on uterine artery RI at pregnancy diagnosis. Whether these changes are a cause or effect of the abnormal pregnancy remains to be elucidated.

Forecasting and Comparative Application of PV System Electricity Generation for Sprinkler Irrigation Machines Based on Multiple Models

Currently, photovoltaic (PV) resources have been widely applied in the agricultural sector. However, due to the unreasonable configuration of multi-energy collaboration, issues such as unstable power supply and high investment costs still persist. Therefore, this study proposes a solution to reasonably determine the area and capacity of PV panels for irrigation machines, addressing the fluctuations in power generation of solar sprinkler PV systems under different regional and meteorological conditions. The aim is to more accurately predict photovoltaic power generation (PVPG) to optimize the configuration of the solar sprinkler power supply system, ensuring reliability while reducing investment costs. This paper first establishes a PVPG prediction model based on four forecasting models and conducts a comparative analysis to identify the optimal model. Next, annual, seasonal, and solar term scale models are developed and further studied in conjunction with the optimal model, using evaluation metrics to assess and compare the models. Finally, a mathematical model is established based on the optimal combination and solved to optimize the configuration of the power supply system in the irrigation machines. The results indicate that among the four PVPG prediction models, the SARIMAX model performs the best, as the R2 index reached 0.948, which was 19.4% higher than the others, while the MAE index was 10% lower than the others. The solar term scale model exhibited the highest accuracy among the three time scale models, the RMSE index was 4.8% lower than the others, and the MAE index was 1.1% lower than the others. After optimizing the configuration of the power supply system for the irrigation machine using the SARIMAX model based on the solar term scale, it is verified that the model can ensure both power supply reliability and manage energy overflow effectively.

Dynamic modeling of post-combustion carbon capture process based on multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder network

Solvent-based post-combustion carbon capture (PCC) technology is a promising, near-term solution for decarbonizing power generation and industrial facilities. Model-based process simulation is crucial for the optimal design and operation of the PCC process. Recently, data-driven models have gained attention due to their adaptability, efficient computation and high accuracy. However, the nonlinearity, strong couplings and multi-time scale features of the PCC process pose significant challenges for model identification. To this end, this paper proposes a multi-gate mixture-of-experts incorporating dual-stage attention-based encoder-decoder (MMoE-DAED) network for dynamic modeling of the PCC process under wide operating conditions. An encoder-decoder composed of long short-term memory (LSTM) network is employed to extract features from the time-dependent input data and learn the complex dynamic interactions caused by the inertial and delay properties of the process. Dual-stage attention mechanism is incorporated into the encoder and decoder respectively to select the most relevant input features and their correlations within the time series data. To enhance multi-output prediction accuracy, multi-gate mixture-of-experts (MMoE) framework that considers correlations of multitask learning is implemented. Simulation results using operating data from a PCC experimental setup indicate that the proposed modeling approach accurately predicts the steady-state values and dynamic trends of the CO2 capture rate and stripper bottom temperature over a wide operating range. The RMSE, MAPE and R2 indices for the CO2 capture rate are 2.1592, 0.0295, 0.9641, respectively, and for the stripper bottom temperature are 0.1491, 0.0003, 0.9833, respectively. Validations on a PCC simulator further verify the accuracy and efficiency of the MMoE-DAED model, which enables an 80.87% reduction in computation time compared to the simulator. This paper points to a new direction for the data-driven dynamic modeling of complex energy conversion processes.

