Search

Overbreak is a prevalent and detrimental phenomenon in hard rock tunnel excavation that escalates construction costs and compromises tunnel structural stability. Therefore, accurate prediction of overbreak during excavation is significant for cost reduction and risk mitigation. This study introduces an efficient metaheuristic method, namely the honey badger algorithm (HBA), for optimizing the light gradient boosting machine (LGBM) model, and proposes an explicit equation for the prediction of overbreak based on gene expression programming (GEP) technology. Utilizing a dataset comprising 523 overbreak cases collected from the Huxitai (HXT) tunnel in China, this study conducts the modeling of overbreak prediction and assesses the model's performance through various metrics and non-parametric statistical tests. The results indicate that the HBA-LGBM hybrid model developed herein achieves the highest coefficient of determination (R2) of 0.9472 among the tested models, while the GEP model reaches a R2 of 0.9275. Clearly, the overbreak prediction model constructed in this paper shows superior overall performance, and the comparative analysis of multiple models also highlights HBA's significant advantage in mitigating overfitting. Lastly, various interpretive techniques were applied to analyze the impact of input variables on overbreak, providing insights into the decision-making principles of the predictive model from both global and individual case levels. The analysis revealed that the total charge (TC) and powder factor (PF) are the most influential blasting parameters on overbreak occurrence. Furthermore, a graphical user interface for testing purposes was developed and showcased. In summary, the overbreak models established in this study effectively predict tunnel overbreak caused by blasting, demonstrating superior predictive performance and interpretability compared to previous efforts. Highlights: An efficient hybrid ensemble model based on HBA is proposed for predicting tunnel overbreak caused by blasting. An explicit high-accuracy prediction equation for tunnel overbreak is constructed using GEP technology. The model performance is comprehensively evaluated through various metrics and non-parametric statistical tests. The constructed model demonstrates excellent generalization capabilities and interpretability. [ABSTRACT FROM AUTHOR]

Background: Sorafenib is the standard treatment for patients with hepatocellular carcinoma (HCC) with advanced stage disease. An accurate prediction model is important to ascertain the prognosis of HCC patients treated with sorafenib. This study aimed to predict the outcome of HCC patients treated with sorafenib using ACLR and HALP scores. Methods: This Observational Retrospective Cohort Study was conducted on 110 Patients with HCC patients from January 2015 to December 2022 at Medical Oncology Department, Faculty of Medicine, Zagazig University. Results: HALP and ACLR score were significantly associated with treatment outcome among HCC patients treated with sorafenib. HALP was a predictor for treatment outcome among HCC patients treated with sorafenib at cut off point of 42.9 with sensitivity of 75.7% and specificity of 86.3%. ACLR was a predictor for treatment outcome among HCC patients treated with sorafenib at cut off point of 75.6 with sensitivity of 78.4% and specificity of 82.2%. High HALP score indicates better prognosis with a cut off of 42.9. Low ACLR indicates better prognosis with a cut of 75.6. Conclusion: Both HALP and ACLR scores can be used as valid prognostic scores for independently predicting the overall prognosis in HCC patients treated with Sorafenib. Having a low HALP score indicates worse prognosis, while, our results showed that the cut off for ACLR 75.6 .. but high and low score didn't show any significance in predicting the PFS or OS but they show significant sensitivity and specificity. [ABSTRACT FROM AUTHOR]

In many practical problems, there is interest in the estimation of mixed effect projections for new data that are outside the range of the training data. Examples include predicting extreme small area means for rare populations or making treatment decisions for patients who do not fit typical risk profiles. Standard methods have long been known to struggle with such problems since the training data may not provide enough information about potential model changes for these new data values (extrapolation bias). We propose a new framework called Prediction Using Random-effect Extrapolation (PURE) which involves constructing a generalized independent variable hull (gIVH) to isolate a minority training set which is "close" to the prediction space, followed by a regrouping of the minority data according to the response variable which results in a new (but misspecified) random effect distribution. This misspecification reflects "extrapolated random effects" which prove vital to capture information that is needed for accurate model projections. Projections are then made using classified mixed model prediction (CMMP) (?) with the regrouped minority data. Comprehensive simulation studies and analysis of data from the National Longitudinal Mortality Study (NLMS) demonstrate superior predictive performance in these very challenging paradigms. An asymptotic analysis reveals why PURE results in more accurate projections. for this article are available online. [ABSTRACT FROM AUTHOR]

Copyright of Forest Engineering is the property of Forest Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Background: In adult females, mycoplasma infection is common and challenging to diagnose. This study aimed to use retrospective laboratory data to construct a nomogram for predicting the mycoplasma infection of individuals with probable urogenital tract mycoplasma infection. Methods: A total of 2,859 patients with suspected urogenital tract mycoplasma infection were retrospectively enrolled in this study. Demographics and routine examinations of leucorrhea were used to develop a nomogram for predicting mycoplasma infection. The least absolute shrinkage and selection operator (LASSO) method was applied to filter variables and select predictors, and multivariable logistic regression was used to construct a nomogram. The discriminatory ability of the model was determined by calculating the area under the curve (AUC). The performance and clinical utility of the nomogram were generated by using Harrell's concordance index, calibration curve, and decision curve analysis (DCA). Results: By using the LASSO regression method, seven variables (age, white blood cell, epithetical cell, cleanliness, candidiasis vaginalis, sialidases, and leukocyte esterase) were chosen, and a nomogram was constructed using these variables. The prediction nomogram (0.676, 95% CI: 0.611 - 0.744) demonstrated a satisfactory performance. The prediction model's AUC was 0.679 (95% CI: 0.660 - 0.691). Furthermore, the DCA showed a good clinical net benefit based on the mycoplasma infection nomogram. Conclusions: A nomogram was created in this study, which included seven demographic and clinical characteristics of female patients. The nomogram could be of great value for the diagnosis of mycoplasma infection. [ABSTRACT FROM AUTHOR]

