A rapid and efficient technique using an electronic nose based on a mass detector combined with headspace sampling (HS-SPME-MS e-nose) and chemometric tools was applied to classify beer samples between fresh and aged and between samples contained in aluminium cans or glass bottles, and to predict the shelf life of beer. The mass spectra obtained from the HS-SPME-MS e-nose contain information on the volatile compounds, recorded as the abundance of each ion at different mass-to-charge (m/z) ratios. The analysis was performed on 53 samples aged naturally for eleven months in the absence of light and with a controlled temperature of around 14° C +/- 0.5° C. Principal Component Analysis (PCA) was performed on the data, showing a grouping of samples between fresh and aged. Partial Least Square Discriminant Analysis (PLS-DA) allowed discriminating fresh from aged beers but was not able to discriminate samples packaged in aluminium cans or in glass bottles. Finally, Partial Least Square Regression (PLSR) was applied to build a prediction model and showed to be effective to predict beer shelf life.

Lithium-ion batteries with improved energy densities have made understanding the Solid Electrolyte Interphase (SEI) generation mechanisms that cause mechanical, thermal, and chemical failures more complicated. SEI processes reduce battery capacity and power. Thus, a review of this area's understanding is important. It is essential to know how batteries degrade in EVs to estimate battery lifespan as it goes, predict, and minimize losses, and determine the ideal time for a replacement. Lithium-ion batteries used in EVs mainly suffer two types of degradation: calendar degradation and cycling degradation. Despite the existence of several existing works in the literature, several aspects of battery degradation remain unclear or have not been analyzed in detail. This work presents a systematic review of existing works in the literature. The results of the present investigation provide insight into the complex relationships among various factors affecting battery degradation mechanisms. Specifically, this systematic review examined the effects of time, side reactions, temperature fluctuations, high charge/discharge rates, depth of discharge, mechanical stress, thermal stress, and the voltage relationship on battery performance and longevity. The results revealed that these factors interact in complex ways to influence the degradation mechanisms of batteries. For example, high charge currents and deep discharges were found to accelerate degradation, while low temperatures and moderate discharge depths were shown to be beneficial for battery longevity. Additionally, the results showed that the relationship between cell voltage and State-of-Charge (SOC) plays a critical role in determining the rate of degradation. Overall, these findings have important implications for the design and operation of battery systems, as they highlight the need to carefully manage a range of factors to maximize battery performance and longevity. The result is an analysis of the main articles published in this field in recent years. This work aims to present new knowledge about fault detection, diagnosis, and management of lithium-ion batteries based on battery degradation concepts. The new knowledge is presented and discussed in a structured and comprehensive way.

Background Acute kidney injury (AKI) is a common comorbidity in the intensive care unit (ICU), with higher mortality rate among those who receive continuous renal replacement therapy (CRRT). This study aimed to investigate the association of white blood cell (WBC) levels with all-cause mortality in AKI patients undergoing CRRT. Method We conducted a post hoc analysis of ICU patient data from multiple centers in Korea. First, the levels of WBCs were classified into four groups based on quartiles. Second, the relationship between different WBC levels and mortality was investigated with the Kaplan-Meier (K-M) survival curves, Cox proportional hazards model, and generalized additivity model (GAM). Finally, we used multiple imputation to avoid bias caused by non-randomized missing data. The endpoints were short-term (28 days) and long-term (90 days) mortality. Result In our analysis, a total of 1,100 ICU patients were included. Among them, 670 (60.90%) and 781 (71.00%) died within 28 and 90 days, respectively. K-M survival curves showed that patients with the lowest WBC levels had the highest risk of mortality for both outcomes. Adjusted multivariate Cox regression analysis confirmed that compared with the reference level (quartile 2), low WBC levels increased the risk of both 28-day mortality (quartile 1, HR = 1.43, 95% CI: 1.13–1.83, P = 0.004) and 90-day mortality (quartile 1: HR = 1.32; 95% CI: 1.05-1.66, P = 0.016). GAM analysis showed a non-linear, U-shaped relationship between pre-CRRT WBC levels and all-cause mortality (non-linear P < 0.05). Conclusion The baseline WBC level is an independent predictor of prognosis for ICU patients receiving CRRT. Patients in the lowest WBC quartile had the highest risk of all-cause mortality. These results provide further evidence that early observation and intervention may have a prognostic value for these high-risk patients.

This paper explores the application of various machine learning techniques for predicting customer churn in the telecommunications sector. We utilized a publicly accessible dataset and implemented several models, including Artificial Neural Networks, Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, and gradient boosting techniques (XGBoost, LightGBM, and CatBoost). To mitigate the challenges posed by imbalanced datasets, we adopted different data sampling strategies, namely SMOTE, SMOTE combined with Tomek Links, and SMOTE combined with Edited Nearest Neighbors. Moreover, hyperparameter tuning was employed to enhance model performance. Our evaluation employed standard metrics such as Precision, Recall, F1-Score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). Regarding the F1-Score metric, CatBoost demonstrates superior performance compared to other machine learning models, achieving an outstanding 93% following the application of Optuna hyperparameter optimization. In the context of the ROC AUC metric, both XGBoost and CatBoost exhibit exceptional performance, recording remarkable scores of 91%. This achievement for XGBoost is attained after implementing a combination of SMOTE with Tomek Links, while CatBoost reaches this level of performance after the application of Optuna hyperparameter optimization.

Air quality is one of the most concerning problems in major industrialized cities in the world. Prediction of future air quality is highly relevant to public health. In some big cities, multiple air quality measurement stations are deployed at different locations to monitor air pollutants, such as NO2, CO, PM 2.5 and PM 10, over time. At every monitoring time stamp t, we observe one station×feature matrix xt of the pollutant data, which represents a spatio–temporal process. Traditional methods on prediction of air quality typically use data from one station or can only predict a single pollutant (such as PM 2.5) at a time, which ignores the spatial correlation among different stations. Moreover, the air pollution data are typically highly nonstationary, We propose a de-trending graph convolutional LSTM (long short term memory) to continuously predict the whole station×feature matrix in the next 1 to 48 hours, which not only captures the spatial dependency among multiple stations by replacing an inner product with convolution, but also incorporates the de-trending signals (transform a nonstationary process to a stationary one by differencing the data) into our model. Experiments on the air quality data of the city Chengdu and multiple major cities in China demonstrate the feasibility of our method and show promising results.

The synthesis and characterization of the multicomponent crystals formed by 2,2’-thiodiacetic acid (H2tda) and 2,6-diaminopurine (Hdap) or N9-(2-hydroxyethyl)adenine (9heade) are reported. The crystals are in the salt rather than cocrystal form, as witnessed by single crystal X-ray diffractometry where a structural analysis revealed their ionic nature, confirming the proton transfer from the 2,2’-thiodiacetic acid to the basic groups of the coformers. The new multicomponent crystals have molecular formulas [(H9heade+)(Htda)] (1) and [(H2dap+)2(tda2)]·2H2O (2), and were also characterized by FTIR, elemental analysis as well as thermogravimetric/differential scanning calorimetry (TG/DSC) analyses. In the crystal packing the ions interact with each other via O–H···N, O–H···O. N–H···O and N–H···N hydrogen bonds generating cyclic hydrogen bonded motifs with graph-set notation of R22(16), R22(10), R32(10), R33(10), R22(9), R32(8) and R42(8), to form different supramolecular homo- and hetero-synthons. In addition, in the crystal packing of 2, pairs of diaminopurinium ions display an strong anti-parallel ,-stacking interaction, with short inter-centroids and interplanar distances (3.39 and 3.24 Å respectively) and fairly tight angle (17.5°). These assemblies have been further analyzed energetically by using DFT calculations, MEP surface analysis and QTAIM characterization.

Electrochemical Impedance Spectroscopy techniques were applied in this work to 9 lead-acid battery prototypes fabricated industrially, divided on three type/technology packages. Frequency dependent impedance changes were interpreted during successive charge/discharge cycles on two distinct stages: 1) immediately after fabrication; and 2) after a controlled aging procedure to 50% Depth of Discharge, following industrial standards. By investigating their State of Health behaviour vs electrical response, three methods were employed, namely the (Q-Q0) total charge analysis, the decay values of Constant Phase Element in the equivalent Randles circuits, and the resonance frequency of the circuit. A direct correlation has been found for prediction of the best performant batteries in each package, thus allowing a qualitative analysis capable to provide the decay of the battery State of Health. We emphasized which parameters are directly connected with their lifetime performance in both stages, and by consequence, which type/technology battery prototype emphasize the best performance. Based on this methodology, the industrial producers can further establish the quality of the novel batteries in terms of performance vs lifespan, allowing them to validate the novel technological innovations implemented in the current prototypes.

The present research aimed at understanding individuals’ vaccination intentions and behaviours against COVID-19 through two different studies. In Study 1 (N = 213, 73% women; mean age = 24.03) the PMT model was tested considering the fear of COVID-19 as a possible mediator between threat appraisal (in terms of both health and social life) and intentions to get vaccinated when vaccination was not already available. In Study 2 (N = 1111, 68.9% women; mean age = 38.33), we aimed to understand how people who got vaccinated and the ones who did not differed, considering fear of vaccination, personality and vaccination hesitancy, which is determined not only by strictly individual but also by social factors. In study 1, contrary to what we expected, fear of Covid-19 was not a significant predictor of vaccination intention, which was predicted by both response efficacy and self-efficacy. In Study 2, in line with previous studies, vaccine hesitancy was negatively related to vaccination. More specifically, the social-oriented dimension of collective responsibility was the strongest predictor of effective behaviour. Our findings provide insights into the complexity of vaccine acceptance and emphasise the need for targeted interventions to promote vaccination and mitigate the spread of infectious diseases.

Arctic sea ice prediction holds significant importance for facilitating Arctic route planning, optimizing fisheries management, and advancing the field of sea ice dynamics research. While various deep learning models have been developed for sea ice prediction, they predominantly operate at the seasonal or sub-seasonal scale, often focusing on localized areas, and few cater to full-region daily scale prediction. This study introduces the use of spatiotemporal sequence data prediction models, namely, the convolutional LSTM (ConvLSTM) and predictive recurrent neural network (PredRNN), for the prediction of sea ice concentration (SIC). Our analysis reveals that, when solely utilizing SIC historical data as the input, the ConvLSTM model outperforms the PredRNN model in SIC prediction. To enhance the model's capacity to capture spatiotemporal relationships between multiple variables, we expanded the range of input data types to form the ConvLSTM-multi and PredRNN-multi models. Experimental findings demonstrate that the ConvLSTM-multi model excels in assimilating the influence of reanalysis data on sea ice within the sea ice edge region, thus exhibiting superior performance in predicting daily Arctic SIC over the subsequent 10 days. Furthermore, sensitivity tests on various model parameters highlight the substantial impact of sea surface temperature and prediction date on the accuracy of daily sea ice prediction. Additionally, meteorological and oceanographic parameters primarily affect the prediction accuracy of the thin ice region at the edge of the sea ice.

Atrial fibrillation (AF) is the most common cardiac arrhythmia encountered in clinical practice, affecting millions of individuals worldwide. The management of AF presents significant challenges due to its complex nature and diverse patient profiles. In recent years, the integration of artificial intelligence (AI) and machine learning technologies has emerged as a promising approach to enhance various aspects of AF management. This comprehensive review aims to explore the evolving role of AI in AF management, with a focus on its potential applications in diagnosis, risk prediction, treatment selection, and patient monitoring. Real academic references were employed to provide evidence-based insights into the impact of AI on AF management.

Artificial intelligence algorithms have gained widespread adoption in the field of air conditioning load prediction. However, their prediction accuracy is substantially influenced by the quality of training samples. Training samples that lack relevance to the predicted moments can introduce interference into the neural network's learning process, potentially leading to a state of local convergence during its iterative process. This, in turn, diminishes the robustness and generalization capabilities of the prediction model. To enhance the prediction accuracy of air conditioning load prediction models based on artificial intelligence algorithms, this study presents an artificial intelligence algorithm prediction model based on the method of sample similarity sample screening. Initially, the comprehensive similarity coefficient between samples is computed using the gray correlation analysis method, enriched with enhancements in information entropy. Subsequently, a subset of closely related samples is extracted from the original dataset and employed as the training dataset for the artificial intelligence prediction model. Finally, the trained artificial intelligence algorithm prediction model is deployed for air conditioning load prediction. The results illustrate that the method of screening training samples based on sample similarity effectively improves the prediction accuracy of BP neural network (BPNN) and extreme learning machine (ELM) prediction models. However, it is important to note that this approach may not be suitable for genetic algorithm BPNN (GABPNN) and support vector regression (SVR) models.

(1) Background: The analysis of athletic performance has always aroused great interest from sport scientist. This study utilized machine learning methods to build predictive models using a comprehensive CrossFit (CF) dataset, aiming to reveal valuable insights into the factors influencing performance and emerging trends.; (2) Methods: The study used Random Forest (RF) and Multiple Linear Regression (MLR) models to predict performance in four key weightlifting exercises within CF: clean &amp; jerk, snatch, back squat, and deadlift. Performance was evaluated using R-squared (R2) values and Mean Squared Error (MSE). Feature importance analysis was conducted using RF, XGBoost, and AdaBoost models.; (3) Results: The RF model excelled in deadlift performance prediction (R2 = 0.80), while the MLR model demonstrated remarkable accuracy in clean &amp; jerk (R2 = 0.93). Across exercises, clean &amp; jerk consistently emerged as a crucial predictor. The feature importance analysis revealed intricate relationships among exercises, with gender significantly impacting deadlift performance.; (4) Conclusions: This research advances our understanding of performance prediction in CF through machine learning techniques. It provides actionable insights for practitioners, optimize performance, and demonstrates the potential for future advancements in data-driven sports analytics.

This study investigates the complex interplay between public sentiment, as captured through news titles and descriptions, and the stock prices of three major tech companies: Microsoft (MSFT), Tesla (TSLA), and Apple (AAPL). Leveraging advanced analytical methods including Pearson correlation, wavelet coherence, and regression analysis, this research probes the degree to which stock price fluctuations can be attributed to the polarity of media sentiment. The methodology combines statistical techniques to assess sentiment's predictive power on stock opening and closing prices, while wavelet coherence analysis unveils the temporal dynamics of these relationships. Results demonstrate a significant correlation between sentiment polarity and stock prices, with description polarity affecting Microsoft's opening prices, title polarity influencing Tesla's opening prices, and a positive impact of title polarity on Apple's closing prices. However, Tesla's stock showed no significant coherence, indicating a potential divergence in how sentiment affects stock behavior across companies. The study highlights the importance of sentiment analysis in forecasting stock market trends, revealing not only direct correlations but also lagged influences on stock prices. Despite its focus on large-cap tech firms, this research provides a foundational understanding of sentiment's financial implications, suggesting further investigation into smaller firms and other market sectors.