A spatiotemporal correlation and attention-based model for pipeline deformation prediction in foundation pit engineering

In foundation pit engineering, the deformation prediction of adjacent pipelines is crucial for construction safety. Existing approaches depend on constitutive models, grey correlation prediction, or traditional feedforward neural networks. Due to the complex hydrological and geological conditions, as well as the nonstationary and nonlinear characteristics of monitoring data, this problem remains a challenge. By formulating the deformation of monitoring points as multivariate time series, a deep learning-based prediction model is proposed, which utilizes the convolutional neural network to extract the spatial dependencies among various monitoring points, and leverages the bi-directional long-short memory unit network to extract temporal features. Notably, an attention mechanism is introduced to adjust the trainable weights of spatial-temporal features extracted in the prediction. The evaluation of a real-world subway project demonstrates that the proposed model has advantages compared with current models, particularly in long-term prediction. It improves the Adjusted R2 index averagely by from 19.4 to 61.6%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} compared with existing models. The proposed model also exhibits a decrease in mean absolute error ranging from 51.5 to 70.3%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} compared to others. Experiments and analyses verify that the spatial-temporal dependencies in time series and the attention learning for spatial-temporal features can improve the prediction of such engineering problems.

Recognition and Scoring Physical Exercises via Temporal and Relative Analysis of Skeleton Nodes Extracted from the Kinect Sensor

Human activity recognition is known as the backbone of the development of interactive systems, such as computer games. This process is usually performed by either vision-based or depth sensors. So far, various solutions have been developed for this purpose; however, all the challenges of this process have not been completely resolved. In this paper, a solution based on pattern recognition has been developed for labeling and scoring physical exercises performed in front of the Kinect sensor. Extracting the features from human skeletal joints and then generating relative descriptors among them is the first step of our method. This has led to quantification of the meaningful relationships between different parts of the skeletal joints during exercise performance. In this method, the discriminating descriptors of each exercise motion are used to identify the adaptive kernels of the Constrained Energy Minimization method as a target detector operator. The results indicated an accuracy of 95.9% in the labeling process of physical exercise motions. Scoring the exercise motions was the second step after the labeling process, in which a geometric method was used to interpolate numerical quantities extracted from descriptor vectors to transform into semantic scores. The results demonstrated the scoring process coincided with the scores derived by the sports coach by a 99.5 grade in the R2 index.

Application of machine learning algorithms for predicting the life-long physiological effects of zinc oxide Micro/Nano particles on Carum copticum

Nanoparticles impose multidimensional effects on living cells that significantly vary among different studies. Machine learning (ML) methods are recommended to elucidate more consistence and predictable relations among the affected parameters. In this study, nine ML algorithms [Support-Vector Regression (SVR), Linear, Bagging, Stochastic Gradient Descent (SGD), Gaussian Process, Random Sample Consensus (RANSAC), Partial Least Squares (PLS), Kernel Ridge, and Random Forest] were applied to evaluate their efficiency in predicting the effects of zinc oxide nanoparticles (ZnO NPs: 0.5, 1, 5, 25, and 125 µM) and microparticles (ZnO MPs: 1, 5, 25, and 125 µM) on Carum copticum. The plant root/shoot biomass; number of leaves, branches, umbellates, and flowers; protein content; reducing sugars; phenolic compounds; chlorophylls (a, b, Total); carotenoids; anthocyanins; H2O2; proline; malondialdehyde (MDA); tissue zinc content; superoxide dismutase (SOD) activity; and media ΔpH were measured and considered input variables. All levels of ZnO MPs treatments increased growth parameters compared to the control (ZnSO4). The highest shoot/root fresh and dry mass were recorded at 5 µM ZnO MPs compared with the control. The root fresh/dry mass under ZnO NPs treatments was more sensitive than shoot parameters. The number of flowers increased by 134 and 79% in MPs and NPs treatments compared to the control, respectively. ZnO NPs reduced protein content by up to 81% in 125 µM NPs compared to ZnSO4. Reducing sugar content increased to 25, 40 and 36% in 5, 25, 125 µM MPs and 67, 68, 26, 26 and 21% in 0.5, 1, 5, 25 and 125 µM NPs treatments, respectively. The pH alteration was more significant under NPs and affected zinc uptake. All levels of ZnO NPs treatments increased growth parameters compared to the control. All ML algorithms showed varied efficiencies in predicting the nonlinear relationships among parameters, with higher efficiency in predicting the behavior of root and shoot dry mass, root fresh weight and number of flowers according to R2 index. The model obtained from SVR with the radial basis function (RBF) kernel was selected as a comprehensive model for predicting and determining the efficacy of the results.