BACKGROUND: The American Conference of Governmental Industrial Hygienists (ACGIH) Threshold Limit Values (TLVs) for Lifting is a manual material handling (MMH) assessment method to identify weight limits that nearly all workers may be exposed to without developing work-related low back disorders (LBD). However, this assessment method only applies to lifting with the torso within 30° asymmetry of the sagittal plane. OBJECTIVE: Estimate TLV weight limits while lifting with torso asymmetry greater than 30° beyond the sagittal plane. METHODS: Lifting tasks were performed from various horizontal and vertical locations, at torso asymmetry angles of 0°, 15°, 30°, 45°, 60°, 75° and 90°, using ACGIH identified TLVs. Validated MMH assessment methods (NIOSH Lifting Equation, Ohio State University LBD Risk Model) were utilized to estimate TLVs at torso asymmetries greater than 30°. RESULTS: The current ACGIH TLVs resulted in low- to moderate-risk risk levels for torso asymmetries from 0° to 30°, and the risk incrementally increased as torso asymmetry increased to 90°. With the intention to keep the risk levels to that found at 30° torso asymmetry, lower TLV weight limits in the vertical and horizontal zones investigated were estimated for torso asymmetries from 45° to 90°. The resulting adjusted TLVs were consistent with weight limits identified for similar lifting conditions from other assessment methods that account for torso asymmetry. CONCLUSIONS: This research found current ACGIH-defined TLVs possess less than high-risk for LBD, and provided guidance to practitioners for reduced TLVs when torso asymmetry is greater than 30° from the sagittal plane. [ABSTRACT FROM AUTHOR]

This study investigated whether the use of peak force (PF) obtained from multiple joint positions during isometric squat (IsoSqt) can predict of 1-repetition maximum (1RM) squat with high precision. Twenty-nine male and female resistance-trained athletes (age = 23.0 ± 3.7 years, height = 1.57 ± 0.06 m, body mass = 56.6 ± 9.1 kg, 1RM squat = 104.6 ± 24.2) performed the 1RM squat, and IsoSqt at 60°, 90°, and 120° knee angles on 3 separate occasions. Peak force obtained from IsoSqt at all positions significantly correlated with 1RM squat (r = 0.684-0.940, p < 0.05). Linear regression analysis based on group data showed r² = 0.903, based on male data only, r² = 0.826, and based on female data only, r² = 0.855. Predicted 1RM squat using linear regression equations based on group, male-only, and female-only data showed nonsignificant differences of 0.02-0.6% from actual 1RM squat (p = 0.812-0.947, 95% CI = -8.00 to 10.08), with error of estimate of 1.5-2.3%. In addition, Bland-Altman analysis showed a mean bias of -1.04 to 0.35 kg, 95% CI = -10.08 to 8.00 kg. The results showed that using PF obtained from IsoSqt at multiple positions was able to predict 1RM squat with low difference from actual 1RM squat. Furthermore, using linear regression equation derived from gender-specific data was able to predict 1RM squat with higher precision than that based on group data. [ABSTRACT FROM AUTHOR]

The prediction of the ablation rate of silicone rubber-based composites is of great significance to accelerate the development of flexible thermal protection materials. Herein, a method which combines uniform design experimentation, active learning, and virtual sample generation was proposed to establish a prediction model of the mass ablation rate based on a small dataset. Briefly, a small number of sample points were collected using uniform design experimentation, which were marked to construct the initial dataset and primitive model. Then, data points were acquired from the sample pool and iterated using various integrated algorithms through active learning to update the above dataset and model. Finally, a large number of virtual samples were generated based on the optimal model, and a further optimized prediction model was achieved. The results showed that after introducing 300 virtual samples, the average percentage error of the gradient boosting decision tree (GBDT) prediction model on the test set decreased to 3.1%, which demonstrates the effectiveness of the proposed method in building prediction models based on a small dataset. [ABSTRACT FROM AUTHOR]

A hysteretic model is essential for the study of the seismic performance of structures. Due to the ability to capture the component strength and stiffness deterioration, the modified Ibarra–Medina–Krawinkler (ModIMK) hysteretic model has been widely used recently. Previous studies on the ModIMK model have mainly focused on reinforced-concrete (RC) square columns, and very few have focused on circular columns. In contrast, studies on the ModIMK model specifically for corroded circular RC columns have not yet been conducted. For this reason, a database of 35 corroded and uncorroded comparison columns was gathered, and the hysteretic model parameters of each column were calibrated. The ratios of the model parameters of the corroded and uncorroded comparison components are defined as the corrosion-induced deterioration coefficients (CIDCs). After the CIDCs were calculated for all the corroded columns, the empirical equations for the CIDCs were established using regression methods. Through determining the ModIMK model parameters of the corroded columns when they were uncorroded, combined with these equations, the ModIMK model parameters of the corroded circular columns were calculated and their hysteretic models defined. Finally, the accuracy of the ModIMK model's prediction method was demonstrated using the hysteretic response analyses of four components in the database and the application of two components outside the database. The prediction method lays the foundation for applying the ModIMK model to structures containing corroded circular RC columns. [ABSTRACT FROM AUTHOR]

The continuous improvement of bridge construction technology has resulted in an ongoing expansion of bridge spans, which has concomitantly increased the difficulty of controlling the alignment of long-span bridges during construction. In order to address the issue of the grey prediction model exhibiting a significant discrepancy in its alignment predictions for long-span continuous girder bridges, a pre-camber prediction method for bridges based on a combination of the grey model (GM) and BP neural network (GM-BP) is proposed. Firstly, the parameters are identified according to their influence on the pre-camber, and the appropriate parameters are selected as the original data to improve the efficiency of prediction. Subsequently, the original data are preliminarily fitted by the GM(1,1) model, and the predicted values are used as inputs for training the neural network. Finally, the new predicted values are output using the nonlinear fitting ability of the BP neural network. To assess the efficacy of the model, it is applied to the prediction of the pre-camber of the girder segments of a bridge under cantilever construction. The pre-camber prediction for 11#–13# girder sections was based on 10 sets of monitoring data from constructed girder sections. The results demonstrated that the average relative error of the GM-BP combined prediction model was 3.01%, which was 5.68% less than that of the GM(1,1) model, and the overall prediction exhibited a closer alignment with the original data. The GM-BP combined prediction model is an effective method for ensuring the alignment control of bridge construction and is able to achieve high accuracy and stability in its predictions in the case of limited and irregular data. [ABSTRACT FROM AUTHOR]