One of the most important sources of energy is the sun. Taiwan is located at north 22-25° latitude. Due to its proximity to the equator, it experiences only a small angle of sunlight incidence. Its unique geographical location which can obtain sustainable and stable solar resources. This study takes research on the forecast of solar radiation to maximize the benefits of solar power generation, and develops methods that can predict the future solar radiation pattern to help reduce the costs of solar power generation. This study builds supervised machine learning models, known as deep neural network (DNN) and long short-term memory neural network (LSTM). The hybrid supervised and unsupervised model, namely cluster-based artificial neural network (k-means clustering and fuzzy C-means clustering-based models), was developed. After establishing these models, the study evaluated their prediction results. For different prediction periods, the study selected the best-performing model based on the results and proposed combining them to establish a real-time updated solar radiation forecast system capable of predicting the next 12 hours. The study area covered Kaohsiung, Hualien, and Penghu in Taiwan. Data from ground stations of the Central Weather Administration, collected between 1993 and 2021, as well as the solar angle parameters of each station, were used as input data for the model. The results of this study show that different models have their advantages and disadvantages in predicting different future times. Therefore, the hybrid prediction system can predict future solar radiation more accurately than a single model.

Data mining techniques have garnered significant attention within the realm of education. However, the procurement of ample student data poses a formidable challenge. In response to this challenge, we present a student dataset characterized by its size and distinctive attributes. This dataset encompasses various task-related topics interconnected through a learning pathway, thereby enabling researchers to delve into the data from novel perspectives. Moreover, it encompasses extensive longitudinal student behavioral data, a rarity that adds substantial value. Spanning the years from 2010 to 2021, our dataset comprises a cohort of 7,933 students, 64,344 test scores, and 183,390 behavior records, solidifying its status as a valuable resource for educational research. In our experiments, we achieved successful predictions of students' test outcomes based on behavioral learning data. The strengths of our dataset render it apt for analyzing the nexus between student conduct and academic performance, crafting personalized learning recommendations, and pursuing various other research pursuits.

With the rapid development of artificial intelligence, machine learning is gradually becoming popular in predictions in all walks of life. In meteorology, It is gradually competing with traditional climate predictions dominated by physical models. This survey aims to consolidate the current understanding of Machine Learning (ML) applications in weather and climate prediction—a field of growing importance across multiple sectors including agriculture and disaster management. Building upon an exhaustive review of more than 20 methods highlighted in existing literature, this survey pinpointed eight techniques that show particular promise for improving the accuracy of both short-term weather and medium-to-long-term climate forecasts. According to the survey, while ML demonstrates significant capabilities in short-term weather prediction, its application in medium-to-long-term climate forecasting remains limited, constrained by factors such as intricate climate variables and data limitations. Current literature tends to focus narrowly on either short-term weather or medium-to-long-term climate forecasting, often neglecting the relationship between the two, as well as general neglect of modelling structure and recent advances. By providing an integrated analysis of models spanning different time scales, this survey aims to bridge these gaps, thereby serving as a meaningful guide for future interdisciplinary research in this rapidly evolving field.

Sparse training (ST) aims to ameliorate deep learning by replacing fully connected artificial neural networks (ANNs) with sparse or ultra-sparse ones, such as brain networks are, therefore it might benefit to borrow brain-inspired learning paradigms from complex network intelligence theory. Here, we launch the ultrasparse advantage challenge, whose goal is to offer evidence on the extent to which ultra-sparse (around 1% connection retained) topologies can achieve any leaning advantage on fully connected. Epitopological learning is a field of network science and complex network intelligence that studies how to implement learning on complex networks by changing the shape of their connectivity structure (epitopological plasticity). One way to implement Epitopological (epi- means new) Learning is via link prediction: predicting the likelihood of nonobserved links to appear in the network. Cannistraci-Hebb learning theory inspired the CH3-L3 network automata rule for link prediction which is effective for general-purpose link prediction. Here, starting from CH3-L3 we propose Epitopological Sparse Meta-deep Learning (ESML) to apply Epitopological Learning to sparse training. In empirical experiments, we find that ESML learns ANNs with ultra-sparse hyperbolic (epi-)topology in which emerges a community layer organization that is meta-deep (meaning that each layer also has an internal depth due to powerlaw node hierarchy). Furthermore, we discover that ESML can in many cases automatically sparse the neurons during training (arriving even to 30% neurons left in hidden layers), this process of node dynamic removal is called percolation. Starting from this network science evidence, we design Cannistraci-Hebb training (CHT), a 4-step training methodology that put ESML at its heart. We conduct experiments on 6 datasets and 3 network structures (MLPs, VGG16, ResNet50) comparing CHT to dynamic sparse training SOTA algorithms and fully connected network. The results indicate that, with a mere 1% of links retained during training, CHT surpasses fully connected networks on VGG16 and ResNet50. This key finding is an evidence for ultra-sparse advantage and signs a milestone in deep learning. CHT acts akin to a gradient-free oracle which adopts CH3-L3 based epitopological learning to guide the placement of new links in the ultra-sparse network topology to facilitate sparse-weight gradient learning, and this in turn reduces the convergence time of ultra-sparse training. Finally, CHT offers first examples of parsimony dynamic sparse training because, in many datasets, it canretain network performance by percolating and significantly reducing the node network size.

Website defacement is an illegal electronic act of changing a website. In this paper, robust machine learning classifiers’ capabilities were exploited to select the best input feature set for evaluating a website’s defacement risk. Zone-H, a private organization, offered us a defacement mining dataset. A sample of 93644 datapoints was concisely pre-processed and used for modelling purposes. Considering multidimensional features as input, reason and hackmode variables were chosen as outputs. Massive machine learning models were examined; however, decision tree (DT), k-nearest neighbour (k-NN), and random forest (RF) were the most powerful algorithms used to predict the target model. The input variables 'domain', 'system', 'web_server','redefacement', 'type', 'def_grade', and 'reason/hackmode' were tested and used to shape the final model. Using the cross-validation (CV) technique, the model’s key performance factors were calculated and reported. After calculating the average scores for the hyperbolic metrics (i.e., max-depth, min-sample-leaf, weight, max-features, and CV), both targets were evaluated, and the learning algorithms were ranked as RF, DT, and k-NN. The reason and hackmode variables were thoroughly analysed. The average score accuracies for the reason and hackmode targets were 0.85 and 0.585, respectively. The results showed a significant development in terms of modelling and optimizing website defacement risk. The study also successfully addresses the main cybersecurity concerns, in particular website defacement.

Abstract: In recent years, the construction engineering sector has undergone a transformative shift towards the integration of machine learning (ML) techniques, particularly in predicting the properties of steel fiber-reinforced concrete (SFRC). Despite the theoretical sophistication of existing models, a persistent challenge remains – their opacity, lacking transparency and real-world relevance for practi-tioners. To address this gap and advance our current understanding, this study employs the extra gradient (XG) Boosting algorithm, crafting a comprehensive ap-proach. Grounded in a meticulously curated database drawn from 43 seminal pub-lications, encompassing 420 distinct records, this research focuses predominantly on three primary fiber types: crimped, hooked, and mil-cut. Complemented by hands-on experimentation involving 20 diverse SFRC mixtures, this empirical campaign is further illuminated through the strategic use of Partial Dependence Plots (PDPs), revealing intricate relationships between input parameters and con-sequent compressive strength. A pivotal revelation of this research lies in the identification of optimal SFRC formulations, offering tangible insights for real-world applications. The developed ML model stands out not only for its sophistication but also its tangible accuracy, evidenced by exemplary performance against inde-pendent datasets, boasting a commendable mean target-prediction ratio of 99%. To bridge the theory-practice gap, we introduce a user-friendly digital interface, thri-ughly designed to guide professionals in optimizing and accurately predicting the compressive strength of SFRC. This research thus contributes to the construction and civil engineering sectors by enhancing predictive capabilities and refining mix designs, fostering innovation, and addressing the evolving needs of the industry.

Time-series analysis is a widely used technique across various fields and industries, as it helps in understanding, predicting, and forecasting the behavior of data points over time. These fields include but are not limited to finance, economics, healthcare, transportation, etc. In the case of this paper, we have focused on finance. Predicting future values of financial time series offers several benefits. Accurate forecasts can help investors make better decisions about their investments. To predict future values, deep learning algorithms are commonly used since it is an effective method with complex data. In this study, we conduct a study that investigates the use of different data pre-processing techniques on deep learning algorithms in predicting the time series values. To conduct this experimental study, we utilize an open source software, which using long short-term memory technique as the representative deep learning technique, published in github software code repository platform. With this study, we investigate the effects of autoencoder and discrete wavelet transform data pre-processing techniques in time-series prediction. We discuss the details of the experimental study and report our results. The results show that time series prediction (using backtesting methodology) without any data pre-processing leads to 12.6% for mean absolute percentage error. The results also show that, time series prediction with the data preprocessing techniques (Wavelet Transform and Stacked Autoencoder) lead to 3.4%

Changes in sea level exhibit nonlinearity, nonstationarity, and multivariable characteristics, making traditional time series forecasting methods less effective in producing satisfactory results. To enhance the accuracy of the predictions of changes in sea level, this study introduced an improved VMD–EEMD–LSTM hybrid model. This model decomposes satellite altimetry data from near the Dutch coast using VMD, resulting in components of the Intrinsic Mode Function (IMF) with various frequencies and a residual sequence. EEMD further dissects the residual sequence obtained from VMD into second-order components. These IMFs decomposed by VMD and EEMD are utilized as features in the LSTM model for making predictions, culminating in the final forecasted results. The experimental results demonstrated significant improvements in the predictive performance compared with the VMD–LSTM model. The RMSE (root mean square error) decreased by an average of 58.68%, the MAE (mean absolute error) reduced by an average of 59.96%, and the R2 (coefficient of determination) increased by an average of 49.85% compared with the VMD–LSTM model. In comparison with the EEMD–LSTM model, the RMSE decreased by an average of 26.95%, the MAE decreased by an average of 28.00%, and the R2 increased by an average of 6.53%. The VMD–EEMD–LSTM model exhibited significantly improved predictive performance.

Accurate prediction of the degree of airport delays under the influence of convective weather is crucial for collaborative traffic management implementation and improving the efficiency of airport operations. However, existing studies usually only consider numerical-type quantitative features of weather-affected traffic in their models, and lack the introduction of spatial information to comprehensively portray the traffic operation scenarios under the influence of weather. In order to overcome this problem, this paper firstly designs a new image representation of weather-affected air traffic, and constructs a multi-channel traffic and weather scene image (MTWSI) by populating the airspace two-dimensional grid with traffic and meteorological information to represent the overall traffic operation situation in the terminal area under the influence of convective weather; then, a deep convolutional neural network-based airport delay prediction model ( ADLCNN), which takes MTWSI images as input and uses a specific CNN model to extract the deep features that affect traffic operation in it to input into the subsequent classification algorithm to predict the flight delay level; finally, a series of comparative experiments are carried out on the operational data of Guangzhou Baiyun Airport, and the experimental validation shows that, compared with the traditional machine learning methods, the proposed CNN-based airport delay prediction The experimental validation shows that the proposed CNN-based airport delay prediction model has satisfactory prediction performance compared with the traditional machine learning methods, which also proves that the proposed MTWSI method can more comprehensively respond to the real traffic conditions.

As the oil industry increasingly turns to unconventional low-permeability and low-porosity reservoirs, precise post-fracture production prediction is a pivotal instrument in investment de-cision-making, formulation of energy policies, and promotion of environmental assessments. Nevertheless, despite extensive research spanning decades, the precise post-fracture production prediction based on logging parameters remains an intricate task. In this study, we gathered ex-tensive logging data and segmented the post-frac gas production during well testing on the first day to enrich the dataset. Nine pipelines were then architected using various techniques of data preprocessing, feature extraction, and advanced machine learning models. Hyperparameter op-timization was executed via the GridsearchCV. To assess the efficacy of diverse models, metrics including the coefficient of determination (R2), standard deviation (SD), and root mean square error (RMSE) were invoked. Among the several pipelines explored, the PS-NN exhibited excellent predictive capability in specific reservoir contexts (an R2 value of 0.94 and an RMSE of 48.15). In essence, integrating machine learning with logging parameters effectively assesses reservoir productivity at multi-meter formation scales. This strategy not only mitigates uncertainties en-demic to reservoir exploration but also equips petroleum engineers with monitoring on reservoir dynamics, thereby facilitating reservoir development. Additionally, this approach provides res-ervoir engineers with an efficient way of reservoir performance oversight.

In this study, we conducted experiments to assess the forecasting capabilities for the tropical cyclone (TC) genesis over the South China Sea using the ensemble-based data assimilation system (EPS-DA) by WRF-LETKF. These experiments covered forecast lead times of up to 5 days and spanned a period from 2012 to 2019, involving a total of 45 TC formation events. The evaluation involved forecast probability assessments and positional and timing error analysis. Results indicated that successful forecasting depends on lead time and initial condition quality. For TC formation from an embryo vortex to tropical depression intensity, the EPS-DA system demonstrated improved accuracy as the forecast cycle approached the actual formation time. TC centers converged toward observed locations, highlighting the potential of assimilation up to 5 days before formation. We examined statistical variations in dynamic and thermodynamic variables relevant to TC processes, offering an objective system assessment. Our study emphasized early warnings of TC development appear linked to formation-time environmental conditions, particularly strong vorticity and enhanced moisture processes.

Hepatitis C presents a significant global health challenge, necessitating early diagnosis and precise severity classification for timely medical intervention. This study explores the application of machine learning techniques to predict the severity of hepatitis C, leveraging an extensive dataset. Our approach encompasses rigorous data preprocessing, advanced model development, and fine-tuned hyperparameter optimization to ensure accurate and reliable predictions. We evaluated four classification models: Logistic Regression, Random Forest, Gradient Boosting, and Support Vector Machine (SVM), comparing their accuracy in classifying patients. The results showed that the Random Forest and Gradient Boosting models outperformed the others with an accuracy of approximately 93.50%, demonstrating their potential in assisting Hepatitis C diagnosis. Further model enhancements through hyperparameter tuning and feature engineering can improve the precision of Hepatitis C diagnosis, contributing to better patient care.