Food Insecurity among Iranian Pregnant Women: A Systematic Review and Meta-Analysis.

Estimating the prevalence of food insecurity among vulnerable sub-groups, especially pregnant women, is significant. This study aimed to estimate the pooled prevalence of food insecurity among Iranian pregnant women and to determine its related factors. This study constitutes a systematic review and meta-analysis of cross-sectional studies involving pregnant women, published between January 2000 and September 2022, in English and Persian on seven databases. Finally, 14 studies were analyzed and synthesized, with the results presented in the form of forest plots. Heterogeneity was investigated using the I2 index and the meta-regression to evaluate variables suspected of causing heterogeneity. Statistical analysis and synthesis were performed using Stata-16. The pooled prevalence of food insecurity among Iranian pregnant women was 45% (95% confidence interval: 37-54%). In a multi-variable meta-regression model, p values were significant for the year of data collection and the type of the questionnaire. The adjusted I2 and R2 indices were estimated at 84.47 and 51.46%, respectively. The prevalence of food insecurity among Iranian pregnant women has been estimated at half a million. Given the high prevalence of food insecurity among pregnant women in Iran, we propose the inclusion of food insecurity screening for this vulnerable demographic within the primary healthcare package. Additionally, we advocate for the allocation of food subsidies to pregnant women confronting food insecurity.

Screening of Functional Small Molecules via Modified Machine Learning Strategy toward Efficient All-Inorganic Perovskite Solar Cells.

Organic small molecules are proven to be capable of passivating the bulk/interfacial defects in inorganic perovskite solar cells. Considering the burdensome situation to screen the functional small molecules, we employ a modified machine learning (ML) strategy to guide screening suitable small molecules toward efficient solar cells through three modified ML algorithms to construct the prediction model: (i) random forest algorithm (RF), (ii) support vector machine algorithm (SVR), and (iii) XGBoost. Among them, the XGBoost algorithm displays a better overall predictive performance, whereby the R2 index reaches 0.939. Accordingly, eight small molecules are selected to modify the interface of perovskite films, and both the theoretical and experimental results certify that the difluorobenzylamine with additional fluorine atoms has a better interface modification effect among the small molecules containing functional groups, e.g., the benzene ring and amino group. The high accuracy of the modified machine learning model enables us to simplify the small-molecule screening process and form an important step for ongoing developments in perovskite solar cells and other optoelectronic devices.

An improved model for primary prediction of performance map for turbocharger radial turbine

In the contemporary landscape, possessing an intricate understanding of the performance characteristics of turbocharger radial turbine proves invaluable during engine development phases, to improve predictive capabilities of calculation codes and enhance the critical process of matching engines with turbochargers. This research deals with offering two precise yet straightforward analytical functions intended to generate comprehensive performance maps of turbocharger turbines. This is achieved through a refined adjustment of a preexisting analytical function, after introducing an inventive multiplication factor that aligns numerical calculations with experimental data to predict the turbine’s expansion ratio. Besides, a second analytical function forecasts the turbine’s thermo-mechanical efficiency by establishing a power balance equation between the turbine and supplied compressor map. The outcome of the developed model is compared with existing method on two distinct turbochargers, encompassing various rotational speeds. Additionally, a sensitive analysis aiming to detect the most important factors affecting our developed model while exploring it possible validity range for different thermodynamic parameters. The results indicate that the two functions yield reliable estimations of turbine performance, with maximum; root mean square error, R2, and mean absolute percentage error indices find around 9.47%, 0.993, and 9.03% for the turbine expansion ratio, and about 4.42%, 0.612, and 19.78% for efficiency prediction. This novel model enhances simulation accuracy while preserving user-friendliness and robustness based on the prerequisite of limited geometric and thermodynamic parameters at the turbocharger boundaries. Finally, the main advantages of the proposed model is its adaptability for the implementation in calculation codes, turbomachinery optimization strategies and assessments of the design and performance, addressing scenarios where the original turbine maps are rarely provided by turbocharger manufacturers.