Knowledge tracing is a significant research area in educational data mining, aiming to predict future performance based on students' historical learning data. In the field of programming, several challenges are faced in knowledge tracing, including inaccurate exercise representation and limited student information. These issues can lead to biased models and inaccurate predictions of students' knowledge states. To effectively address these issues, we propose a novel programming knowledge tracing model named GPPKT (Knowledge Graph and Personalized Answer Sequences for Programming Knowledge Tracing), which enhances performance by using knowledge graphs and personalized answer sequences. Specifically, we establish the associations between well-defined knowledge concepts and exercises, incorporating student learning abilities and latent representations generated from personalized answer sequences using Variational Autoencoders (VAE) in the model. This deep knowledge tracing model employs Long Short-Term Memory (LSTM) networks and attention mechanisms to integrate the embedding vectors, such as exercises and student information. Extensive experiments are conducted on two real-world programming datasets. The results indicate that GPPKT outperforms state-of-the-art methods, achieving an AUC of 0.8840 and an accuracy of 0.8472 on the Luogu dataset, and an AUC of 0.7770 and an accuracy of 0.8799 on the Codeforces dataset. This demonstrates the superiority of the proposed model, with an average improvement of 9.03% in AUC and 2.02% in accuracy across both datasets. [ABSTRACT FROM AUTHOR]

Numerous surrogate-assisted evolutionary algorithms have been proposed for expensive optimization problems. However, each surrogate model has its own characteristics and different applicable situations, which caused a serious challenge for model selection. To alleviate this challenge, this paper proposes an adaptive surrogate-assisted particle swarm optimization (ASAPSO) algorithm by effectively combining global and local surrogate models, which utilizes the uncertainty level of the current population state to evaluate the approximation ability of the surrogate model in its predictions. In ASAPSO, the transformation between local and global surrogate models is controlled by an adaptive Gaussian distribution parameter with a gauge of the advisability to improve the search process with better local exploration and diversity in uncertain solutions. Four expensive optimization benchmark functions and an airfoil aerodynamic real-world engineering optimization problem are utilized to validate the effectiveness and performance of ASAPSO. Experimental results demonstrate that ASAPSO has superiority in terms of solution accuracy compared with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Direct reduction of iron (DRI) technology in fluidized beds has been identified as a promising approach due to its environmental benefits over other methods. Nevertheless, the process of iron particle sintering in the DRI approach poses a significant obstacle to its advancement. The present work investigated the phenomenon of agglomeration in fine iron particles across various temperatures and with multiple sintering force models of different intensities of solid bridge force. The study utilized a simple but comprehensive and cost-effective CFD model developed using the Eularian–Eularian two-fluid model. The model was explicitly incorporated with user-defined subroutines for the solid phase, while the gas phase was modeled with AVL Fire advance simulation software. The solid bridge force between solid particles was modeled as the inter-particle cohesive force. The model was validated with the experimental results and results from another CFD-DEM model for the same experiment. High temperatures with increased sintering forces were observed to have the most impact on the iron particle agglomeration, while the gas's superficial velocity had a minimal effect on it. The predictions of this model closely align with the CFD-DEM model results, providing sufficient reliability to implement this model on a large scale. [ABSTRACT FROM AUTHOR]

This paper focuses on predicting road passenger probability and optimizing taxi driving routes based on trajectory big data. By utilizing clustering algorithms to identify key passenger points, a method for calculating and predicting road passenger probability is proposed. This method calculates the passenger probability for each road segment during different time periods and uses a BiLSTM neural network for prediction. A passenger-seeking recommendation model is then constructed with the goal of maximizing passenger probability, and it is solved using the NSGA-II algorithm. Experiments are conducted on the Chengdu taxi trajectory dataset, using MSE as the metric for model prediction accuracy. The results show that the BiLSTM prediction model improves prediction accuracy by 9.67% compared to the BP neural network and by 6.45% compared to the LSTM neural network. The proposed taxi driver passenger-seeking route selection method increases the average passenger probability by 18.95% compared to common methods. The proposed passenger-seeking recommendation framework, which includes passenger probability prediction and route optimization, maximizes road passenger efficiency and holds significant academic and practical value. [ABSTRACT FROM AUTHOR]

The increase in mining depth necessitates higher strength requirements for hard rock pillars, making mine pillar stability analysis crucial for pillar design and underground safety operations. To enhance the accuracy of predicting the stability state of mine pillars, a prediction model based on the subtraction-average-based optimizer (SABO) for hyperparameter optimization of the least-squares support vector machine (LSSVM) is proposed. First, by analyzing the redundancy of features in the mine pillar dataset and conducting feature selection, five parameter combinations were constructed to examine their effects on the performance of different models. Second, the SABO-LSSVM prediction model was compared vertically with classic models and horizontally with other optimized models to ensure comprehensive and objective evaluation. Finally, two data sampling methods and a combined sampling method were used to correct the bias of the optimized model for different categories of mine pillars. The results demonstrated that the SABO-LSSVM model exhibited good accuracy and comprehensive performance, thereby providing valuable insights for mine pillar stability prediction. [ABSTRACT FROM AUTHOR]

High-Entropy Alloys (HEAs) represent a transformative class of materials characterized by multiple principal elements and high configurational entropy. This review article provides an in-depth examination of their structural particularities, prediction methodologies, and synthesis techniques. HEAs exhibit unique structural stability due to high-entropy effects, severe lattice distortions, and slow diffusion processes. Predictive models, including thermodynamic and kinetic approaches, are essential for understanding phase stability. Various synthesis methods impact HEA properties, and advanced characterization techniques are crucial for their study. The article highlights current applications and future research directions, emphasizing the potential of HEAs in diverse technological fields. [ABSTRACT FROM AUTHOR]

This paper addresses the challenges of close proximity operations, such as rendezvous, docking, and fly-around maneuvers for micro/nano satellites, which require high control precision under the low power and limited computational capabilities of spacecraft. Firstly, a three-degree-of-freedom air float simulator platform is designed for ground-based experiments. Subsequently, model predictive controllers based on constraints aware of particle filtering (CAPF-NMPC) are developed for executing operations such as approach, fly-around, and docking maneuvers. The results validate the effectiveness of the experimental system, demonstrating position control accuracy less than 0.03 m and attitude control accuracy less than 3°, maintaining lower computational resource consumption. This study offers a practical solution for the onboard deployment of optimized control algorithms, highlighting significant value for further engineering applications. [ABSTRACT FROM AUTHOR]