For a fiber optic gyroscope, thermal deformation of the fiber coil can introduce additional ther-mal-induced phase errors, commonly referred to as thermal errors. Thermal error compensation techniques are effective means of addressing this issue. The principle behind these techniques involves real-time sensing of thermal errors and correcting them within the output signal. Since it is challenging to directly separate thermal errors from the output signal of the fiber optic gyro-scope, it is necessary to predict thermal errors based on temperature. To establish a mathematical model between temperature and thermal errors, this paper measured synchronized data of phase errors and angular velocity for the fiber coil under different temperature conditions and aimed to model it using data-driven methods. Due to the difficulty of conducting tests and the limited number of data samples, an algorithm called TD-model modeling is proposed to address the issue of overfitting, which can reduce the model's generalization ability. First, a theoretical analysis of the phase errors caused by thermal deformation of the fiber coil is performed. Subsequently, the critical parameters, such as the thermal expansion coefficient, are determined, and a theoretical model is established. Finally, the theoretical analysis model is incorporated as a regularization term and combined with the test data to jointly participate in the regression of model coefficients. Through experimental comparative analysis, it is shown that, relative to ordinary regression models, the TD-model effectively mitigates overfitting caused by the limited number of samples, leading to a 58% improvement in predictive accuracy.

1. Background: Cardiovascular diseases (CVDs) are India’s leading cause of mortality. This study aimed to recalibrate the original Framingham Risk Score (FRS) equations among adults in Kerala state. 2. Methods: Baseline survey data from the Kerala Diabetes Prevention Program were analyzed: 921 males and 567 females for lipid-based FRS scores and 1042 males and 646 females for BMI-based FRS scores. Recalibration of the original FRS scores was performed using local data on CVD risk factors and CVD mortality. 3. Results: Among males, the median 10-year CVD risk with the recalibrated lipid-based FRS score was 7.34 (IQR 4.33-12.42), compared with the original score of 8.88 (5.23-14.87) (p<0.001). For BMI-based FRS scores, the median 10-year CVD risk was 7.40 (4.27-11.83) with the recalibrated score, compared to 9.32 (5.40-14.80) for the original score (p<0.001). In females, the median 10-year CVD risk was 4.83 (2.90-8.36) with the recalibrated score, compared to 2.85 (IQR 1.71-4.98) with the original score (p<0.001). Similarly, the median 10-year CVD risk was 4.66 (2.74-8.81) with the recalibrated BMI-based FRS score, compared to 2.95 (1.72-5.61) with the original score (p<0.001). 4. Conclusions: Recalibrated FRS scores estimated a significantly lower 10-year CVD risk in males and a higher risk in females than the original FRS scores.

In this study, a design of Morlet wavelet neural networks (MWNNs) is presented to solve the prediction differential model (PDM) using the global approximation capability of genetic algorithm (GA) and local quick interior-point algorithm scheme (IPAS), i.e., MWNN-GAIPAS. The famous PDM is known as a variant of functional differential system that works as an opposite of the historical delay differential models. A fitness function is optimized using the mean square error by applying the GA-IPAS for solving the PDM. Three PDM examples have been presented numerically to check the authenticity of the MWNN-GAIPAS. For the perfection of the designed MWNN-GAIPAS, the comparability of the obtained results and exact results is performed. Moreover, the neuron analysis is performed by taking the 3, 10 and 20 number of neurons. The statistical observations have been performed to authenticate the reliability of the MWNN-GAIPAS for solving the PDM.

Background: Patients with chronic obstructive pulmonary disease (COPD) often suffer from acute exacerbations. Our objective was to describe recurrent exacerbations in a GP based Swiss COPD cohort, and develop a statistical model for predicting exacerbation. Methods: In a questionnaire-based COPD cohort, demographic and medical data were recorded for 24 months. Data set was split into training (75%) and validation (25%) datasets. A negative binomial regression model was developed using the training dataset to predict the exacerbation rate within 1 year. An exacerbation prediction model was developed, and the overall performance was validated. A nomogram was created to facilitate the clinical use of the model. Results: Of the 229 COPD patients analyzed, 77% of patients had no exacerbation during the follow-up. The best subset in the training dataset found that lower forced expiratory volume, high scores on the MRC dyspnoea scale, exacerbation history, being on combination therapy of LABA+ICS or LAMA+LABA at baseline were associated with a higher rate of exacerbation. When validated, the area-under-curve (AUC) was 0.75 for one or more exacerbations. Calibration was accurate (predicted 0.34 exacerbations vs observed 0.28 exacerbations). Conclusion: Nomograms built from these models can assist clinicians in the decision-making process of their COPD care.

Living organisms are active open systems far from thermodynamic equilibrium. The ability to behave actively corresponds to dynamical metastability: minor but supercritical internal or external effects may trigger major substantial actions such as gross mechanical motion, dissipating internally accumulated energy reserves. Gaining selective advantage from beneficial use of activity requires a consistent combination of sensual perception, memorised experience, statistical or causal prediction models, and resulting favourable decisions on actions. This information processing chain originated from mere physical interaction processes prior to life, here denoted as structural information exchange. From there, the self-organised transition to symbolic information processing marks the beginning of life, evolving by novel purposivity of trial-and-error feedback and accumulation of symbolic information. The emergence of symbols and prediction models can be described as a ritualisation transition, a symmetry-breaking kinetic phase transition of the 2^nd kind previously known from behavioural biology. The related new symmetry is the neutrally stable arbitrariness, conventionality or code invariance of symbols with respect to their meaning. The meaning of such symbols is given by the structural effect they ultimately unleash, directly or indirectly, by deciding on which actions to take. The early genetic code represents the first symbols. The genetically inherited symbolic information is the first prediction model for activities sufficient for survival under the condition of environmental continuity, sometimes understood as a “final causality” property of the model.

Cotton leaf curl Kokhran virus (CLCuKoV) (genus, Begomovirus; family, Geminiviridae) is highly infectious, widespread and the most dangerous pathogen of cotton (Gossypium hirsutum L.) that is responsible to a serious disorder, cotton leaf curl disease (CLCuD). Begomoviruses are spread very efficiently by the whitefly Bemisia tabaci cryptic species, causing economic losses to cotton crop, all over the world. The ‘Lucknow’ strain of CLCuKoV has emerged as a divergent isolate that could cause CLCuD. The monopartite ssDNA genome of CLCuKoV-Lu (2.7 Kb) contains six open reading frames (ORFs) that was shown to encode four major proteins. RNA interference (RNAi)-based antiviral innate immunity is a sequence-specific biological phenomenon and a powerful tool to control plant viruses. The present study aims to determine cotton locus-derived microRNAs (ghr-miRNAs) that are identified for targeting the CLCuKoV-Lu ss-DNA-encoded mRNAs using a predictive approach that involves four computational algorithms, miRanda, RNA22, psRNATarget and RNAhybrid. Mature ghr-miRNA sequences (n=80) from allotetraploid upland cotton (2n = 4x = 52) were selected from the miRBase and were tested for alignment with the CLCuKoV-Lu genome. Among the 80 cotton locus-derived ghr-miRNAs evaluated, only one consensus cotton locus-derived ghr-miRNA (ghr-miR2950) was concluded to have effective ghr-miRNA target site at common nucleotide position 82 in the CLCuKoV-Lu genome respectively, using a stringent criterion, identified by all the algorithms used. The miRNA targeting is reliant on base pairing of miRNA-mRNA target pairings. Conservation of the hybridization binding site of the predicted ghr-miR2950 was validated using multiple sequence alignment within all the strains of CLCuKoV. We constructed a regulatory interaction network of miRNA–mRNA to identify novel targets. The efficacy of the predicted miRNAs against CLCuKoV-Lu was evaluated by RNAi-mediated targeted mRNA cleavage. The current investigated miRNA targets provide evidence for the development of CLCuD-resistant cotton plants.

Entangled metallic wire material (EMWM) can be utilized as a novel elastic element in vibration isolation devices for mechanical actuators. This paper presents a vibration experiment aimed at investigating the degradation behavior of mechanical performance in EMWM under cyclic compressive environment. An electric vibration testing system, coupled with an isolation structure, is employed to apply compressive loads to the EMWM specimens. Through visual observations and quasi-static compression tests, the variations in geometric morphology and mechanical properties are studied, considering different relative densities and stress amplitudes. The results incidate a significant reduction in the compressed dimension of the specimens as the number of cycles increases, without any wire fractures or wear. Moreover, the mechanical properties exhibit an increasing secant modulus and a decreasing loss factor. These variations ultimately lead to a gradual deviation of the vibration characteristics of the isolation structure from its design state. To predict the mechanical property degradation of EMWM, prediction models are proposed, incorporating dimension, modulus and damping by fitting the obtained results. This research provides valuable experimental data and presents an effective method to determine the operational lifetime of vibration isolators utilizing EMWM.

The precipitation, flocculation, and deposition of asphaltene cause severe formation damage within a reservoir and shorten a well’s productive life. Pressure depletion is one factor that contributes to asphaltene precipitation during production; therefore, the first step in managing asphaltene is to determine the onset pressure of the precipitation. While there are numerous equation of state models that can be used to predict the onset pressure, these models are complex and heavily reliant on tuning parameters. Using multivariate linear regression, this work attempts to develop a simple and accurate thermodynamic model for predicting the upper precipitation onset pressure under pressure depletion above the bubble point pressure (Pb) at various temperatures. A total of 94 experimental data points from 37 published crude oil data sets were compiled from the literature. To develop the model, 59 experimental data points were used as training data and 35 experimental data points as testing data. According to the results of the multicollinearity test, the bubble point pressure, temperature, resins, and saturate-to-aromatic ratio were chosen as predictors. The upper onset pressure data with comparable trends were clustered, and unsupervised recognition of three distinct cluster groups was performed. For each cluster identified, a multivariate linear regression model was developed. The model was chosen based on Mallow’s coefficient of determination (Cp), adjusted R² (statistical measure of fit), and S (standard error of the regression slope). The developed model was tested using a data set, and the results showed an adjusted R² of 96.25%, with a mean absolute error of 4.1%. The model was randomly applied to 15 data points to compare it to perturbed-chain statistical associated fluid theory (PC SAFT) and the Peng-Robinson equation of state models and to the multivariate regression models of Fahim (2007) and Ameli et al. (2016). The results showed that the mean absolute error for predicting the asphaltene precipitation onset pressure was 2.82% using Peng-Robinson, 2.36% using the PC SAFT equation of state, 23.96% using the Fahim model, 24.80% using the model reported by Ameli et al., and 2.39% using the newly developed multivariate regression model. The developed multivariate model appears to be as accurate as the PC SAFT equation of state modeling with tuning parameters. The primary advantage of multivariate regression is that, unlike the PC SAFT equation of state model, it does not require saturates, aromatics, resins, and asphaltenes (SARA)-based characterization methodologies or rigorous parameter tuning. It is simple to use, quick, and it produces results in a short period of time.

The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.

Accurate forecast of tail water level (TWL) is of great importance for the safe and economic operation and management of hydropower stations. The predictive performance is significantly influenced by the backwater effect of downstream hydropower stations and tributaries, but the explicit quantification method of the backwater effect is lacked. In this study, a deep learning model based forecasting framework for TWL predictions is established and applied to forecast TWL of Xiangjiaba (XJB) hydropower stations, which is influenced by the backwater effect of downstream tributaries including Hengjiang River (HJR) and Minjiang River (MJR). Firstly, the lag time of the backwater effect of HJR and MJR is analyzed based on the permutation importance. The results demonstrate that the lag time of backwater effect on the TWL of XJB is 5-7 hours for the HJR and 1-2 hours for the MJR. Then, the runoff thresholds of the HJR and MJR for impacting the TWL of the XJB station are obtained by scenario comparison, and the results show that the thresholds of HJR and MJR are 700 m3/s and 7000 m3/s respectively. Finally, the deep learning methods based TWL forecasting model is established based on the lag time and threshold analysis. The model is used to forecast the TWL in future 48 hours. The results show that the forecasting model has a good predictive performance with 98.22% of absolute errors less than 20 cm. The mean absolute error over the validation dataset is 5.27 cm and the maximum absolute error is 63.35 cm.

The escalation of climate change and the increasing frequency of extreme weather events have amplified the importance of precise and timely lightning prediction. This predictive capability is pivotal for the preservation of life, protection of property, and maintenance of crucial infrastructure safety. Recently, the rapid advancement and successful application of data-driven deep learning across diverse sectors, particularly in computer vision and spatio-temporal data analysis, have opened up innovative avenues for enhancing both the accuracy and efficiency of lightning prediction. This article presents a comprehensive review of the broad spectrum of existing lightning prediction methodologies. Starting from traditional numerical forecasting techniques, we traverse the path to the most recent breakthroughs in deep learning research. We encapsulate these diverse methods, shedding light on their progression and summarizing their capabilities, while also predicting their future development trajectories. This exploration is designed to enhance our understanding of these methodologies, allowing us to better utilize their strengths, navigate their limitations, and potentially integrate these techniques to create novel and powerful lightning prediction tools. Through such endeavors, our aim is to bolster our preparedness against the growing unpredictability of our climate and ensure a proactive stance towards lightning prediction.

The Cancer Genome Atlas (TCGA) has classified papillary thyroid carcinoma (PTC) into indolent RAS-like and aggressive BRAF-like based on its distinct driver gene mutations. This study aimed to assess clinicopathology and pERK1/2 expression variations between BRAF-like and RAS-like PTCs and establish predictive models for BRAFV600E and RAS-mutated PTCs. A total of 222 PTCs underwent immunohistochemistry staining to assess pERK1/2 expression and Sanger sequencing to analyze the BRAF and RAS genes. Multivariate logistic regression was employed to develop prediction model. Independent predictors for the BRAFV600E mutation include a nuclear score of 3, the absence of capsules, an aggressive histology variant, and pERK1/2 levels exceeding 10% (X2=0.128, P&gt;0.05, AUC=0.734, P&lt;0.001). RAS mutation predictive model includes follicular histology variant and pERK1/2 expression &gt;10% (X2=0.174, P&gt;0.05, AUC=0.8, P&lt;0.001). We proposed using the prediction model concurrently with four potential combination group outcomes. PTC cases included in combination of low BRAFV600E-scoring group and high RAS-scoring group are categorized as RAS-like (adjOR=4.857, P=0.01, 95% CI=1.470-16.049). PTCs included in combination of high BRAFV600E-scoring group and low RAS-scoring group are categorized as BRAF-like PTCs (adjOR=3.091, P=0.001, 95% CI=1.594-5.995). The different prediction models indicate variations in biological behaviour between BRAF-like and RAS-like PTCs, necessitating adjustments in treatment approaches.

The assessment and prediction of drought risk under future climate change and land use land cover (LULC) scenarios is critically important for drought prevention and mitigation, as it enables a clearer understanding of potential shifts in drought patterns. The primary aim of this study is to evaluate sub-seasonal and seasonal meteorological and hydrological drought hazards across the Yellow River Basin (YRB) under projected future climate conditions and LULC patterns. The BCC-CSM1-1 climate model projections from the NASA Earth Exchange Global Daily Downscaled Projections (NEX-GDDP) dataset are utilized to represent future climate for 2025-2060 under RCP 4.5 and 8.5 scenarios. The CA-Markov model is employed to predict future LULC distributions. Meteorological and hydrological drought risks across different YRB zones are evaluated through a copula-based risk assessment approach, based on the joint probability distribution of drought duration and severity. The results indicate that sub-seasonal meteorological and hydrological droughts will likely be the primary concern moving forward. Specifically, the upper YRB (zones A, B, C) exhibits greater vulnerability to sub-seasonal meteorological drought, while the Loess Plateau (zones C, E) shows higher susceptibility to sub-seasonal hydrological drought. Moreover, zone F in the downstream region may experience increased seasonal hydrological drought risk due to projected urban expansion in the middle and lower portions of the YRB.