Kinetics model of crystal nucleation and growth in supercooled water for designing ice-templating soft matter scaffold

Ice-templating technology has recently attracted extensive attention to achieve programed structure-property relationships in porous soft matter scaffolds. However, there is a huge gap existed between theoretical understanding and practical applications of nucleation kinetics and growth of ice crystals in supercooled water. This paper establishes a nucleation kinetics model of crystal growth in supercooled water, for designing ice-templating soft matter scaffolds with programmable structure-property relationship. A phase transition model was firstly formulated to characterize liquid-liquid phase transition of supercooled water, based on a two-state model and free-volume theory. Effects of diffusion coefficient and density of the supercooled water on ice nucleation kinetics and crystal growth were investigated, based on the classic nucleation theory. Analytical results showed excellent agreement with experimental data, with correlation indices of R2=90.7 % for diffusion coefficients and R2=94.0 % for densities, respectively. The model predicted a nucleation rate of 31.7 m−3∙s−1 at 200 K and peak nucleation rate and crystal growth rates appearing at 183 K and 227 K. Constitutive relationships among mechanical behaviors, ice nucleus radius, nucleation ratio, and crystallization growth rate, were developed for the ice-templating scaffolds, based on the affine model theory and verified with finite element analysis results (R2= 99.9 %) and experimental results (R2 = 95.8 %). Finally, the prediction results using the proposed model were further verified using the experimental data reported in the literature. This study provides a new methodology to describe the nucleation kinetics and growth of ice crystals in supercooled water and programmable structure-property relationships in ice-templating soft matter scaffolds.

Auto‐regulated radial base function structure implementation in the hybrid and ensemble hybrid domains to assess the hardened properties of novel mixture high performance concrete

AbstractThe mechanical properties of concrete, such as compressive strength and slump flow rates, are very nonlinear. For academics, it is crucial to forecast these qualities while creating new building methods. Such capabilities should be developed to lower the cost of expensive tests and increase the precision of the measurements. The goal of this study is to create an radial basis function neural network to describe the characteristics of hardness in high‐performance concrete (HPC) mix. Metaheuristic techniques were used to enhance the RBFNN's functionality. A dataset of 181 HPC mixes comprising ecologically beneficial ingredients, such as fly ash and silica fume, was used for training and evaluating the capabilities of the proposed hybrid models. According to the modeling process based on sensitivity analysis of input parameters and the results of hybrid models, the model combined with the multiverse optimization algorithm (MVO) had a higher correlation between the predicted and observed CS and slump values than the model combined with three optimization algorithms in terms of the R2 index being the maximum value of 0.984 in the tasting phase of CS and SL estimation. While evaluating two mechanical aspects of HPC samples, the of the model coupled with the MVO algorithm reconfirmed its accuracy being 3.59.

Milk weighing scale based on machine learning

Milk weight records are an important source of information for daily decisions on dairy farms. Most milking parlor systems have technologies that record milk production at cow level on a daily basis. However, a great number of dairy farms simply do not have this crucial information because they lack the necessary technology in the parlor systems. The aim of this study is to implement a machine learning-based milk weighing scale exploring the dynamics of milking flow, looking for an alternative strategy for low-cost mechanical milking systems, and/or parlor milking systems without appropriated hardware/software integrated. We developed a milk flow sensor integrated to the milking parlor system to compute the milk flow during milking, and installed some cameras to label real milk weight. The regression model based on machine learning predicted the milk weight with high precision, achieving minimum values of 2.81, 1.29, and 10.26 in terms of mean squared error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE), respectively, along with a maximum value of 0.84 in terms of the R2 index. We found that the area under milk flow curve (AUC), the number of milk flushes (MF), and the thirty-seventh to forty-fourth milk flow during milking have the most important influence in the efficacy of our proposed model. Milk flow of 250 cows milked 3 times a day were recorded during 12 days, generating 8,601 milk flow curves. Our preliminary results showed that we can confidently estimate the weight milk produced by a cow using machine learning algorithms to empower dairy farms to make better decisions.