Due to the deformation of ships, it becomes difficult to ensure the accuracy of attitude measurement in typical areas on the deck, which seriously impacts the safety and operational efficiency of shipborne equipment. To address this issue, this paper presents a parameter identification method for dynamic deformation models based on angle increment differences and introduces the related vector machine (RVM) algorithm for online estimation of dynamic deformation model parameters. In view of the truncation error and non-Gaussian noise of the model, this article proposes a dynamic attitude measurement method based on model predictive filtering (MPF), constructs a dynamic measurement model using Rodrigues parameters in an inertial frame, and designs a maximum correlation entropy (MCE) robust filter to achieve robust estimation of deck dynamic deformation. The performance of the method is verified through simulation analysis and shipborne experiments. The comparative results indicate that, compared with existing methods, the proposed improved deck dynamic attitude measurement algorithm based on model prediction (IDAM) can substantially enhance the accuracy of attitude measurement in the presence of deck dynamic deformations. [ABSTRACT FROM AUTHOR]

Accurate PV power prediction is crucial for enhancing grid planning, optimizing dispatch operations, and advancing management strategies. In pursuit of this objective, this study proposes a short-term distributed PV power prediction method that incorporates temporal and spatial feature extraction as well as similar day analysis. Firstly, to address the poor adaptability of traditional clustering methods to time-series data, the K-shape clustering algorithm is employed to categorize the time series into different weather types. Secondly, to overcome the challenges posed by varying time resolutions in similar day analysis, a novel method based on Dynamic Time Warping (DTW) is proposed. This method calculates the similarity between the target days and the days to be collected, considering both the time of day and the day of the week. Subsequently, a PV power generation prediction model based on a convolutional long short-term memory (CNN-LSTM) network is developed to enhance prediction accuracy. To tackle the difficulty of manual hyperparameter tuning, the chaos reverse sparrow search algorithm (CRSSA) is introduced. Finally, a case study is conducted on the measured data of a distributed photovoltaic power station in a certain region of China. By comparing RMSE and MAPE, compared with other prediction models, the proposed prediction model and solving algorithm effectively reduced the relative error by more than 1%, verifying the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

With the explosive development of power edge equipment and the continuous improvement in power inspection performance, the requirements of substations and terminal equipment, such as drones with limited resources, cannot meet the strict delay and energy consumption requirements. This paper proposes an adaptive partitioning strategy for heterogeneous substation inspection systems. First, a layer delay prediction model and layer energy consumption prediction model are established on each heterogeneous node, and nonlinear characteristics related to delay and energy consumption are trained. On this basis, a deep neural network (DNN) hybrid partitioning strategy is proposed. The DNN task is divided into synchronous cooperative reasoning between terminal devices and multi-heterogeneous edge nodes. The experimental results show that the average absolute percentage error (MAPE) of the delay model was reduced by 31.49% on average. On drones and mobile edge nodes, the energy consumption model MAPE reduced the average by 21.92%, and the DNN end-to-end latency was reduced by 31.48%. The total cost of the system was reduced and the efficiency of UAV inspection was improved. [ABSTRACT FROM AUTHOR]

The prediction of patient attendance in emergency departments (ED) is crucial for effective healthcare planning and resource allocation. This paper proposes an early warning system that can detect emerging trends in ED attendance, offering timely alerts for proactive operational planning. Over 13 years of historical ED attendance data (from January 2010 till December 2022) with 1,700,887 data points were used to develop and validate: (1) a Seasonal Autoregressive Integrated Moving Average with eXogenous factors (SARIMAX) forecasting model; (2) an Exponentially Weighted Moving Average (EWMA) surge prediction model, and (3) a trend persistence prediction model. Drift detection was achieved with the EWMA control chart, and the slopes of a kernel-regressed ED attendance curve were used to train various machine learning (ML) models to predict trend persistence. The EWMA control chart effectively detected significant COVID-19 events in Singapore. The surge prediction model generated preemptive signals on changes in the trends of ED attendance over the COVID-19 pandemic period from January 2020 until December 2022. The persistence of novel trends was further estimated using the trend persistence model, with a mean absolute error of 7.54 (95% CI: 6.77–8.79) days. This study advanced emergency healthcare management by introducing a proactive surge detection framework, which is vital for bolstering the preparedness and agility of emergency departments amid unforeseen health crises. [ABSTRACT FROM AUTHOR]

Migraine is one of the most common neurological disorders, characterized by moderate-to-severe headache episodes. Autonomic nervous system (ANS) alterations can occur at phases of migraine attack. This study investigates patterns of ANS changes during the pre-ictal night of migraine, utilizing wearable biosensor technology in ten individuals. Various physiological, activity-based, and signal processing metrics were examined to train predictive models and understand the relationship between specific features and migraine occurrences. Data were filtered based on specified criteria for nocturnal sleep, and analysis frames ranging from 5 to 120 min were used to improve the diversity of the training sample and investigate the impact of analysis frame duration on feature significance and migraine prediction. Several models, including XGBoost (Extreme Gradient Boosting), HistGradientBoosting (Histogram-Based Gradient Boosting), Random Forest, SVM, and KNN, were trained on unbalanced data and using cost-sensitive learning with a 5:1 ratio. To evaluate the changes in features during pre-migraine nights and nights before migraine-free days, an analysis of variance (ANOVA) was performed. The results showed that the features of electrodermal activity, skin temperature, and accelerometer exhibited the highest F-statistic values and the most significant p-values in the 5 and 10 min frames, which makes them particularly useful for the early detection of migraines. The generalized prediction model using XGBoost and a 5 min analysis frame achieved 0.806 for accuracy, 0.638 for precision, 0.595 for recall, and 0.607 for F1-score. Despite identifying distinguishing features between pre-migraine and migraine-free nights, the performance of the current model suggests the need for further improvements for clinical application. [ABSTRACT FROM AUTHOR]