Background: Novel technologies like continuous glucose monitor (CGM) systems are improving diabetes management by means of real-time sensor glucose levels, retrospective course of glucose and trend arrows. Continuous Glucose Monitoring (CGM) offers real-time alerts for (prognostic) hypo- and hyperglycemia, fast dropping or increasing glucose, and hence improving glycaemia under unstable conditions like during meals, physical activity and exercise management. Complex CGM systems challenge people with diabetes and health care professionals in interpreting rapid changes, sensor delay (~10-minute difference between interstitial and plasma glucose), and malfunctions. Enhanced prediction models are necessary for optimal insulin dosing, daily activities, and especially for future fully closed-loop systems. Methods: The aim of this study was to investigate the efficacy of three different predictive models for glucose responses: 1) an autoregressive integrated moving average model (ARIMA), 2) logistic regression, 3)and long short-term memory networks (LSTM), in predicting glucose levels after 15 minutes and one hour. We compared and evaluated the performance of these models in predicting hypoglycemia (<70 mg/dL), euglycemia (70-180 mg/dL), and hyperglycemia (>180 mg/dL). In more detail, by assessing metrics such as precision, recall, F1-score, and accuracy, we specifically assessed which model provided the most accurate and reliable predictions for glucose levels Results: As expected, ARIMA showed the worst accuracy especially predicting hypoglycaemia withing 1-hour (7.3%). The accuracy of the logistic regression model, predicting hypoglycemia during the first 15 min was higher (98%), comparing to LSTM (88%). However, the LSTM model (87%) exceeded the accuracy of hypoglycemia prediction of the logistic regression (83%) during an hour prognosis. The same pattern observed in hyperglycemia - ARIMA model (60%, 1 hour), logistic regression (96%, 15 minutes) and LSTM (85%, 1 hour) Conclusions: These findings suggest that different models may have varying strengths and weaknesses in predicting glucose levels, and the choice of model should be carefully considered based on the specific requirements and context of the clinical application. The logistic regression model was more accurate for the next 15 minutes, especially predicting hypoglycemia. However, the LSTM model exceeded logistic regression for the next one hour prediction. Future research could explore hybrid models or ensemble approaches that combine the strengths of multiple models to further improve the accuracy and reliability of glucose predictions.

In a super-aged society, maintaining healthy aging, preventing death, and enabling a continua-tion of economic activities are crucial. This study sought to develop a model for predicting the survival time in community-dwelling older individuals by using a deep learning method, and to identify the level of influence of various risk factors on the survival period, so that older in-dividuals can manage their own health. This study used the Korean National Health Insurance Service claims data. We observed community-dwelling older people, aged 66 years, for 11 years and developed a survival time prediction model. Of the 189,697 individuals enrolled at baseline, 180,235 (95.0%) survived from 2009 to 2019, while 9,462 (5.0%) died. Using deep learning based models (C statistics = 0.7011), we identified Charlson’s comorbidity index; the frailty index; long-term care benefit grade; disability grade; income level; a combination of diabetes mellitus, hypertension, and dyslipidemia; sex; smoking status; and alcohol consumption habit as factors impacting survival. In particular, Charlson’s comorbidity index (SHAP value: 0.0445) and frailty index (SHAP value: 0.0443) were strong predictors of survival time. Older individuals should rec-ognize modifiable risk factors that affect survival period in order to manage their own health.

Global climate change, dominated by climate warming, is seriously affecting the balance of global ecosystems, but the risk of species extinction is particularly high in low-altitude mountain areas. To clarify the response of the endemic and critically endangered species Ilex nanchuanensis to climate change, this study used the MaxEnt model to simulate and predict the potential habitat of I. nanchuanensis during the Last Interglacial, Last Glacial Maximum, the current period, and two future periods (the 2050s and 2070s). The results showed that the hottest monthly minimum temperature is the most important climatic factor affecting the geographical distribution of I. nanchuanensis. Furthermore, I. nanchuanensis will be at risk of population shrinkage and extinction in the future, with the center of mass moving further northwest as concentrations of greenhouse gases increase, especially in the 2070s, when its geographical distribution shrinks the most under the RCP6 scenario. Global warming is causing habitat degradation for many species and will continue to migrate to higher altitudes and latitudes in the future, seriously affecting the global ecosystem balance. Therefore, to actively respond to the impacts of climate change, protected areas should be established around the geographical distribution centers of species, and core, buffer, and experimental areas should be scientifically and rationally delineated for the conservation and cultivation of germplasm resources.

This paper explores the use of different deep learning models for predicting precipitation in 56 meteorological stations in Jilin Province, China. The models used include Stacked-LSTM, Transformer, and SVR, and Gaussian noise is added to the data to improve their robustness. Results show that the Stacked-LSTM model performs the best, achieving high prediction accuracy and stability. The study also conducts variable attribution analysis using LightGBM and finds that temperature, dew point, precipitation in previous days, and air pressure are the most important factors affecting precipitation prediction, which is consistent with traditional meteorological theory. The paper provides detailed information on the data processing, model training, and parameter settings, which can serve as a reference for future precipitation prediction tasks. The findings suggest that adding Gaussian noise to the dataset can improve the model's generalization ability, especially for predicting days with zero precipitation. Overall, this study provides useful insights into the application of deep learning models in precipitation prediction and can contribute to the development of meteorological forecasting and applications.

With the rise of the Internet of Things (IOT), mobile devices and Location-Based Social Network (LBSN), an abundant amount of trajectory data has made research on location prediction more popular. The check-in data shared through LBSN hides information related to life patterns, obtaining this information is helpful for location prediction. However, the trajectory data recorded by mobile devices is different from check-in data that has semantic information. In order to obtain the user’s semantic, relevant studies match the stay point to the nearest Point of Interest (POI), but location error may lead to wrong semantic matching. Therefore, we propose A Self-Attention for Next Location Prediction based on Semantic Mining to predict the next location. When calculating the semantic feature of a stay point, the first step is to search for the k nearest POI, then use the reciprocal of the distance from the stay point to the k nearest POI and the number of categories as weights. Finally, we use the probability to express semantic without losing other important semantic information. Furthermore, this research combined with sequential pattern mining can bring richer semantic features. In order to better perceive the trajectory, temporal features learn periodicity of time series by sine function. In terms of location features, we build a directed weighted graph and regard the frequency of users visiting locations as the weight, so the location features are rich in contextual information. We then adopt the Self-Attention model to capture long-term dependencies in long trajectory sequences. Experiments in Geolife show that the semantic matching of this study improved by 45.78% in TOP@1 compared with the closest distance search for POI. Compared with the baseline, the model proposed in this study improved by 2.5% in TOP@1.

Paving blocks are concrete pieces placed in exposed places to the weather, which are sub-jected to loads and wear. Hence, quality control in the manufacture of paving blocks is es-sential to guarantee the properties and durability of the product in construction projects. In Ecuador, the requirements are described in the Ecuadorian technical standard "NTE INEN 3040", and tensile splitting strength is a fundamental requirement to guarantee product quality. It is analyzed using quality control measurements such as dimensions, the weight of the fresh paving block in the vibro-compacted process, and the percentage of water absorption in order to know how the variables influence and manage to predict the tensile splitting strength to avoid product non-conformity in advance, having a timely and better control of the manufacturing process. The data was obtained from a company that can produce 30 000 units per day of rectangular paving blocks with 6 cm thickness. Mul-tivariate models such as multiple linear regression, regression trees, random forests and neural networks are performed to predict the tensile splitting strength variable through two groups of predictors; the first group is the thickness mm, width mm, length mm, mass of fresh paving block g and percentage of water absorption %. The second group of pre-dictor variables is the density of the fresh paving block kg/m3 and the percentage of water absorption %. It is concluded that the multiple linear regression method performs better in predicting the first group of predictor variables with a mean square error (MSE) of 0.110086, followed by the neural network without hidden layers resulting in an MSE of 0.112198. The best method for the second set of predictors was the neural network with-out hidden layers with a mean square error ( MSE ) of 0.112402, closely followed by the multiple linear regression model with an MSE of 0.115044.

This article presents a comprehensive study on enhancing grid resilience through advanced forecasting and optimization techniques in the context of power outages. Power outages pose significant challenges to modern societies, affecting various sectors such as industries, households, and critical infrastructures. The research combines statistical analysis, machine learning algorithms, and optimization methods to address this issue to develop a holistic approach for predicting and mitigating power outage events. The proposed methodology involves the use of Monte Carlo simulations in MATLAB for future outage prediction, Long Short-Term Memory (LSTM) networks for forecasting solar irradiance and load profiles, and a hybrid LSTM-Particle Swarm Optimization (PSO) model to improve accuracy. Furthermore, the role of Battery State of Charge (SoC) in enhancing system resilience is explored. The study also assesses the techno-economic advantages of a grid-tied microgrid integrated with solar panels and batteries over conventional grid systems. The results highlight the potential of the proposed approach in strengthening grid resilience, reducing downtime, and fostering sustainable energy utilization.

In South Korea, the residential real estate market is influenced not just by traditional supply and demand dynamics, but also by external factors such as housing policies and macroeconomic conditions. Given the significant role of housing assets in individual wealth, market fluctuations can have profound implications. While prior research has utilized variables like GDP growth rate, patent issuance, and birth rates, and employed models like LSTM and ARIMA for housing price predictions, many overlook key localized factors. Notably, the impact of subway stations and living SOC facilities on housing prices, especially in metropolitan areas, remains underexplored. This study addresses these gaps by analyzing usage trends across subway stations, assessing the influence of living SOC facilities on housing values, and identifying the optimal machine learning model for price predictions near transport hubs. Through a comparative analysis of machine learning techniques, we aim to provide insights for more informed housing price determinations, promoting a more stable real estate market.

This paper investigates the roll parameter estimation of periodic disturbances where the amplitude, frequency, offset, and phase are hardly recognized in real practice. The key problem is to make an estimation that could eliminate the unknown disturbance parameters. An adaptive mechanism applies these four parameters to the globally exponential convergence using linear second-order filters and parameter estimation errors. Then, a backstepping controller is employed to make an exponential convergence to zero of the state variables. Moreover, reservoir computing is used to forecast chaotic roll motions to support predictability using Lyapunov exponents and the Poincaré map. Numerical simulations are demonstrated to validate the dynamical behaviors and efficacy of the proposed control scheme with machine learning.

Taste determination in small molecules is critical in food chemistry, but traditional experimental methods can be time-consuming. Consequently, computational techniques have emerged as val-uable tools for this task. In this study, we explore taste prediction using various molecular feature representations and assess the performance of different machine learning algorithms on a dataset comprising 2,601 molecules. The results reveal that GNN-based models outperform other ap-proaches in taste prediction. Moreover, consensus models that combine diverse molecular repre-sentations demonstrate improved performance. Among these, molecular fingerprints + GNN con-sensus model emerges as the top performer, highlighting the complementary strengths of GNNs and molecular fingerprints. These findings have significant implications for food chemistry research and related fields. By leveraging these computational approaches, taste prediction can be expedited, leading to advancements in understanding the relationship between molecular structure and taste perception in various food components and related compounds.

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it becomes crucial to identify ion-binding sites. Accurate identification of protein-ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46% respectively in F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools producing prediction results for a hundred sequences for a specific ion in under ten minutes.

AlphaFold is a groundbreaking Deep Learning tool for protein structure prediction. It achieved remarkable accuracy in modeling the many 3D structures while taking as the input only the known amino acid sequence of proteins in question. Intriguingly though, in the early steps of each individual structure prediction procedure, AlphaFold is not respecting topological barriers that in real proteins result from the reciprocals impermeability of polypeptide chains. This study aims to investigate how this non-respecting of topological barriers affects AlphaFold predictions with respect to the topology of protein chains. We focus on such classes of proteins that during their natural folding form reproducibly the same knot type on their linear polypeptide chain as revealed by their crystallographic analysis. We use partially artificial test constructs in which the mutual non-permeability of polypeptide chains should not permit the formation of such knots during natural protein folding. We find that despite the formal impossibility that the protein folding process could produce such knots, AlphaFold predicts these proteins to be knotted. Our study underscores the necessity for cautious interpretation and further validation of topological features in protein structures predicted by AlphaFold.

Generally, when cognitive radio users are in Underlay mode, through the analysis of the electromagnetic spectrum in time, frequency, space, and field of multiple dimensional data accounts for judging the inherent correlation of the radio spectrum used/idle state, this is the realization of cognitive radio users (secondary users, SUs) efficient access to the foundation of the limited spectrum resources. Therefore, how to efficiently use of spectrum status of each SU implementation of reception multidimensional combination forecasting is the core of this paper addressing the problem. In this paper, we propose a deep-learning hybrid model called TensorGCN-LSTM based on the tensor data structure. The model treats SUs deployed at different spatial locations under the same frequency and the spectrum status of SUs themselves under different frequencies in the task area as nodes and constructs two types of graph structures. Graph convolutional operations are used to sequentially extract corresponding spatial-domain and frequency-domain features from the two types of graph structures. Then, the long short-term memory (LSTM) model is used to fuse the spatial, frequency, and temporal features of the cognitive radio environment data. Finally, the prediction task of the spectrum distribution situation is accomplished through fully connected layers. Specifically, the model constructs a tensor graph based on the spatial similarity of SUs' locations and the frequency correlation between different frequency signals received by SUs, which describes the electromagnetic wave's dependency relationship in spatial and frequency domains. LSTM is used to capture the electromagnetic wave's dependency relationship in the temporal domain. To evaluate the effectiveness of the model, we conducted ablation experiments on LSTM, GCN, GC-LSTM, and TensorGCN-LSTM models using simulated data. The experimental results show that our model achieved better prediction performance in RMSE, and the correlation coefficient R2 of 0.8753 also confirmed the feasibility of the model.

The proton exchange membrane fuel cell (PEMFC) is a critical and essential component of zero-emission electro-hydrogen generators. An accurate prediction of its performance is important for optimal operation management and preventive maintenance of these generators. However, the prediction is not simple because the PEMFCs have complex electrochemical reactions with multiple nonlinear relations between operating variables as inputs and voltage as output. In this paper, we propose an efficient prediction approach based on XGBRegressor and Tree-structured Parzen Estimator. In addition, to better select relevant features, Kernel Principal Component Analysis and Mutual Information are jointly used. The proposed approach allows consideration of the dynamic operating conditions of the PEMFC. To test and validate the robustness of the proposed approach, a real data-set of ten PEMFCs was considered. Furthermore, a comparison study with traditional machine learning models, such as artificial neural networks and support vector machine regression, was investigated. The obtained results confirm that our model outperforms the considered traditionel machine learning models.