Kinetic and artificial neural network modeling of dried black beauty eggplant (Solanum melongenaL.) slices during rehydration

AbstractThis paper targeted to investigate rehydration characteristics of dehydrated black beauty eggplant (which was dried under sun, by hot air, microwave, and infrared) at 25, 50, and 75°C, and to analyze rehydration ratio (RR) by artificial neural network (ANN) approach. RRs of both microwave‐processed specimens (between 5.66 and 7.91) and sun‐dried ones (between 5.38 and 6.37) were always greater than the others, at all rehydration temperatures. Rehydration temperature had an enhancing effect on RRs, and the image that closely resembled the fresh sample was captured in the microwave‐dried rehydrated samples. Nearly 180–240 min was adequate for rehydration of all slices. Zeroth‐ and first‐order kinetic models, Peleg, Peppas, and two‐term exponential decay models, as well as a new rational model were tested to describe rehydration kinetics. Two‐term equation was almost superior with high R2 (between 0.9734 and 0.9994) and the lowest root mean square error (RMSE) and χ2. Novel recommended mathematical expression was also successful (R2: 0.9679–0.9989, χ2: 0.0051–0.0975, RMSE: 0.0191–0.0866). Regarding relationship between actual and predicted RRs and performance indices of ANN equation, overall R and R2 were recorded as follows: 0.9975–0.9950 (sun‐dried) &gt; 0.99642–0.9929 (hot air‐dried) &gt; 0.9955–0.9911 (infrared‐dried) &gt; 0.9907–0.9815 (microwave‐dried), respectively. The proposed ANN model and novel mathematical formula not only offer a considerable potential in predicting rehydration patterns and developing rehydration protocols in food production sector, but also contribute to save energy by completely understanding the process and optimizing conditions.Practical applicationsThe eggplant is a cherished vegetable often dried, providing a velvety texture and rich taste in Anatolian recipes. In Anatolia, colorful vegetables are strung together on strings, adorning traditional houses, and serving as a testament to the region's deep‐rooted cultural heritage. The Turkic people in Central Asia demonstrated remarkable skill in preserving plants by carefully drying leaves, stems, or roots. The process of rehydration entails the addition of water to dehydrated eggplant slices in order to restore their initial dimensions and attributes for being consumed. This investigation integrates the utilization of ANNs to simulate the rehydration procedures of eggplant. This simulation can be employed for the purpose of quality control and standardization within the food sector. Hence, food manufacturers can anticipate the rehydration characteristics of their products across various production batches and conditions, thereby guaranteeing adherence to quality benchmarks.

A new strategy for prediction of water qualitative and quantitative parameters by deep learning-based models with determination of modelling uncertainties

ABSTRACT This study presents a new method based on three types of deep learning-based models (DLM) for estimation of water parameters. The DLM models were recurrent neural networks (RNN), long short-term memory (LSTM), and bidirectional long short-term memory (BiLSTM). The study areas were the Colorado River basin in the United States and the Mighan Wetland in Iran. The electrical conductivity (EC), dissolved oxygen (DO), total dissolved solids (TDS), chloride ions (Cl), and river flow rate (debi) were simulated by the DLM models. The Wilson score (WS) uncertainty analysis results for Colorado modelling showed that LSTMdebi, RNNDO, and RNNEC were the best models in simulating due to having the lowest errors (Mean ei equal to 0.36, −1.50, and −0.59), respectively. Finally, the highest value of the R2 index, 0.998, was achieved by the LSTM model in modelling the debi parameter, and 0.996 in EC modelling, in the Mighan Wetland.