Background: COVID-19 has had a substantial influence on healthcare systems, requiring early prognosis for innovative therapies and optimal results, especially in individuals with comorbidities. AI systems have been used by healthcare practitioners for investigating, anticipating, and predicting diseases, through means including medication development, clinical trial analysis, and pandemic forecasting. This study proposes the use of AI to predict disease severity in terms of hospital mortality among COVID-19 patients. Methods: A cross-sectional study was conducted at King Abdulaziz University, Saudi Arabia. Data were cleaned by encoding categorical variables and replacing missing quantitative values with their mean. The outcome variable, hospital mortality, was labeled as death = 0 or survival = 1, with all baseline investigations, clinical symptoms, and laboratory findings used as predictors. Decision trees, SVM, and random forest algorithms were employed. The training process included splitting the data set into training and testing sets, performing 5-fold cross-validation to tune hyperparameters, and evaluating performance on the test set using accuracy. Results: The study assessed the predictive accuracy of outcomes and mortality for COVID-19 patients based on factors such as CRP, LDH, Ferritin, ALP, Bilirubin, D-Dimers, and hospital stay (p-value ≤ 0.05). The analysis revealed that hospital stay, D-Dimers, ALP, Bilirubin, LDH, CRP, and Ferritin significantly influenced hospital mortality (p ≤ 0.0001). The results demonstrated high predictive accuracy, with decision trees achieving 76%, random forest 80%, and support vector machines (SVMs) 82%. Conclusions: Artificial intelligence is a tool crucial for identifying early coronavirus infections and monitoring patient conditions. It improves treatment consistency and decision-making via the development of algorithms. [ABSTRACT FROM AUTHOR]

The chickpea plays a significant role in global agriculture and occupies an increasing share in the human diet. The main aim of the research was to develop a model for the prediction of two chickpea productivity traits in the available dataset. Genomic data for accessions were encoded in Artificial Image Objects, and a model for the thousand-seed weight (TSW) and number of seeds per plant (SNpP) prediction was constructed using a Convolutional Neural Network, dictionary learning and sparse coding for feature extraction, and extreme gradient boosting for regression. The model was capable of predicting both traits with an acceptable accuracy of 84–85%. The most important factors for model solution were identified using the dense regression attention maps method. The SNPs important for the SNpP and TSW traits were found in 34 and 49 genes, respectively. Genomic prediction with a constructed model can help breeding programs harness genotypic and phenotypic diversity to more effectively produce varieties with a desired phenotype. [ABSTRACT FROM AUTHOR]

Coarse roots and the root plate play an important role in tree resistance to uprooting. In this study, a qualitative mechanistic model was developed to analyze coniferous tree resistance to uprooting in relation to tree morphological characteristics. The sizes of the crown, stem, and root plate of twenty sample spruces and twenty sample Korean pines were individually measured for this purpose. Using Ground Penetrating Radar (GPR), the coarse root distribution and root plate size were detected. In the qualitative mechanistic model, a larger crown area increased the overturning moment, while higher DBH and root plate mass increased the resistance moment. The resistance coefficient (Rm) was calculated by comparing resistive and overturning moments, classifying samples into three uprooting hazard levels. Trees with smaller crown areas, larger stems, and root plates tend to have higher resistance to uprooting, as indicated by higher Rm values. This qualitative mechanistic model provides a useful tool for assessing coniferous standing tree uprooting resistance. [ABSTRACT FROM AUTHOR]

Current systems that allow inline pH control in the fermented dairy industry have drawbacks, such as protein adhesion on the non-glass pH probes, measurement distortion, frequent recalibration needs, and sensitivity to extreme pH conditions encountered during clean-in-place operations. Therefore, the objective of this study was to validate the feasibility of estimating the pH of milk during the yogurt making process by using a NIR light backscatter sensor measuring under different fermentation temperatures and milk protein concentrations using a mathematical model that correlates the light scatter signal with pH. Three replications of the experiment with two protein concentrations (3.5 and 4.0%) and two fermentation temperatures (43 and 46 °C) were used to validate this inline pH prediction model. Continuous and discontinuous measurements of pH were collected as a reference during fermentation, simultaneously with the light backscatter data acquisition. Also, the effect of adjusting the initial voltage gain of the light scatter device on the accuracy of the pH prediction model was evaluated. Temperature and initial voltage were the main factors affecting the fitting accuracy of the model. The adjustment of the initial voltage gain improved the pH prediction model fit. The model has been successfully validated for both continuous and discontinuous measurements of pH, with SEP values < 0.09 pH units and CV < 1.78%. The proposed optical inline and non-destructive method was feasible for inline pH monitoring of milk fermentation, avoiding traditional manual pH measurement. [ABSTRACT FROM AUTHOR]

The fluctuation of the tide is closely related to the production and life of people in coastal areas, and the change in the tide level will have a significant impact on the safety of infrastructure, ship travel, ecological environment, and other issues. Therefore, it is of great significance to analyze, study, and forecast the change in tide level. Aiming at the complex characteristics of nonlinearity, time-varying dynamics, and uncertainty generated by celestial bodies' movements and influenced by geographical as well as hydrometeorological factors, this paper proposes a combined model based on variational mode decomposition (VMD) and long short-term memory neural networks (LSTM). A tidal level prediction procedure is proposed by combining the harmonic analysis method with a neural network and takes the point tide data of Luchao Port from 2021 to 2022 as the applied data. First, the VMD algorithm decomposes the tidal level data into model components. Then, the LSTM model is used to predict each component. Finally, the predicted value of each component is superposed to obtain the final prediction result. Standard evaluation indexes were used to analyze the performance of the proposed model. The model's RMSE, MAE, MAPE, and R2 were 0.0385, 0.0267, 5.8327, and 99.91%, respectively, superior to other compared models (BP, SVM, and LSTM). This study can provide a reference for tidal level prediction. These results show that the VMD-LSTM model is an effective and reliable tidal level prediction tool with considerable potential in offshore engineering and maritime management. [ABSTRACT FROM AUTHOR]

Rapid urbanization and industrialization have caused water quality issues in urban rivers. Appropriate measures based on water quality monitoring systems and prediction methods are needed for water quality management. While South Korea has operated a water quality monitoring system that measures various environmental factors and has accumulated water quality data, a water quality prediction system is not in place. This study suggests a water quality prediction method based on a long short-term model using water quality and meteorological monitoring data. Additionally, we present a derived input set of the prediction model that can improve the prediction model performance. The prediction model's performance was evaluated by the coefficient of determination under various conditions, such as the hyperparameters, temporal resolution of input data, and application of upstream and downstream data. As a result, using the temporal resolution of the input data as hourly data improved predictions by an average of 25.6% over three days of the prediction period compared to daily data. Meanwhile, it was analyzed that the hyperparameters and using upstream and downstream data have a minor effect on the model performance. The results of this study underscore the crucial role of the number, duration, and temporal resolution of available monitoring data in water quality management. [ABSTRACT FROM AUTHOR]