Knowledge graphs (KGs) play a crucial role in many applications, such as question answering, but incompleteness is an urgent issue for their broad application. Much research in knowledge graph completion (KGC) has been performed to resolve this issue. The methods of KGC can be classified into two major categories: rule-based reasoning and embedding-based reasoning. The former has high accuracy and good interpretability, but a major challenge is to obtain effective rules on large-scale KGs. The latter has good efficiency and scalability, but it relies heavily on data richness and cannot fully use domain knowledge in the form of logical rules. We propose a novel method that injects rules and learns representations iteratively to take full advantage of rules and embeddings. Specifically, we model the conclusions of rule groundings as 0-1 variables and use a rule confidence regularizer to remove the uncertainty of the conclusions. The proposed approach has the following advantages: 1) It combines the benefits of both rules and knowledge graph embeddings (KGEs) and achieves a good balance between efficiency and scalability. 2) It uses an iterative method to continuously improve KGEs and remove incorrect rule conclusions. Evaluations on two public datasets show that our method outperforms the current state-of-the-art methods, improving performance by 2.7% and 4.3% in mean reciprocal rank (MRR).

Transportation authorities aim to boost road safety by identifying risky locations and applying suitable safety measures. The Highway Safety Manual (HSM) is a vital resource for US transportation professionals, aiding in the creation of Safety Performance Functions (SPFs), which are predictive models for crashes. These models rely on Negative Binomial distribution-based regression and misinterpreting them due to unmet statistical assumptions can lead to erroneous conclusions, including inaccurately assessing crash rates or missing high-risk sites. The Florida Department of Transportation (FDOT) has introduced context classifications to HSM SPFs, complicating assumption violation identification. This study, part of an FDOT-sponsored project, investigates established statistical diagnostic tests to identify model violations and proposes a novel approach to determine optimal spatial regions for Empirical Bayes adjustment. This adjustment aligns HSM-SPFs with regression assumptions. The study employs a case study involving Florida roads. Results indicate that a 20-mile radius offers an optimal spatial sample size for modeling crashes of all injury levels, ensuring accurate assumptions. For severe injury crashes, which are less frequent and harder to predict, a 60-mile radius is suggested to fulfill statistical modeling assumptions. This methodology guides FDOT practitioners in assessing the conformity of HSM-SPFs with intended assumptions and determining appropriate region sizes.

Continuous glucose monitoring devices allow diabetes condition management. However, when limited data is available, one option is to increase their size by generating synthetic samples. From a homemade wearable prototype was created a real dataset with 18 instances and 53 attributes that capture characteristics of capillary and venous blood glucose, oxygen concentration, pulse rate, skin temperature, and 24 modules and 24 phases related to bio-impedance. The objective of this article is to generate synthetic datasets, and also it investigates the ideal features subset and optimal model for non-invasive diabetes prediction. Gaussian-Copulas (GC), conditional generative adversarial networks (CG), variational autoencoders, and Copula-GAN techniques' were used to generate five synthetic datasets. Experiments show that GC1 and GC2 datasets follow min/max boundaries and are not copies of the original data. Multilayer perceptron regressor outperformed (train and test) with 2.17, 2.51 in MAE; 9.29, 13.59 in MSE; 3.05, 3.69 in RMSE, and 0.95, 0.92 in R2 in GC1, and 2.64, 3.02 in MAE; 11.43, 15.11 in MSE; 3.38, 3.89 in RMSE, and 0.94, 0.92 in R2 in GC2 with eight features. Future work is necessary to explore autoencoder and generative architectures, datasets with diverse characteristics, and the effect of the number of features.

The problem of low soil fertility and limited research in agricultural data driven tools, may lead to low crop productivity which makes it imperative to research in applications of high throughput computational algorithms such as of machine learning (ML) for effective soil analysis and fertility status prediction in order to assist in optimal soil fertility management decision-making activities. However, difficulties in the choice of the key soil properties parameters for use in reliable soil nutrients analysis and fertility prediction. Also, individual ML algorithms setbacks and modelling expert implementation procedures subjectivity, may lead to exploitation of worst fertility level targets and soil fertility status targets classification models performance reported variations. This paper surveys state-of-affair in ML for agricultural soil nutrients analysis and fertility status prediction. Prominent soil properties and widely used classical modelling algorithms and procedures are identified. Empirically exploited fertility status target classes are scrutinized, and reported soil fertility prediction model performances are depicted. The three pass method, with mixed method of qualitative content analysis and qualitative simple descriptive statistics were used in this survey. Observably, the frequently used soil nutrients and chemical properties were organic carbon, phosphorus, potassium, and potential Hydrogen, followed by iron, manganese, copper and zinc. Predominant algorithms included Random Forest, and Naïve Bayes, followed by Support Vector Machine. Model performances varied, with highest accuracy 98.93% and 98.15% achieved by ensemble methods, and the least being 60%. Interdisciplinary ML related researchers may consider using ensemble methods to develop high performance soil fertility status prediction models.

. Identifying students who might have difficulty in their course of studies ahead of time is crucial. There can be many reasons for performance issues, such as personality, family, social, and/or economic. We advocate that educational systems should use machine learning to predict students’ performance based on performance factors. This would allow educational professionals and institutions to put in place a preventive plan to help students towards achievements of their educational goals and success. In this chapter, we propose a student performance prediction method and evaluate its performance. We provide a taxonomy of performance factors that help to gauge students performance from different perspectives and give insights on the categories and features that have more significant impact on students’ performance. The results of this work can be used by education institutions to put in place a student-centric approach to tackle performance issues before they create long-term effects on student’s life. In addition, it will help education policymakers to introduce a tailored approach for the population in specific areas.

Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been utilised to forecast the foreign exchange market (Forex). However, such models usually exhibit unstable behaviour, as data perturbations often downgrade the functionality of the entire network due to their monolithic architecture. Hence, this study proposes a novel neuroscience-informed modular network applied to the closing prices and the sentiments retrieved from Yahoo Finance and Twitter APIs, aiming to anticipate better price fluctuations in Euro to British Pound Sterling (EUR/GBP) rather than monolithic methods. The proposed model is based on a new modular CNN, replacing pooling layers with orthogonal kernel initialisation RNNs coupled with Monte Carlo Dropout (MCD), namely MCoRNNMCD. It combines two modules: i) a convolutional simple RNN and ii) a convolutional Gated Recurrent Unit (GRU), where orthogonality and MCD are added to reduce the overfitting, assessing each module's uncertainty. These parallel feature extraction modules concatenate their outputs to a final three-layer Artificial Neural Network (ANN) decision-making module. A comprehensive comparison viewing objective evaluation metrics such as the Mean Square Error (MSE) proved that the proposed MCoRNNMCD-ANN outperformed single CNN, LSTM, GRU, and the state-of-the-art hybrid BiCuDNNLSTM, CLSTM, CNN-LSTM, and LSTM-GRU in forecasting hourly EUR/GBP closing price fluctuations.

Recently, NOAA has included GNSS (Global Navigation Satellite System) Radio Occultation (RO) data as one of the crucial long-term observables for weather and climate applications. To include more GNSS RO data in the numerical weather prediction system, the NOAA Commercial Weather Data Pilot program (CWDP) started to explore the commercial RO data available on the market. After two rounds of pilot studies, the CDWP decided to award the first Indefinite Delivery Indefinite Quantity (IDIQ) contract to GeoOptics and Spire Incs. in 2020. This study examines the quality of Spire data products for weather and climate applications. Spire RO data are collected from commercial CubeSats through careful comparison with the data from Formosa Satellite Mission 7–Constellation Observing System for Meteorology, Ionosphere, and Climate-2 (COSMIC-2), ERA-5, and high-quality radiosonde data. The results demonstrated that although with lower Signal-Noise-Ratio (SNR) in general, the pattern of the lowest penetration height for Spire is similar to those for COSMIC-2. The Spire and COSMIC-2 penetrate heights are between 0.6 and 0.8 km altitude at the tropical oceans. Although using different GNSS RO receivers, the precision of Spire STRASP receivers is of the same quality as those of COSMIC-2 Global Positioning System - GPS, GALILEO, and GLObal NAvigation Satellite System – GLONASS (TGRS) receivers. The retrieval accuracy from Spire is very compatible with those from COSMIC-2. We validated Spire temperature and water vapor profiles by comparing them with collocated radiosonde data. Generally, over the height region between 8 km and 16.5 km, the Spire temperature profiles match those from RS41 RAOB very well with temperature biases &lt; 0.02 K. Over the height range from 17.8 to 26.4 km, the temperature differences are ~-0.034 K with RS41 RAOB being warmer. We also estimated the error covariance matrix for Spire, COSMIC-2, and KOMPSAT-5. Results showed that the COSMIC-2 estimated error covariance values are slightly more significant over the oceans at the mid-latitudes (45oN-30oN and 30oS-45oS), which may also be owing to COSMIC-2 SNR being lower at those latitudinal zones.

Breast cancer is the most common malignancy in women worldwide. The pathogenesis of this disease is closely related to the estrogen receptor alpha subtype (ERα). Therefore, it is of great importance to develop effective inhibitors of ERα activity for the treatment of breast cancer. In this paper, we propose a novel ensemble machine learning model for quantitative structure-activity relationship of anti-breast cancer drugs, which can effectively predict drug activity in small samples with multiple characteristic variables. To avoid the problem of over-fitting caused by low-correlation independent variables, the scoring mechanism of random forest was improved by incorporating three relevance indicators, including the maximum mutual information number, Pearson correlation coefficient and distance correlation coefficient, and 20 optimal molecular descriptors were selected. The Bayesian hyperparameter optimization method was used to optimize the parameters of multiple linear regression (MLR), support vector regression (SVR), and extreme gradient boosting (XGBoost), respectively. The AdaBoost strong learner was constructed by combining the weak learner with the weighted linear addition method. The results show that the proposed ensemble learning model has the best prediction performance compared to the three basic learner models and the CNN-LSTM combination prediction model. The root mean square error was reduced by 7.60%-26.51%. The mean relative error was reduced by 6.46%-30.92%. Goodness of fit increased by 9.57%-36.94%. Finally, the biological activities of 50 candidate compounds for ERα inhibitors were predicted, and it was found that 4-[2-benzyl-1-[4-(2-pyrrolidin-1-ylethoxy)phenyl]but-1-enyl]phenol had an excellent biological activity value pIC50, which had the potential to be an ERα inhibitor. The model proposed in this paper has good prediction accuracy, which can provide an effective reference for the discovery and development of anti-breast cancer drugs.

Urban rail transit offers advantages like high safety, energy efficiency, and environmental friendliness. With cities rapidly expanding, travelers are increasingly using rail systems, heightening demands for passenger capacity and efficiency while also pressuring these networks. Passenger flow forecasting is an essential part of transportation systems. Short-term passenger flow forecasting for rail transit can estimate future station volumes, providing valuable data to guide operations management and mitigate congestion. This paper investigates short-term forecasting for Suzhou's Shantang Street station. Shantang Street's high commercial presence and distinct weekday versus weekend ridership patterns make it an interesting test case. Wavelet denoising and LSTM modeling were combined to predict short-term flows, comparing the results to standalone LSTM and SVR approaches. This study illustrates that the adopted algorithms exhibit good performance for passenger prediction. The LSTM model with wavelet denoising proved most accurate, demonstrating applicability for short-term rail transit forecasting and practical significance.

Tripping is the largest cause of falls and low swing foot ground clearance during the mid-swing phase, particularly at the critical gait event known as Minimum Foot Clearance (MFC) is the major risk factor for tripping-related falls. Intervention strategies to increase MFC height can be effective if applied in real-time based on feed-forward prediction. The current study investigated the capability of machine learning models to classify the MFC into various categories using toe-off kinematics data. Specifically, three MFC sub-categories (less than 1.5cm, between 1.5-2.0cm and higher than 2.0cm) were predicted applying machine learning approaches. A total of 18,490 swing phase gait cycles’ data were extracted from six healthy young adults, each walking for 5-minutes at a constant speed of 4km/h on a motorised treadmill. Both K-Nearest Neighbour (KNN) and Random-Forest were utilised for prediction based on the data from toe-off for five consecutive frames (0.025s duration). Foot kinematics data were obtained from inertial measurement unit attached to the mid-foot, recording tri-axial linear accelerations and angular velocities of the local coordinate. KNN and Random-Forest achieved 84% and 86% accuracy, respectively, in classifying MFC into the three sub-categories with run time of 0.39 seconds and 13.98 seconds respectively. The KNN-based model was found to be more effective if incorporated into an active exoskeleton as the intelligent system to control MFC based on the preceding gait event, toe-off due to its quicker computation time. The machine learning based prediction model shows promise for the prediction of critical MFC data indicating higher tripping risk.

In this systematic review of the literature on using Machine Learning (ML) for credit risk prediction, we raise the need for financial institutions to use AI and ML to assess credit risk, analyzing large volumes of information. We posed research questions about algorithms, metrics, results, data sets, variables, and related limitations in predicting credit risk. We searched renowned databases to answer them and identified 52 relevant studies with the credit industry microfinance. Challenges and approaches in credit risk prediction using ML models we identified, difficulties with the implemented models such as the black box model, the need for explanatory artificial intelligence, the importance of selecting relevant features, addressing multicollinearity, and the problem of the imbalance in the input data. By answering the questions, we identified that the Boosted Category is the most researched family of ML models; the most commonly used metrics for evaluation are Area Under Curve (AUC), Accuracy (ACC), Recall, precision measure F1 (F1), and Precision; Research mainly uses public data sets to compare models, and private ones to generate new knowledge when applied to the real world. The most significant limitation identified is the representativeness of reality, and the variables primarily used in the microcredit industry are related data to the demographic, the operation, and payment behavior. This study aims to guide the developers of credit risk management tools and software towards the existing offer of ML methods, metrics, and techniques used to forecast it, thereby minimizing possible losses due to default and guiding risk appetite.

Google Trends data can be informative for infectious disease incidences, including Lyme disease. However, the use of Google Trends for predictive purposes is underutilized. In this study, we tested the ability of Google Trends search data to predict monthly state-level Lyme disease case counts in the United States. We requested Lyme disease data for the years 2010-2021. We downloaded Google Trends search data on terms for Lyme disease, symptoms of Lyme disease, and diseases with similar symptoms as Lyme disease. We built mixed negative binomial models based on a training dataset (2010-2016) and tested the models on a test dataset (2017-2021). A model was built for each search term and monthly lags of search terms were included as predictors. The highest performing models had high predictive ability, indicated by low Root Mean Squared Errors (RMSEs) and close association between observed and predicted case counts. The highest performing model was for the search term “Summer Flu”, which indicates low specificity of some of the terms. We outline challenges of using Google Trends data, including data availability and a mismatch between geographic units. We discuss opportunities for Google Trends data, including prediction of additional zoonotic diseases and incorporating environmental and companion animal data.