Soft Sensor Development for Real-Time Interface Tracking in Multiple Product Pipelines Based on Knowledge and Data

Summary Petroleum products are usually consecutively transported in the same multiple-product pipeline, and the occurrence of mixed oil happens during the process. Accurately tracking the mixed oil interface is essential for the optimal scheduling of oil transportation. However, complicated operating conditions and unavoidable measurement noise pose challenges to methods for locating the interface. The data-driven modeling method is a potential solution, but it may face limitations due to issues of overfitting, especially when the data set is contaminated with noise. To tackle such problems, in this paper, we propose a knowledge-informed Bayesian-Gaussian mixture regression (KIBGMR) model to enable the real-time tracking of the interface. The KIBGMR employs finite Gaussian distribution to learn the multimode characteristics of input data, including the hydrothermal data, measured density of tail oil, and the velocity of interface transportation and output data including the measured density of tail oil and interface transportation velocity. Subsequently, it utilizes the prior knowledge related to the regression coefficient through the Bayesian treatment. Evaluations demonstrate that the R2 index achieved by the proposed model in predicting the interface arrival time is greater than 0.98, even with the contaminated data set. This research can help operators accurately grasp the location of the mixed oil interface, formulate reasonable valve switch operations for better management of the mixed oil section, and provide a reference for the method of knowledge-data hybrid modeling.

Comparisons of Different Machine Learning-Based Rainfall–Runoff Simulations under Changing Environments

Climate change and human activities have a great impact on the environment and have challenged the assumption of the stability of the hydrological time series and the consistency of the observed data. In order to investigate the applicability of machine learning (ML)-based rainfall–runoff (RR) simulation methods under a changing environment scenario, several ML-based RR simulation models implemented in novel continuous and non-real-time correction manners were constructed. The proposed models incorporated categorical boosting (CatBoost), a multi-hidden-layer BP neural network (MBP), and a long short-term memory neural network (LSTM) as the input–output simulators. This study focused on the Dongwan catchment of the Yiluo River Basin to carry out daily RR simulations for the purpose of verifying the model’s applicability. Model performances were evaluated based on statistical indicators such as the deterministic coefficient, peak flow error, and runoff depth error. The research findings indicated that (1) ML-based RR simulation by using a consistency-disrupted dataset exhibited significant bias. During the validation phase for the three models, the R2 index decreased to around 0.6, and the peak flow error increased to over 20%. (2) Identifying data consistency transition points through data analysis and conducting staged RR simulations before and after the transition point can improve simulation accuracy. The R2 values for all three models during both the baseline and change periods were above 0.85, with peak flow and runoff depth errors of less than 20%. Among them, the CatBoost model demonstrated superior phased simulation accuracy and smoother simulation processes and closely matched the measured runoff processes across high, medium, and low water levels, with daily runoff simulation results surpassing those of the BP neural network and LSTM models. (3) When simulating the entire dataset without staged treatment, it is impossible to achieve good simulation results by adopting uniform extraction of the training samples. Under this scenario, the MBP exhibited the strongest generalization capability, highest prediction accuracy, better algorithm stability, and superior simulation accuracy compared to the CatBoost and LSTM simulators. This study offers new ideas and methods for enhancing the runoff simulation capabilities of machine learning models in changing environments.

Modelling and validation of liquefaction potential index of fine-grained soils using ensemble learning paradigms

This study explores the utilization of ensemble-based soft computing techniques for predicting the liquefaction potential of fine-grained soils. Generally, deterministic methods are used to assess the possibility of liquefactions. However, recent advancements have highlighted the implementation of machine learning techniques considering the diverse geotechnical characteristics for liquefaction susceptibility analysis. The current study predicts liquefaction potential index (LPI) of soils using five ensemble-based soft computing paradigms viz., decision tree, random forest, gradient boosting, AdaBoost, and XGBoost regressors. Various influential factors including stress parameters, depth of soil stratum, peak ground acceleration, earthquake magnitude, cyclic stress ratio, fine content, and SPT- N value, were used for estimating the LPI of soils. Experimental results of the employed models were assessed using multiple statistical indices. The results demonstrate that the employed XGBoost model achieved higher predictive accuracy with 99 % accuracy (based on R2 index) during the testing phase. Overall results exhibit that the employed XGBoost paradigm can be utilized as a viable alternative to empirical approaches, enabling an early assessment of liquefaction susceptibility in different engineering projects. This will expedite identification and evaluation of liquefaction hazards, allowing engineers to make more informed decisions.