Copyright of Cotton Textile Technology is the property of Cotton Textile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The support of athlete career excellence in sport is a growing societal issue. For professional athletes within North America, the factors that contribute to athlete career excellence are not well understood. The current investigation examined the relationships between three athlete career excellence resources: athletic identity; career engagement; and mental well-being. Using a non-random convenience sampling strategy, 72 professional athletes currently active in the sports of baseball, football, and ice hockey in North America participated in the study. It was found that athletic identity and career engagement significantly predicted mental well-being in North American professional athletes. Furthermore, both athletic identity and career engagement added significantly to the prediction model. The current investigation supports the conceptualisation and understanding of how North American professional athletes' career engagement and mental well-being contribute to athletes' striving for career excellence. Recommendations for further research and practical applications are considered. [ABSTRACT FROM AUTHOR]

A convolutional neural network is trained on a large dataset of suitably randomized film profiles and corresponding elastic energy densities ρ ɛ , computed by the finite element method. The trained model provides quantitative predictions of ρ ɛ for arbitrary profiles, surrogating its explicit calculation, and is used for the time integration of partial differential equations describing the evolution of strained films. The close match found between the neural network predictions and the "ground-truth" evolutions obtained by the finite element method calculation of ρ ɛ , even after tens-of-thousands of integration time-steps, validates the approach. A substantial computational speed up without significant loss of accuracy is demonstrated, allowing for million-steps simulations of islands growth and coarsening. The intriguing possibility of extending the domain size is also discussed. [ABSTRACT FROM AUTHOR]

The Atlantic Meridional Overturning Circulation (AMOC) is a significant component of the global ocean system, which has so far ensured a relatively warm climate for the North Atlantic and mild conditions in regions, such as Western Europe. The AMOC is also critical for the global climate. The complexity of the dynamical system underlying the AMOC is so vast that a long-term assessment of the potential risk of AMOC collapse is extremely challenging. However, short-term prediction can lead to accurate estimates of the dynamical state of the AMOC and possibly to early warning signals for guiding policy making and control strategies toward preventing AMOC collapse in the long term. We develop a model-free, machine-learning framework to predict the AMOC dynamical state in the short term by employing five datasets: MOVE and RAPID (observational), AMOC fingerprint (proxy records), and AMOC simulated fingerprint and CESM AMOC (synthetic). We demonstrate the power of our framework in predicting the variability of the AMOC within the maximum prediction horizon of 12 or 24 months. A number of issues affecting the prediction performance are investigated. [ABSTRACT FROM AUTHOR]

Copyright of Shipin Kexue/ Food Science is the property of Food Science Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Temporary employment has spiked in OECD countries over the last 40 years and is now a common feature of their labor market landscape. A large body of empirical literature examines the spread of temporary employment, but no systematic review and interpretation of its findings in light of economic theory exists. This survey aims at filling this gap by interpreting the key empirical results based on the predictions of the macro models in markets with frictions developed to address specific features of temporary employment. Revisions of workhorse models used so far to analyze temporary employment are also suggested. (JEL J22, J31, J41, J81, J83, K31) [ABSTRACT FROM AUTHOR]

The current extension limit prediction model for offshore extended-reach well (ERW) in mudstone does not consider the formation collapse, which poses a huge risk to offshore drilling construction. To address this problem, this paper presents new open-hole extension limit prediction model for ERW. By considering formation collapse, rate of penetration (ROP), and annular pressure loss, the extension limit models during normal drilling and tripping were derived. The sensitivity of geological and engineering factors was evaluated by analyzing limits for wells 1H and 2H. The research results showed that: (1) The extension limit increases with the ROP and formation collapse duration, but decreases with the increase in mud weight, plastic viscosity, and flow rate. (2) In ERWs, the mud flow rate has a significant impact on the extension limit than the plastic viscosity of mud fluid. However, mud weight has the least impact compared to the two. (3) Considering various parameters, the predicted extension limit of well 1H, when the mud weight is 1.16 g/cm3 [9.67 ppg], is 1593.28 m [5225.96 ft] less than the limit when the collapse period is not considered. [ABSTRACT FROM AUTHOR]

Tight sandstone reservoirs are significant sources of natural gas reserves. As traditional reserves become increasingly scarce and costly, optimizing the development of these reservoirs becomes crucial. This study introduces a novel two-phase gas–water flow model for single wells, incorporating both Darcy and non-Darcy flow equations. These equations are derived from mass conservation and momentum principles for both gas and water phases. Using data from a real tight gas well, our model, which includes stress-sensitive phases for gas and water, outperforms traditional Darcy flow models. Specifically, the average relative deviations in daily production rates were 0.1815% for gas and − 0.2677% for water, which are significantly smaller compared to traditional Darcy flow models. Further application of the non-Darcy flow model reveals strategies to enhance well performance. For example, mitigating liquid lock damage within a 2 m radius near the well could restore the permeability from 0.045 to 0.143 mD, thereby tripling the daily gas production. This non-Darcy flow model is easy to implement and shows significant potential in forecasting production yields in tight sandstone reservoirs, highlighting its importance in the petroleum and natural gas industry. [ABSTRACT FROM AUTHOR]

Background: Integrating life-threatening clinical simulations improves learning outcomes. This study assessed nursing students' critical thinking factors before and after simulation, evaluated nursing clinical reasoning ability and learning satisfaction at two time points, and explored relationships and predictions among critical thinking, clinical reasoning, and satisfaction before and after simulation. Method: Surveys and focus groups were used for this mixed-methods study. Results: Quantitative findings revealed increased critical thinking scores for curiosity, skepticism, and systematicity; clinical reasoning; and satisfaction after simulation. Qualitative results supported these improvements and indicated enhanced curiosity for clinical knowledge and iterative phases of clinical reasoning. Students expressed satisfaction with the simulations. Objectivity significantly influenced clinical reasoning and satisfaction in nursing students following life-threatening simulations. Conclusion: Fostering a culture of critical thinking in life-threatening simulations is crucial. Educators must teach the importance of objectivity in clinical practice, encourage critical evaluation, and foster self-reflection in simulations. [J Nurs Educ. 2024;63(9):595–603.] [ABSTRACT FROM AUTHOR]