Background: External beam radiation therapy requires a sophisticated and laborious planning procedure. To improve the efficiency and quality of the planning procedure, machine learning predictions of the dose distributions have been introduced to speed up the planning procedure and to serve as quality assurance. The most recent dose prediction models are based on deep learning U-Nets that give good approximations of the dose in 3D almost instantly. It is our purpose to train a 3D dose prediction for glioblastoma VMAT treatment and test its robustness and sensitivity for the purpose of quality assurance of automatic contouring. Methods: From a cohort of 125 glioblastoma (GBM) patients, VMAT plans were created according to a clinical protocol. The initial model was trained on a concatenated 3D U-Net. A total of 60 cases were used for training, 15 for validation and 20 for testing. The prediction model was tested for sensitivity to dose changes according to realistic contour variations. Additionally, the model was tested for robustness by exposing it to a worst-case test set containing out-of-distribution cases.Results: The initially trained prediction model had a dose score of 0.94 Gy and a mean DVH score for all structures of 1.95 Gy. In terms of sensitivity, the model was able to predict the dose changes that occurred due to the contour variations with a mean error of 1.38 Gy.Conclusions: We obtained a 3D VMAT dose prediction model for GBM with limited data, providing good sensitivity to realistic contour variations. We tested and improved the model's robustness, by targeted updating the training set, making it a useful technique for dose awareness in the contouring evaluation and quality assurance.

Purpose: To compare refractive prediction error (PE)s between phacotrabeculectomy and phacoemulsification. Methods: Refractive PE was defined as the difference of spherical equivalent between the predicted value using the Barrett Universal II formula and the actual value obtained at postoperative one month. Forty-eight eyes that had undergone phacotrabeculectomy (19 eyes, open-angle glaucoma; 29 eyes, angle-closure glaucoma) were matched with 48 eyes that had undergone phacoemulsification by age, average keratometry value and axial length (AL), and their PEs were compared. The factors associated with PE were analyzed by multivariable regression analyses. Results: Phacotrabeculectomy group showed a larger absolute PE compared to the phacoemulsification group (0.51 ± 0.37 Diopters vs. 0.38 ± 0.22, P=0.033). Larger absolute PE was associated with longer AL (P=0.010) and higher intraocular pressure (IOP) difference (P=0.012). Hyperopic shift (PE>0) was associated with shallower preoperative anterior chamber depth (ACD) (P=0.024) and larger IOP difference (P=0.031). In the phacotrabeculectomy group, the PE was inversely correlated with AL: long eyes showed myopic shift and short eyes hyperopic shift (P=0.002). Conclusions: Surgeons should be aware of the possibility of worse refractive outcomes when planning phacotrabeculectomy especially in eyes with high preoperative IOP, shallow ACD, and/or extreme AL.

This study describes the AMD impacted environments and critically discusses the effects of AMD, current prediction and prevention methods and treatment technologies. The study further, crit-ically analyses the case studies, gaps in AMD research and the challenges and opportunities of-fered by AMD. The study outlined future technological intervention aiming at a paradigm shift towards reducing the volume of sludge generated as well as the operating cost and improving AMD treatment efficiency. The integrated AMD treatment technologies that result in a holistic approach toward sustainable AMD treatment are a current need. As a result, a sustainable AMD treatment strategy has been made possible due to water reuse and rich resource recoveries such sulphuric acid, rare earth elements, and metals. The cost of AMD treatment can be decreased with the use of recovered water and resources, which is essential for developing a sustainable AMD treatment process.

The primary goal of picture compression is to reduce the amount of unused image data while still storing or transmitting it in a format that is appropriate. The compression of raw binary data is quite different from the compression of a picture, and these differences may be rather substantial. In light of this, compression is often regarded as an essential technique for the purposes of both data storage an d transmission in order to mitigate the excessive amounts of data that are generated by these images. In order to transmit enormous datasets, particularly for the purposes of telemedicine and teleradiology, one needs a significant amount of storage capacity as well as an expansive network. As a result, compression is an important aspect of medical imaging. In addition to the importance of compression, the quality of the photos themselves is also an essential factor in the success of analysis. In addition to this, the amount of time necessary to compress the photographs before sending them should be reduced.

Machine learning methods have been a standard approach to select features that are associated with an outcome and build a prediction model when the number of candidate features is large. LASSO has been one of the most popular approaches to this end. LASSO approach selects features with large regression estimates, rather than based on statistical significance, associating the outcome, by imposing L1-norm penalty to overcome the high dimensionality of the candidate features. As a result, LASSO may select insignificant features while possibly missing significant ones. Furthermore, from our experience, LASSO has been found to select too many features. By selecting features that are not associated with the outcome, we may have to spend more cost to collect and manage them in the future use of a fitted prediction model. Using the combination of L1- and L2-norm penalties, elastic net (EN) tends to select more features than LASSO. The overly selected features that are not associated with the outcome act like white noise, so that the fitted prediction model loses the prediction accuracy. In this paper, we propose to use the standard regression methods (without any penalizing approach) with stepwise variable selection procedure to overcome these issues. Unlike LASSO and EN, this method selects features based on statistical significance. Through extensive simulations, we show that this maximum likelihood estimation based method selects very small number of features while maintaining a high prediction power, while LASSO and EN make a large number of false selections to result in loss of prediction accuracy. Contrary to LASSO and EN, the regression methods combined with a stepwise variable selection method is a standard statistical method, so that any biostatistician can use it to analyze high dimensional data even without advanced bioinformatics knowledge.

This paper presents a new method of process parameters optimization, adequate for 3D printing of PLA (Polylactic Acid) components. The authors developed a new Hybrid Manufacturing Equipment (HME), suitable for producing complex parts made from a biodegradable thermoplastic polymer, for environmental sustainability. Our new HME equipment is producing PLA parts by both additive and subtractive techniques, with the aim of obtaining accurate PLA components with a good surface quality. A design of experiments has been applied for optimization purposes. The following manufacturing parameters were analyzed: rotation of the spindle, cutting depth, feed rate, layer thickness, nozzle speed, and surface roughness. Linear regression models and neural network models were developed to improve and predict the surface roughness of the manufactured parts. A new test part was designed and manufactured from PLA, to validate the new mathematical models, which can now be applied for producing complex parts made from polymer materials.

Background: Cochlear implantation is an efficient treatment for postlingually deafened adults who do not benefit sufficiently from acoustic amplification. Implantation is indicated when it can be foreseen that speech recognition with a cochlear implant (CI) is superior to that with a hearing aid. Especially for subjects with residual speech recognition it is desirable to predict CI outcome on the basis of preoperative audiological tests. Purpose: The purpose of the study was to extend and to refine a previously developed model for CI outcome prediction for subjects with preoperative word recognition to include subjects with no residual hearing by incorporat-ing additional results of routine examinations. Results: By introducing the duration of unaided hearing loss (DuHL) the median absolute error (MAE) of the prediction was reduced. While for subjects with preoperative speech recognition the model modification did not change the MAE, for subjects with no residual speech recognition before surgery, the MAE decreased from 23.7% with the previous model to 17.2% with the extended model. Conclusions: Prediction of word recognition with CI is possible within clinically relevant limits. Outcome prediction is particu-larly important for preoperative counselling and in CI aftercare, to support systematic monitor-ing of CI fitting.

Asphalt pavement temperature has several applications, including pavement structural design and evaluation, asphalt mixture design, asphalt binder grade determination and material aging characterization. However, available asphalt pavement temperature prediction models were mostly developed for temperate climatic conditions, outside of the tropics. Before such models are adopted for use in a tropical climate, their applicability must be evaluated. This study evaluated five empirical asphalt pavement temperature prediction models developed by Lukanen et al. [1], Park et al. [2], Diefenderfer et al. [3], Taamneh [4] all in the United States and Asefzadeh et al. [5] in Canada to ascertain their prediction accuracy in tropical climate, using Ghana as a case study. In-situ asphalt pavement temperature data were measured at two sites for eight months: Kumasi and Tamale in the Forest and Savannah climatic zones, respectively. The measured pavement temperature data were statistically compared with predicted temperatures, and it was found that the Park et al. [2] model provided a more accurate pavement temperature prediction in both climatic zones. The other models either over-predicted or under-predicted asphalt pavement temperature with significant error margins. However, there is a need to improve the prediction accuracy of the Park et al. [2] model or a local model developed.

In the Versatile Video Coding (VVC) standard, affine motion models have been applied to enhance the resolution of complex motion patterns. However, due to the high computational complexity involved in affine motion estimation, real-time video processing applications face significant challenges. This paper focuses on optimizing affine motion estimation algorithms in the VVC environment and proposes a fast gradient iterative algorithm based on edge detection for efficient computation. Firstly, we establish judging conditions during the construction of affine motion candidate lists to streamline the redundant judging process. Secondly, we employ the Canny edge detection method for gradient assessment in the affine motion estimation process, thereby enhancing the iteration speed of affine motion vectors. Experimental results demonstrate that our affine motion estimation algorithm reduces encoding time by approximately 15%-35% while maintaining video bitrate and quality.

The Covid-19 pandemic and the subsequent implementation of lockdown measures have significantly impacted global electricity consumption, necessitating accurate energy consumption forecasts for optimal energy generation and distribution during a pandemic. In this study, we propose a new forecasting model called the Multivariate Multilayered LSTM with Covid-19 case injection ($\proposedModel$) for improved energy forecast during the next occurrence of a similar pandemic. We utilize data from commercial buildings in Melbourne, Australia during the Covid-19 pandemic to predict energy consumption and evaluate the model's performance against commonly used methods such as LSTM, Bi-LSTM, Linear Regression, Support Vector Machine and the previously published work of Multilayered LSTM (M-LSTM). The proposed forecasting model was analyzed using the following metrics of mean percent absolute error (MPAE), normalized root mean square error (NRMSE), and $R^2$ score values. The model $\proposedModel$ demonstrates superior performance, achieving the lowest MPAE values of 0.061, 0.093, and 0.158 for data sets from 3 different buildings, respectively. Our results highlight the improved precision and accuracy of the model, providing valuable information for energy management and decision-making during the challenges posed by the occurrence of a pandemic like Covid-19 in the future.

This study aims to identify the optimal combination of microphysics (MP) and cumulus (CU) parameterization schemes for accurately simulating heavy to violet rainfall events associated with Tropical Cyclones (TCs) and atmospheric disturbances in Thailand using the coupled Weather Research and Forecasting (WRF) and Regional Oceanic Model (ROMS), hereafter referred to as WRF-ROMS. Three CU schemes, namely Betts–Miller–Janjic (BMJ), Grell 3D Ensemble (G3), and Kain–Fritsch (KF), along with three MP schemes, namely Eta (ETA), Purdue Lin (LIN), and WRF Single-moment 3-class (WSM3), are selected for the sensitivity analysis. Seven instances of heavy to violent rainfall in Thailand, occurring during summer season of 2020 and associated with tropical storms and atmospheric disturbances, are simulated using all possible combinations of the chosen physics schemes. The simulated rain intensities are compared against observations from the National Hydroinformatics Data Center. Performance was assessed using the Probability of Detection (POD), False Alarm Ratio (FAR), and Critical Success Index (CSI) metrics. The models showed proficiency in predicting light to moderate rainfall, with certain combinations performing better in specific rainfall categories. However, forecasting heavy and violent rainfall proved challenging for all models and lead-time forecasts. Specific combinations, particularly those incorporating the KF scheme, demonstrated superior prediction of heavy to violent rainfall. The FAR values increased with lead-time and rain intensity, and the KF scheme combinations showed improved predictions of intense rainfall with lower FAR values. The CSI values indicated comparable performance between the control model and combination models across light to heavy rain categories, with the KF scheme showing better predictions for longer lead-times. However, accurately predicting intense rainfall remained limited. These findings highlight the need for further improvements, including refining model parameters and exploring advanced techniques to enhance accuracy and skill, particularly for longer-term forecasts. Sub-seasonal to seasonal prediction should be considered to extend forecast capabilities.

Interferon-beta is one of the most widely prescribed disease-modifying therapies for multiple sclerosis patients. However, this treatment is only partially effective, and a significant proportion of patients do not respond to this drug. This paper proposes an alternative fuzzy logic system based on the opinion of a neurology expert to classify relapsing-remitting multiple sclerosis patients: high, medium, and low responder to interferon-beta. Also, a pipeline prediction model trained with biomarkers associated to interferon-beta response is proposed for predicting whether patients are potential candidates to be treated with this drug, in order to avoid ineffective therapies. The classification results shows that the fuzzy system presents a 100% efficiency compared with an unsupervised hierarchical clustering method (52%). So, the performance of the prediction model is evaluated, and a 0.8 testing accuracy is achieved. Hence, a pipeline model including data standardization, data compression, and a learning algorithm, can be a useful tool for getting reliable predictions about the response to interferon-beta.

Prediction markets are heralded as powerful forecasting tools, but models to describe them often fail to capture the full complexity of the underlying mechanisms that drive price dynamics. To address this issue, we propose a model in which agents belong in a social network, have an opinion about the probability of a particular event to occur, and bet on the prediction market accordingly. Agents update their opinions about the event by interacting with their neighbours in the network, following the Deffuant model of opinion dynamics. Our results suggest that a simple market model that takes into account opinion formation dynamics is capable to replicate the empirical properties of historical prediction market time series, including volatility clustering and fat-tailed distribution of returns. Interestingly, the best results are obtained when there is the right level of variance in the opinions of the agents. Moreover, this paper provides a new way to indirectly validate opinion dynamics models against real data by using historical data obtained from PredictIt, an exchange platform whose data has never been used before to validate models of opinion diffusion.

In light of the recent pandemic, several COVID-19 vaccines were developed, tested and approved in a very short time, a process that otherwise takes many years. Above all, these efforts have also unmistakably revealed the capacity limits and potential for improvement in vaccine production. This review aims to emphasize recent approaches for targeted rapid adaptation and production of vaccines from an interdisciplinary multifaceted perspective. Using literature research, stakeholder analysis and a value proposition canvas, we reviewed technological innovations on the pharmacological level, formulation, validation and resilient vaccine production to supply bottlenecks and logistic networks. We identified four main drivers to accelerate the vaccine product life cycle: computerized candidate screening, modular production, digitized quality management and a resilient business model with corresponding transparent supply chains. In summary, the results presented here can serve as a guide and implementation tool for flexible, scalable vaccine production to respond swiftly to pandemic situations in the future.