Impact of Models and Eigenvalues on Gold Price Forecasting

The burgeoning synergy between computer science and finance has fostered an increasing integration of these domains. Machine learning has become a prevalent tool in aiding financial analysis and forecasting. Compared to traditional forecasting techniques, machine learning-based models exhibit enhanced accuracy and broader applicability. This study introduces three models, namely linear regression, random forest, and support vector machine, to analyze and predict gold prices. The influence of Eigenvalues on model performance is also examined. In the end, the support vector machine model constructed by using two kinds of US dollar exchange rates, US Treasury bond interest rates, and the 10-day moving average of gold prices and passed cross-validation obtained the best model performance evaluation index, and its R2 index reached nearly 0.99. It can be concluded from this study that the performance of the model is poor when only one eigenvalue is used to build the model, while for the case of building a model with multiple eigenvalues, the contribution of the U.S. Treasury bond rate to the improvement of the performance of the prediction model is the smallest. Therefore, appropriately increasing the number of eigenvalues is conducive to improving the performance of the model, and selecting the types of eigenvalues reasonably is also conducive to improving the accuracy of the model.

Evaluation of Infiltration Modeling in the Cisadane Watershed in Indonesia: Existing and New Approach Equation

This study aims to evaluate the accuracy of semi-empirical models for determining infiltration based on the existing equations (Horton, Kostiakov and Kostiakov–Lewis) and a new form equation with optimized parameters which has good accuracy (lowest RMSE and MBE), sufficient linearity (highest R2), and a Willmott index close to 1. The location of this study was the Cisadane watershed, which is a priority watershed in Indonesia. The lowest values of average RMSE and MBE and highest values of R2 and Willmott index are given by Equation 1, which indicated that the model was closest to the field infiltration conditions. The distribution of the RMSE values for all survey points using Equation 1 resulted in small RMSE values ranging from 0.09 to 1.83. The distribution of R2 values for all survey points using Equation 1 yielded R2 values close to 1 (high linearity) with values ranging from 0.96 to 1. Based on these results, it can be concluded that Equation 1 is the most accurate infiltration model for the Cisadane watershed compared to the existing infiltration rate equation. This research can be used as an initial idea to create the infiltration rate model using other forms of equations with optimization parameters to produce a more representative model with field data.

General medication adherence scale in patients with chronic illnesses: Persian translation and psychometric evaluation.

This study was conducted with the aim of determining the validity and reliability of the Persian version of "General Medication Adherence Scale (GMAS)" in chronic patients in Iran. The study was conducted among patients with chronic diseases in five hospitals of Iran. In this study, after cultural validation, using the steps of Content, Response Reaction, and Internal structure evaluations, the research sample was increased to 150 individuals for exploratory factor analysis (EFA) and 313 chronic patients for confirmatory factor analysis (CFA) to confirm the construct validity. Cronbach's alpha coefficient was used to assess internal consistency, and test-retest method was used to evaluate the reliability of the tool. The results of EFA and CFA confirmed the tool with three factors and 11 items. The R2 index in the above model was estimated at 0.99, indicating that 99% of the variation in medication adherence scores in research units was explained by GMAS with 11 items. The main indices of the model in factor analysis were all above 0.9, indicating a good fit for the model. Overall, the study results showed that the Persian version of GMAS has acceptable and practical characteristics for evaluating medication adherence, and it can be used as a valid tool in various related fields.