Filler components play a crucial role as thermo‐mechanical reinforcement to the epoxy‐based solder mask, ensuring effective insulation and passivation. This study investigates the impact of different inorganic filler types (talc, silica (SiO2), boron nitride (BN) and barium sulfate (BaSO4)) and loadings (5 and 15 wt%) on the tensile and thermal properties of the epoxy composites. The composites were blended, cast and thermally cured. Of these composites, only 15 wt% SiO2/epoxy composite exhibits notable increments in both tensile strength and modulus, surpassing unfilled epoxy by 11.65% and 31.9%, respectively. It also displays the highest elongation at break, supported by small particle size, high specific surface area and minimal void volume fraction. For thermal tests, the addition of all fillers increases the storage modulus in both glassy and rubbery regions, especially 15 wt% talc/epoxy composite with 30.09% increment at 25 °C. Additionally, all fillers raise the glass transition temperature (Tg), notably improving it by 9 °C in the 15 wt% BN/epoxy composite. Moreover, their inclusion generally enhances the onset decomposition temperature (Tonset) and reduces weight loss during decomposition. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Legal documents, like contracts or laws, are subject to interpretation. Different people can have different interpretations of the very same document. Large parts of judicial branches all over the world are concerned with settling disagreements that arise, in part, from these different interpretations. In this context, it only seems natural that during the annotation of legal machine learning data sets, disagreement, how to report it, and how to handle it should play an important role. This article presents an analysis of the current state-of-the-art in the annotation of legal machine learning data sets. The results of the analysis show that all of the analysed data sets remove all traces of disagreement, instead of trying to utilise the information that might be contained in conflicting annotations. Additionally, the publications introducing the data sets often do provide little information about the process that derives the "gold standard" from the initial annotations, often making it difficult to judge the reliability of the annotation process. Based on the state-of-the-art, the article provides easily implementable suggestions on how to improve the handling and reporting of disagreement in the annotation of legal machine learning data sets. [ABSTRACT FROM AUTHOR]

The stable and efficient regulation of voltage and frequency is a critical issue associated with the functioning of modern power system network having renewable integration. This manuscript focuses on the concurrent regulation of voltage and frequency in a power network comprising multiple generating sources. Herein, along with conventional thermal and diesel plants, renewable generations from different sources have been considered such as wind and solar photovoltaic (PV) resources. Further, in a fresh attempt, the authors have modeled wind and solar PV generation using two different stochastic modeling methods concerning combined voltage and frequency loops in the regulated power system model. Furthermore, the novel Leader Harris Hawks Optimized Model Predictive Controller (MPC‐LHHO) has been applied to concurrently minimize the voltage and frequency deviations in the given power network. To address the intermittent nature of load and renewable generations, various auxiliary frequency controllers, such as the unified power flow controller (UPFC) and electric vehicle (EV) integration with the grid, have been implemented. The robustness of the proposed control method has been successfully validated through diverse scenarios of random loadings. [ABSTRACT FROM AUTHOR]

An efficient supply chain (SC) management requires that decisions are taken to minimize the effects of parametric uncertainties and unpredictable external disturbances. In this article, we consider this problem with reference to a multi‐stage SC (MSSC) whose dynamics is characterized by the following elements of complexity: perishable goods with uncertain perishability rate, an uncertain future customer demand that is only known to fluctuate inside a given compact set. The problem we face is to define a resilient and robust Replenishment Policy (RP) such that at any stage the following requirements are satisfied: the fulfilled demand is maximized, overstocking is avoided, the bullwhip effect (BE) is mitigated. These objectives should be pursued despite the mentioned uncertainties and unexpected customer demand behaviors violating the bounds of the compact set. Robustness is here intended with respect to uncertainty on the perishability rate, and resiliency as the ability to quickly react to the mentioned unforeseen customer demands. We propose a method based on a distributed resilient robust model predictive control (DRRMPC) approach. Each local robust MPC (RMPC) involves solving a Min‐Max constrained optimization problem (MMCOP). To drastically reduce the numerical complexity of each MMCOP, we parametrize its solution by means of B‐spline functions. [ABSTRACT FROM AUTHOR]

This paper presents a real‐time optimization method for nonlinear model predictive control (NMPC) of systems governed by partial differential equations (PDEs). The NMPC problem to be solved is formulated by discretizing the PDE system in space and time by using the finite difference method. The proposed method is called the double‐layer Jacobi method, which exploits both the spatial and temporal sparsities of the PDE‐constrained NMPC problem. In the upper layer, the NMPC problem is solved by ignoring the temporal couplings of either the state or costate (Lagrange multiplier corresponding to the state equation) equations so that the spatial sparsity is preserved. The lower‐layer Jacobi method is a linear solver dedicated to PDE‐constrained NMPC problems by exploiting the spatial sparsity. Convergence analysis indicates that the convergence of the proposed method is related to the prediction horizon. Results of a numerical experiment of controlling a heat transfer process show that the proposed method can be two orders of magnitude faster than the conventional Newton's method exploiting the banded structure of NMPC problems. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid data‐driven and physics‐based simulation technique for seismic response evaluation of steel Buckling‐Restrained Braced Frames (BRBFs) considering brace fracture. Buckling‐Restrained Brace (BRB) fracture is represented by cumulative plastic deformation capacity. A dataset, consisting of 95 past BRB laboratory tests and 120 simulated BRB responses generated using the finite element method, is first developed. An Artificial Neural Network‐based (ANN) predictive model is then trained using the training dataset to estimate the cumulative plastic deformation of BRBs. The prediction capability of the ANN‐based predictive model is validated using the training dataset and an existing regression‐based predictive model. In the second part of the paper, an hybrid simulation technique combining the data‐driven model and physics‐based numerical modeling is presented to conduct the nonlinear time history analysis, followed by 1) validation against a full‐scale BRBF testing and 2) demonstration of the proposed simulation technique using a six‐story BRBF. The results confirm that the proposed predictive model can predict the BRB fracture with sufficient accuracy. Furthermore, the hybrid data‐driven physics‐based simulation technique can be used as a powerful tool for dynamic analysis of BRBFs considering BRB fracture. [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