Environmental monitoring systems play a crucial role in assessing environmental quality, detecting limits exceedances, and predicting potential ecological episodes. These systems rely on the measurement of various variables at specific locations and time intervals over an extended period. The concept of environmental monitoring encompasses the assessment of health and safety issues for public and environmental health purposes. Pollution of the atmosphere and water, climate change, and natural disasters are among the consequences of continuous industrial and municipal development and human interference in natural ecosystems. To address these challenges and to protect human lives and the environment, with a special concern on mitigating the ecological effects of industrial development, advanced technical solutions, including the technologies associated with artificial intelligence (artificial neural networks ANNs, machine learning ML) have been developed. These technologies offer powerful tools for analysing the vast amount of data collected by monitoring systems and extracting valuable insights. By applying ANNs and machine learning algorithms, environmental monitoring systems can effectively process and interpret the measured variables to assess environmental quality. Despite challenges and limitations, such as data quality and interpretability of AI models, ongoing research and interdisciplinary collaboration are paving the way for the successful implementation of AI in environmental monitoring, ultimately supporting informed decision-making and sustainable resource management.While several review papers have explored the theory of artificial intelligence (AI), here I aim to review the application of ANNs and ML, in environmental aspects, specifically in automotive and industrial emissions toxicity measurements, as well as atmospheric pollution prevention. By examining the potential of AI in these domains, the paper contributes to understanding the role of advanced technologies in environmental monitoring and protection.

In recent years, how to combine intelligent prospecting algorithms such as random forest with a large number of geological and mineral data for quantitative prediction of exploration geochemistry has become an important topic of concern to quantitatively improve the accuracy of target delineation. The ore-forming geological conditions in the central Kunlun area of Xinjiang are great and have good prospecting prospects. However, due to the exhaustion of shallow deposits and the lag of geological prospecting work in the past ten years, there has been no expected breakthrough in the search for large and super-large metal deposits for many years. There has been a serious shortage of reserve resources. The use of new theories, new methods and new technologies for mineral resources investigation and evaluation has become an urgent need in the current prospecting work. In view of this, based on the existing spatial database of geological and mineral resources in the central Kunlun of Xinjiang, combined with the geological characteristics, genesis and metallogenic regularity of the area, this paper carried out a series of studies on gold polymetallic minerals with the help of geographic information system and data science programming software platform. The researchers integrated geological and regional geochemical data, and constructed a random forest metallogenic discriminant model based on two different sampling methods (integrated random undersampling and selection of training samples) to predict the mineralization of gold polymetallic minerals in the central Kunlun area of Xinjiang and delineate the metallogenic target area. The quantitative prediction of gold polymetallic mineral resources in the central Kunlun area of Xinjiang by two random forest models is compared and discussed: the known ore spots, fault structures and geochemical information are extracted, and the known gold polymetallic ore spots and geochemical data are used to form a training set and a prediction set to construct a machine learning random forest model. The results of prediction evaluation and metallogenic prospect division show that for different sampling methods, the performance evaluation parameters of the training process show that the prediction accuracy of the selected training samples is higher, and the selected training samples are more reliable because they can fully learn the complex information of the original data. In the metallogenic prospect prediction and metallogenic potential division, the random forest model of selecting training samples has more reference value and further exploration research significance in the production problem considering the actual exploration cost because of its small area of high potential prediction area and high proportion of ore bearing per unit area. At the same time, this study innovatively improves the prediction accuracy, reduces the exploration risk, and expands the prospecting idea of machine learning algorithm in mathematical geology in the central Kunlun area of Xinjiang. The delineated metallogenic potential area has positive guiding significance for the actual gold polymetallic prospecting work in this area.

Abstract: Objective: This study aimed to estimate adherence to methotrexate in patients with rheumatoid arthritis and identify specific nonadherence risk factors. Methods: A cross-sectional study included 111 patients (age mean 56.2±10.6 years, 78.4% female, and disease duration mean 6 (3-13) years). Three adherence self-assessment questionnaires were used: the Compli-ance-Questionnaire-Rheumatology (CQR19), the Medication Adherence Reports Scale (MARS-5), and the Visual Analogue Scale (VAS). We also collected demographic data, disease and treatment characteristics, and anxiety/depression estimation results (Hospital Anxiety and Depression Scale- HADS). Results: Adherence was identified in 48.6% of patients (COR19), 70.3% (MARS-5), and 82.9% of patients in the VAS questionnaire. All three questionnaires displayed a significant positive mutual correlation: CQR19 with MARS-5 and VAS (r =0.364, r=0.329 respectively, p<0.001 for both), between VAS and MARS-5 score (r=0.496, p<0.001). A significant positive prediction was shown for urban residence (0.347 (0.134-0.901), p=0.030), using the MARS-5 scale, female sex (0.264 (0.095-0.730), p=0.010) according to CQR19 and for a dose of methotrexate (0.881 (0.783-0.992), p=0.036) in VAS scale, while negative prediction were shown for comorbidity number (3.062 (1.057-8.874), p=0.039), and depression (1.142 (1.010-1.293), p=0.035) using MARS-5 scale and for older age (1.041 (1.003-1.081), p=0.034) according to CQR19. The use of steroids was a significant positive predictor in all three questionnaires and remained an independent predictor for metho-trexate adherence in multivariant logistic regression. Conclusion: We showed nonadherence to methotrexate in a significant number of patients using all three questionnaires. Concomitant steroid therapy emerged as an independent positive predictor for adherence.

The land subsidence occurring in goafs after coal mining is a protracted process. The accurate prediction of long-term land subsidence in goafs relies heavily on the availability of long-term monitoring data. However, the scarcity of continuous long-term land subsidence monitoring data subsequent to the cessation of mining significantly hinders the accurate prediction of long-term land subsidence in goafs. To address this challenge, this study proposes an innovative method based on Interferometric Synthetic Aperture Radar (InSAR) for predicting long-term land subsidence of goafs following coal mining. The proposed method employs a concatenation approach that integrates multiple short-term monitoring data from different coal faces, each with distinct cessation times, into a cohesive and uniform long-term sequence by normalizing the subsidence rates. The method was verified using actual monitoring data from the Yangquan No.2 mine in Shanxi Province, China. Initially, coal faces with same shapes but varying cessation times were selected for analysis. Using InSAR monitoring data collected between June and December of 2016, the average subsidence rate corresponding to the duration after coal mining cessation of each coal face was back-calculated. Subsequently, a function relating subsidence rate to the duration after coal mining cessation was fitted to the data. Finally, the relationship between cumulative subsidence and the duration after coal mining cessation was derived by integrating the function. The results indicated that the relationship between subsidence rate and duration after coal mining cessation followed an exponential function for a given coal face, whereas the relationship between cumulative subsidence and duration after coal mining cessation conformed to the Knothe time function. Notably, after the cessation of coal mining, significant land subsidence persisted in the goaf of the Yangquan No.2 mine for a duration ranging from 5 to 10 years. The cumulative subsidence curve along the long axis of the coal face ultimately exhibited an inclined W-shape. The proposed method enables the quantitative prediction of residual land subsidence in goafs, even in cases where continuous long-term monitoring data are insufficient, thus providing valuable guidance for construction decisions above the goaf.

Strong convective storms can be a serious threat to modern society, influencing both the economy and human life. Thunderstorms can bring much-needed rain after a dry spell, but the nature of thunderstorm mostly causes damage due to high wind associated with it and heavy intensity rain that mostly causes quick overlandflow and flashfloods. The paper focused on the 2011 Pukkelpop event in Belgium where due to heavy thunderstorm a lot of financial damage occurred, and five casualties. In this paper we look into the basic elements that enforces the creation of a thunderstorm like CAPE and windshear. A representative grid has been taken from the Alaro-0 model of 12.5 km resolution for the analysis of the thunderstorm over Belgium which is detailed out in the methodology. The model runs of Alaro-0 from Royal Meteorological Institute of Belgium (RMI) is used for historical and future years for CAPE and Shear. We look into STEnv which is a composite number that can provide some insight on occurrence of thunderstorm, and STEnv is when CAPE*Shear exceeds certain threshold. In this study the threshold has been chosen as 97%. Only summer months have been taken into account into this study as summer(s) has the most thunderstorm in Belgium. The analysis of CAPE and STEnv over historical period (1977-2005), near future (2041-2069) and far future (2071-2099) shows significant increase in occurrence of thunderstorm in the 2071-2099s, specially in extreme cases such as 97% and 99% quantile. CAPE (J/Kg) increases in all future scenarios compared to the historical period. In 2071-2099s, CAPE increases from 2100 J/Kg to 2300 J/Kg (90% quantile) and from 3500 J/Kg to 3900 J/Kg (99% quantile) compared to the historical period. The number of STEnv increases from 300 to 378 in top 10% storm case (90% quantile), 158 to 218 in top 5% storm (95% quantile), 97 to 153 in top 3% storm (97% quantile) and 33 to 66 in top 1% storm (99% quantile) with a 90% confidence interval overall. Shear mostly remains unchanged. The study also shows spatial variation of CAPE, shear and STEnv over Belgium for present and future scenarios in different extremities (90%, 95%, 97% and 99% quantiles). There is a good indication that increase in CAPE translates to increase in STEnv, which is an accepted measure to predict occurrence of thunderstorm. Future climate change also amplifies the occurrence of thunderstorm, which is coherent with relevant studies. The uncertainty related to the study can be reduced with more detailed dataset and involvement of numerical weather prediction models beyond data statistics.

During the last years, the increasing evidence of dietary antioxidant compounds and reducing chronic diseases and the relationship between diet and health have promoted an important innovation on the baked product sector, aiming at healthier formulations. This study aims to develop a tool based on mathematical models to predict baked goods total antioxidant capacity (TAC). The high variability of antioxidant properties of flours based on the aspects related to type of grains, varieties, proximal composition and processing, among others, makes very difficult to innovate on food product development without specific analysis. Using Total phenol content (TP), Oxygen radical absorbance capacity (ORAC) and Ferric reducing antioxidant power assay (FRAP) as proxies of antioxidant capacity. Three Bayesian-type models are proposed based on a double exponential parameterised curve that reflects the initial decrease and subsequent increase as a consequence of the observed processes of degradation and generation, respectively, of the antioxidant compounds. Once the values of the main parameters of each curve have been determined, support vector machines (SVR) with exponential kernel were used to predict, based on the temperature and duration of baking as well as the values of proteins and fibers of each native grain, the values of TAC during the baking time.

The objective of the present study is to isolate phages targeting multidrug resistant (MDR), extended spectrum beta lactamase (ESBL) positive clinical isolate of E. coli ( U1007), sequence and analyze the phage genome and use machine learning tools to predict host cell surface receptor and finally evaluate the efficiency of monophage and phage cocktail in vitro and in vivo in a zebrafish model. Phage specific for E. coli U1007 was isolated from Ganges River (designated as U1G), Cuoom River (designated as CR) and Hospital waste water (designated as M phage). The obtained phages were triple purified and enriched. U1G phages had a greater burst size of 124 PFU/cell and a latent time of 25 min.M phage had a burst size of 150 PFU/cell with a shortlatent time of 20min. Similarly CR phage has a short latent 20 min and a burst size of 115 PFU/cell. Based on capsid architecture, U1G phage resembles Podoviridae, CR phage is structurally similar to Myoviridae and M phage has morphology that resembles Siphoviridae. Genome sequencing and analysis revealed that the size of the U1G phage genome is 73275 bp Whereas that of CR phage and M phage are 45236 bp and 45294 bp, respectively. All three genomes were marked by the absence of genes encoding tRNA sequence, antibiotic resistant or virulent genes. A machine learning (ML) based multi-class classification model using algorithms such as Random Forest, Logistic Regression, and Decision Tree were employed to predict the host receptor targeted by all 3 phages and the best performing algorithm Random Forest predicted LPS O antigen , LamB or OmpC for U1G FhuA, OmpC for CR phage and FhuA, LamB, TonB or OmpF for the M phage as the host receptor targeted by the receptor binding protein (RBP) of the phages. In vitro time kill assay showed that treatment with monophages alone and along with colistin resulted in regrowth whereas phage combinations significantly reduced the regrowth and by 24h the phage cocktail along with colistin produced a significant 3 log declinein cell counts relative to the untreated control. In vivo intramuscular infection study in zebrafish showed that phages were non toxic and a cocktail of dual (U1G +M) phage along with colsitin resulted in a significant 3.5 log decline in cell counts whereas triple phage combination along with colistin resulted in 3 log decline in cell counts probably due to host receptor competition. Our study highlights the potential of phage cocktail therapy in mitigating MDR clinical isolate of E. coli in vitro and in vivo.

The prediction of stock prices holds significant implications for researchers and investors in evaluating stock value and risk. In recent years, researchers have increasingly replaced traditional machine learning methods with deep learning approaches in this domain. However, the application of deep learning in forecasting stock prices is confronted with the challenge of overfitting. To address the issue of overfitting and enhance predictive accuracy, this study proposes a stock prediction model based on GRU (Gated Recurrent Unit) with reconstructed datasets. This model integrates data from other stocks within the same industry, thereby enriching the extracted features and mitigating the risk of overfitting. Additionally, an auxiliary module is employed to augment the volume of data through dataset reconstruction, thereby enhancing the model’s training comprehensiveness and generalization capabilities. Experimental results demonstrate a substantial improvement in prediction accuracy across various industries.

Financial markets require a great deal of decision making from the investors and market makers. One metric that can help ease the process of decision making is investment risk which can be measured in two parts; systematic risk and idiosyncratic risk. Clear understanding of the volatilities in each risk component can be a powerful signal in recognizing the right assets to maximize the investment returns. In this paper, we focus on the idiosyncratic volatility values and pre-calculate the idiosyncratic volatility values for 31,198 members of NYSE, Amex and Nasdaq markets for the trades occurring between January 1963 and December 2019. Utilizing a subset of dataset, limited to Nasdaq100 index, we consider the application of machine learning techniques in predicting the idiosyncratic volatility values using the raw trade data to explore a data extension option for the future market trade records that have not yet occurred. We offer a deep learning based regression model and compare it with traditional tree-based methods on a small subset of our per-calculated idiosyncratic volatility dataset. Our analytical results show that the performance of the deep learning techniques is much more robust in comparison to that of the traditional tree-based baselines.