There is no doubt that accurate short-term inbound metro ridership forecasting has always been a significant part in terms of intelligent transportation. Based on the excellent performance of deep learning models in dealing with processing time series data, a large number of researchers have adopted deep learning methods for short-term inbound metro ridership prediction. However, considering the non-linear and cyclical nature of inbound metro ridership, the prediction accuracy using only deep learning models is limited. To solve this problem, a hybrid prediction model combining Ensemble Empirical Mode Decomposition (EEMD), subsequences recombination, empirical wavelet transform (EWT) and long short-term memory (LSTM) network for inbound metro ridership which can greatly reduce the complexity of the original inbound metro ridership is proposed in this article. To prove the superiority of the proposed EEMD-EWT-LSTM-based model, we compare it with recent main forecasting models on three real datasets from the 2019 TIANCHI competition. The experimental results demonstrate that the reduction in WMAPE of the hybrid model almost reach to 10 percent compared to the non-hybrid models. [ABSTRACT FROM AUTHOR]

Trip purpose is a meaningful aspect of travel behaviour for the understanding of urban mobility. However, it is non-trivial to automatically obtain trip purposes. On one hand, trip purposes are naturally diverse and complicated, but the available predictive data sources are limited in real-world scenarios. On the other hand, since trip purpose labeling is costly and the development levels of cities are unbalanced, it is infeasible to access large-scale labeled data in less developed cities to train advanced prediction models. To narrow the gaps, this article presents A new Graph Embedding Network and active Domain Adaptation based framework (AGENDA) that only requires open data sources and is capable of predicting in both label-rich cities and label-scarce cities. Specifically, in label-rich source cities, we first use the vehicle's GPS trajectory and open POI check-ins to augment trip contexts. Then we establish a supervised graph embedding network with two attention mechanisms to extract the passenger's latent activity semantics and a classifier to predict trip purpose. To enable the prediction in label-scarce target cities, we further devise an active domain adaptation framework, in which adversarial domain adaptation is used to transfer the source-learned knowledge, and active learning is used to integrate human intelligence in the model training. A group of experiments are conducted with real-world datasets in Beijing and Shanghai. Evaluation results demonstrate that the proposed framework significantly outperforms existing trip purpose prediction algorithms, and could make accurate trip purpose prediction in label-scarce cities with much fewer labeling efforts. [ABSTRACT FROM AUTHOR]

We document considerable cross-investor variation in survey expectations about aggregate stock market returns. Although most investors are extrapolators who expect higher returns after a good market performance, some are contrarians who expect lower returns after a good performance. More notably, compared with extrapolators, contrarians have less persistent expectations that are corrected more quickly. We then develop a dynamic equilibrium model accounting for these differences in expectations and find that the equilibrium stock price exhibits short-term momentum and long-term reversal as in the data. Furthermore, we test the key predictions of our model linking the observable differences in extrapolators' and contrarians' expectations to aggregate stock market momentum and future stock performance and find supportive evidence for our model mechanism. This paper was accepted by Lukas Schmid, finance. Supplemental Material: The data files are available at https://doi.org/10.1287/mnsc.2023.4960. [ABSTRACT FROM AUTHOR]

BACKGROUND: Biocontrol agents (BCAs) are alternatives to synthetic fungicides with low risk to the environment and human health. Although several studies on the biocontrol of gray mold in vineyards have been performed, it is necessary to improve the usage of BCAs in fields conditions. Therefore, in the present study, BCAs were used both in calendar‐based [based on four growth stages (GSs), i.e., flowering, pre‐bunch closure, veraison, and before harvest] and predictive model‐based strategies (only when Botrytis cinerea infection risk was predicted by the model). The BCAs applied during the seasons were selected considering the grapevine GSs. Treatments performed with BCAs were compared with synthetic fungicide treatments and an untreated control. The trials were conducted in three experimental vineyards with four epidemics. To evaluate the level of gray mold control of each treatment, disease severity was assessed at harvest and the presence of latent infection was evaluated. RESULTS: The integrative use of the predictive model and BCAs provided satisfactory levels of gray mold control, with gray mold severity levels significantly lower (P < 0.001) than those of the untreated control, which had severity values (< 7%) similar to those observed with synthetic fungicides following both calendar and model‐based strategies. CONCLUSIONS: The integrative use of the predictive model and BCAs represents a valid alternative to conventional methods of gray mold control in vineyards, with more than 75% reduction in fungicide usage. © 2024 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Essays are one of the most used exams to assess students. Universitas Terbuka Indonesia (Open University) conducts three online essay exams within a week for each first-year course, accounting for 30% of the mid-test score. The university has over 500.000 students and hundreds of courses. However, the limited number of correctors resulted in a time-consuming and ineffective process of checking and scoring each student's essay response. Even score results can be subjective, unfair, lack detailed feedback from students, miss contextual and creative aspects, and be less reliable with complex or non-standard writing. This research proposes a hybrid approach of deep learning models and natural semantic grammar to improve and optimize an AES system, with the following steps: First, the datasets are collected from hundreds of students' answers, each representing a single question. The datasets are pre-processed and augmented to enhance the quantity and variety of the original data and scores. Second, the BERT approach was utilized to transform each text dataset into vector feature spaces using pre-trained model weights. Finally, a prediction score model was generated using the BiLSTM method. The experiment's results show that the model had an average Cohen's Kappa score of 0.749 and the highest Cohen's Kappa score of 0.91. This BERT-BiLSTM optimization model also has a better Cohen's Kappa Score average (0.820) than the ATT-CNN-LSTM, BERT-XLNET, R2BERT, and CNNBiLSTM models. After conducting a test on 46 lecturers, the results showed that the average time taken to examine one course for each student decreased to 1 minute and 2 seconds. Additionally, 92.75% of the lecturers found the process of checking responses to be fairer and more objective. In the results of the trial with 200 students, the mean percentage of question indications related to UI/UX, fairness, responsiveness, rubric, feedback, and transparency across students was 93.72%. [ABSTRACT FROM AUTHOR]