In order to realize the performance degradation trend prediction accurately, a prediction method based on multi-domain features and temporal convolutional network (TCN) is proposed. Firstly, construct a high-dimensional feature set in the multi-domain of vibration signals, and use comprehensive evaluation indicators to preliminarily screen performance degradation indexes with good sensitivity and strong trend. Secondly, the kernel principal component analysis (KPCA) method is adopted to eliminate redundant information between multi-domain features, and construct a health index (HI) based on convolutional auto-encoder (CAE) network. Thirdly, a TCN-based performance degradation trend prediction model is constructed, and direct multi-step prediction is used to predict the performance degradation trend of the monitored object. On this basis, the validity of the proposed method is verified using the bearing public data, and it is successfully applied to performance degradation trend prediction of rolling contact fatigue specimen. The results show that the feature set can be reduced from 14 dimensions to 4 dimensions by using KPCA, while 98.33% of the information of the original feature set is retained. Furthermore, the method of constructing HI based on CAE network is effective. The change process of the HI constructed truly reflects the performance degradation process of the rolling contact fatigue specimen. Compared with the two commonly used HI construction methods, auto-encoding (AE) network and gaussian mixture model (GMM), this method has obvious advantages. At the same time, the prediction model based on TCN can accurately predict the performance degradation of the rolling contact fatigue specimen with the root mean square error 0.0146 and the mean absolute error 0.0105, which has better performance and higher prediction accuracy than the prediction model based on the long short-term memory (LSTM) network and the gated recurrent unit (GRU). This method has general significance and may be extended to the performance degradation prediction of other mechanical equipment/parts.

Liver cirrhosis development is a multifactorial process resulting by a combination of environmental and genetic factors. The aim of the study was to develop accurate non-invasive diagnostic and prognostic models for alcoholic cirrhosis. Consecutive subjects with at-risk alcohol intake were retrospectively enrolled (110 cirrhotic patients and 411 non-cirrhotics). At enrollment, the data about the lifetime drinking history were collected and all patients were tested for PNPLA3 rs738409, TM6SF2 rs58542926 and HSD17B13 rs72613567 variants. In cross-sectional analyses, models for the diagnosis of cirrhosis were developed using multivariate logistic regression. A predictive score for cirrhosis development over 24 years was built by evaluating time-dependent AUC curves. The best diagnostic accuracy was demonstrated by the model which also includes daily alcohol consumption, duration of hazardous alcohol use and genetic variants, with AUCs of 0.951 (95% CI 0.925-0.977) and 0.887 (95% CI 0.925-0.977) for cirrhosis and compensated cirrhosis, respectively. The predictive model for cirrhosis future development (AUC of 0.836 95% CI: 0.769 - 0.904) accounted for age at onset of at-risk alcohol consumption and the number of PNPLA3 and HSD17B13 variant alleles. We have developed accurate genetic and alcohol consumption models for the diagnosis of alcoholic cirrhosis and the prediction of its future risk.

In this study, we developed a model that can predict whether patients with cerebral arteriovenous malformation (AVM) will be cured 36 months after intervention by means of stereotactic radiosurgery (SRS), and identified the most important predictors that explain the probability of being cured. A machine learning (ML) approach was applied using decision tree (DT) and logistic regression (LR) techniques on historical data (sociodemographic, clinical, treatment, angioarchitecture, and radiosurgery procedure) of 202 patients with AVM who underwent SRS at the Instituto de Radiocirugía del Perú (IRP) between 2005 and 2018. The LR model obtained the best results for predicting AVM cure with an accuracy of 92.16%, sensitivity of 92.86%, specificity of 88.89%, precision of 97.50%, and AUC of 97.62%, which shows that ML models are suitable for use for predicting the prognosis of medical conditions such as AVM and can be a support tool for medical decision-making. In addition, several factors were identified that could explain whether patients with AMV would be cured at 36 months with the highest likelihood: the location of the AVM, the occupation of the patient, and the presence of hemorrhage.

The goal was to create a novel machine learning (ML) model which can predict the magnitude and direction of pubertal mandibular growth in males with Class II malocclusion. Lateral cephalometric radiographs of 123 males at three time points (T1: 12, T2: 14, T3: 16 years old) were collected from an online database of longitudinal growth studies. Each radiograph was traced, and 7 different ML models were trained using 38 data points obtained from 92 subjects. 31 subjects were used as a test group, to predict post-pubertal mandibular length and Y-axis using input data from T1 and T2 combined (2-year prediction), and T1 alone (4-year prediction). Mean absolute errors (MAEs) were used to evaluate the accuracy of each model. For all ML methods tested using the 2-year prediction, the MAEs for post-pubertal mandibular length ranged from 2.11-6.07mm and 0.85-2.74° for the Y-axis. For all ML methods tested with 4-year prediction, the MAEs for post-pubertal mandibular length ranged from 2.32-5.28 mm and 1.25-1.72° for the Y-axis. Besides its initial length, the most predictive factors for mandibular length were found to be chronological age, upper and lower face heights, upper and lower incisor positions and inclinations. For the Y-axis, the most predictive factors were found to be Y-axis at earlier time points, SN-MP, SN-Pog, SNB and SNA. Whilst the potential of ML techniques to accurately forecast future mandibular growth in Class II cases is promising, a requirement for more substantial sample sizes exists to further enhance the precision of these predictions.

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. The epileptic seizure prediction models face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model that enhances the capability by utilizing the significant amount of seizure patterns from globally distributed patients with data privacy. The determination of the preictal state is influenced by global and local model-assisted decision-making by modeling the two-level edge layer. Integrating the Spiking Encoder (SE) with Graph Convolutional Neural Network (Spiking-GCNN) works as the local model trained using the bi-timescale approach. Each local model utilizes the aggregated seizure knowledge from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. The proposed seizure prediction is evaluated using benchmark datasets by comparing them with the existing works to demonstrate the potential results.

The mountains in northern Xinjiang of China were studied during the snowmelt season. Multi-source fusion live data Chinese Land Data Assimilation System (CLDAS,0.05°× 0.05°,hourly data) were used as real data, and Central Meteorological Observatory guidance forecast (SCMOC,0.05°× 0.05 °,forecasting the following 10 days in 3 h intervals) was used as forecast data, both issued by the China Meteorological Administration. The dynamic linear regression and the average filter correction algorithms were selected to revise the original forecast products SCMOC.Based on conventional temperature forecast information,we designed four temperature rise prediction algorithms for essential factors affecting snowmelt.Temperature rise prediction algorithms included the daily maximum temperature algorithm, daily temperature rise range algorithm, snowmelt temperature algorithm, and daily snowmelt duration algorithm.Four temperature rise prediction algorithms values were calculated of each prediction product.Root-mean-square error algorithm and temperature prediction accuracy algorithm were used to compare and test each prediction algorithm value from the time sequence and spatial distribution.Comprehensive tests show that the forecast product revised by the average filter algorithm was superior to revised by the dynamic linear regression algorithm as well as the original forecast product.Through these algorithms, the more suitable temperature rise forecast value for each grid point in the study area can be obtained at different prediction times. The comprehensive and accurate temperature forecast value in mountainous snowmelt season can provide an accurate theoretical basis for effective prediction of the runoff in snowmelt areas and prevention of snowmelt flooding.

The deployment of a manufacturing execution system (MES) holds promising potential in facilitating the accumulation of a substantial amount of inspection data. Low quality levels in discrete manufacturing environments are the result of multi-factor coupling and failure to find quality issues in a timely manner within manufacturing settings may trigger the propagation of defects downstream. Currently, most of the inspection quality methods are direct measurement followed by manual judgment. The integration of deep learning methods provides a feasible way to identify defects in a timely manner, thus improving the acceptance rate of factories. This paper focuses on the design of a data-driven quality prediction and control model around discrete manufacturing characteristics, and use fuzzy theory to evaluate the quality level of production stages. Building Multivariate Long and short-term memory learning hidden quality representations to extract predictions from multi-level inspection data in manufacturing systems. Finally, by validating the data of actual produced water dispensers according to three evaluation indexes, RMSE, MAE, MAPE, the results show that Multivariate Long and short-term memory has better prediction performance.

Buildings are responsible for approximately 40% of the world’s energy consumption and 36% of the total carbon dioxide emissions. Building occupancy is essential, enabling Occupant-Centric Control for zero emissions and decarbonization. Although existing machine learning and deep learning methods for building occupancy prediction have achieved remarked progress, their analyses remain limited when applied to complex real-world scenarios. Besides, there is a high expectation for Transformer algorithms to predict building occupancy accurately. Therefore, this paper presents an Occupancy Prediction Transformer network (OPTnet). We fuse and feed multi-sensor data (building occupancy, indoor environmental conditions, HVAC operations) into a Transformer model to forecast the future occupancy presence in multiple zones. We perform experimental analysis and compare it to different occupancy prediction methods (e.g., Decision Tree, Long Short-Term Memory networks, Multi-layer perceptron) and diverse time horizons (1,2,3,5,10,20,30mins). The performance metrics (e.g., Accuracy and Mean Squared Error) are employed to evaluate the effectiveness of prediction algorithms. Our OPTnet method achieves superior performance on our experimental two-week data compared to existing methods. The improved performance signifies its potential to enhance HVAC control systems and energy optimization strategies. We will make the code publicly available at https://github.com/kailaisun/occupancy-prediction-binary to promote transparency and reproducibility.

'Huangguan' pear has significant social and economic value, and phosphorus, as one of the three main mineral elements of plants, has an irreplaceable effect on the normal growth of 'Huangguan' pear trees. The objective of this study was to predict the content of phosphorus in the pulp and peel of ‘Huangguan’ pears nondestructively and conveniently by using near-infrared spectroscopy (900–1700 nm) technology. First, twelve algorithms are used to preprocess the original spectral data, and the partial least squares regression algorithm and the gradient boosting regression tree algorithm are used to build a full-band prediction model based on the original spectral data and the processed spectral data. The characteristic wavelengths were extracted using genetic algorithms, followed by establishing a characteristic wavelength prediction model. The prediction accuracy of the models was evaluated according to the coefficient of determination R² and the relative analysis error RPD. The study found that the best prediction model for predicting phosphorus content in the pulp of 'Huangguan' pear was MSC-GA-PLSR, which had R²=0.843 and RPD=1.857 in the modelling set and R²=0.989 and RPD=7.041 in the prediction set. The best prediction model for predicting phosphorus content in the peel of ‘Huangguan’ pear was SG+SNV+FD-GA-PLSR, which had R²=0.991 and RPD=7.470 in the modelling set and R²=0.974 and RPD=4.414 in the prediction set, and the effect was good and met expectations. The results demonstrated that near-infrared spectroscopy could successfully achieve nondestructive detection of phosphorus content in the pulp and peel of 'Huangguan' pears.

GNSS time series prediction plays a significant role in monitoring crustal plate motion, landslide detection, and maintenance of the global coordinate framework. Long Short-Term Memory (LSTM), a deep learning model has been widely applied in the field of high-precision time series prediction especially when combined with Variational Mode Decomposition (VMD) to form the VMD-LSTM hybrid model. To further improve the prediction accuracy of the VMD-LSTM model, this paper proposes a dual variational modal decomposition long short-term memory (DVMD-LSTM) model to effectively handle the noise in GNSS time series prediction. This model extracts fluctuation features from the residual terms obtained after VMD decomposition to reduce the prediction errors associated with residual terms in the VMD-LSTM model. Daily E, N, and U coordinate data recorded at multiple GNSS stations between 2000 and 2022 are used to validate the performance of the proposed DVMD-LSTM model. The experimental results demonstrate that compared to the VMD-LSTM model, the DVMD-LSTM model achieves significant improvements in prediction performance across all measurement stations. The average RMSE is reduced by 9.86%, and the average MAE is reduced by 9.44%. Furthermore, the average accuracy of the optimal noise model for the predicted results is improved by 36.50%, and the average speed accuracy of the predicted results is enhanced by 33.02%. These findings collectively attest to the superior predictive capabilities of the DVMD-LSTM model, thereby enhancing the reliability of the predicted results.

The purpose of this work is to compare two fracture prediction models with real-world data. The pure Artificial Neural Network (ANN) model emphasizes regression analysis, while the hybrid model (SVM-ANN) focuses on the combination of regression and classification analysis or Support Vector Machine. The results were subsequently tested against logging data by combining the Machine Learning approach with advanced logging tools. In this context, we used electrical image logs and the dipole acoustic tool which together allowed the distinction of 404 open fractures and 231 closed fractures and, consequently the estimation of fracture porosity. The results are then fed into two machine-learning algorithms. Pure Artificial Neural Networks and hybrid models are used to establish comprehensive results, which are subsequently tested to check the accuracy of the models. The outputs obtained from the two methods demonstrate that the hybridized model has a lower Root Mean Square Error (RMSE) than pure ANN. The results of our approach strongly suggest that incorporating hybridized machine learning algorithms in fracture porosity estimations can contribute to the development of more trustworthy static reservoir models in simulation programs. Finally, the combination of Machine Learning (ML) and well-log analysis do permit reliable estimation of fracture porosity in the Ahnet field in Algeria, where, in many places, advanced logging data is absent and costly.

Research in brain stroke prediction is very crucial as it can lead to the development of early detection techniques and interventions that can enhance the prognosis for stroke victims. Early detection and intervention can help to minimise the damage caused by a stroke, reduce the risk of long-term complications, and enhance the general quality of life for people who have survived a stroke. Additionally, research in stroke prediction can help to identify risk factors and improve understanding of the underlying causes of stroke, which can lead to the development of better prevention strategies. Research on brain stroke prediction is ongoing and has led to the development of various models and tools for predicting the risk of stroke and detecting it early. However, the implementation and use of these tools in clinical practise vary depending on several factors, such as the availability of resources, the specific healthcare system, and the level of awareness and acceptance of these tools among healthcare providers and patients. In general, risk prediction models may be used to quickly identify individuals at high risk of stroke and target them for preventive interventions, such as lifestyle changes, medication management, and screenings. Early detection tools can be used to quickly identify stroke symptoms and initiate appropriate treatment, which can improve outcomes for stroke patients. However, it is important to note that research and development of these models and tools are ongoing, and their use in clinical practise is constantly evaluated and updated. It may take time for these tools to be widely adopted in clinical practise and to see their real-world impact. This research paper focuses on predicting brain stroke occurrence using a range of machine learning algorithms such as Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Gaussian Naive Bayes (GNB), Bernoulli Naive Bayes (BNB), and a Voting Classifier. The main emphasis of this research was to compare the effectiveness of oversampling techniques, as the data was significantly imbalanced. We have used evaluation metrics in this research to assess the accuracy, precision, recall, and other key performance indicators of a model's predictions. Area under the Receiver Operating Characteristics Curve (AUC), minority class accuracy, and majority class accuracy were used to assess the approaches.

In this paper, the problem of predicting future failure times based on a jointly type-II censored sample from k exponential populations is considered. The Bayesian prediction intervals and point predictors were then obtained. Generalized Bayes is a Bayesian study based on a learning-rate parameter. This study investigated the effects of the learning rate parameters on the prediction results. The loss functions of squared error, Linex, and general entropy were used as point predictors. Monte Carlo simulations were performed to show the effectiveness of the learning rate parameter in improving the results of prediction intervals and point predictors.