Glioblastoma (GBM) is a very aggressive malignant brain tumor with the vast majority of patients surviving less than 12 months (Short-term survivors [STS]). Only around 2% of patients survive more than 36 months (Long-term survivors [LTS]). Studying these extreme survival groups might help in better understanding GBM biology. This work aims at exploring application of machine learning methods in predicting survival groups(STS, LTS). We used age and gene expression profiles belonging to 249 samples from publicly available datasets. 10 Machine learning methods have been implemented and compared for their performances. Hyperparameter tuned random forest model performed best with accuracy of 80% (AUC of 74% and F1_score of 85%). The performance of this model is validated on external test data of 16 samples. The model predicted the true survival group for 15 samples achieving an accuracy of 93.75%. This classification model is deployed as a web tool GlioSurvML. The top 1500 features which retained classification efficiency (Accuracy of 80%, AUC of 74%) were studied for enriched pathways and disease-causal biomarker associations using the HumanPSD^TM database. We identified 199 genes as possible biomarkers of GBM and/or similar diseases (like Glioma, astrocytoma, and others). 57 of these genes are shown to be differentially expressed across survival groups and/or have impact on survival. This work demonstrates the application of machine learning methods in predicting survival groups of GBM.

Introduction: Congenital heart defects (CHD) are the most frequent group of major congenital anomalies, accounting for almost 1% of all births. They comprise a very heterogeneous group of birth defects in terms of their severity, clinical management, epidemiology and embryologic origins. Taking this heterogeneity into account is an important imperative to provide reliable prognostic information to patients and their caregivers, as well as to compare results between centers or to assess alternative diagnostic and treatment strategies. The Anatomic and Clinical Classification of CHD (ACC-CHD) aims to facilitate both the CHD coding process and data analysis in clinical and epidemiological studies. Objectives: 1) To describe the long-term childhood survival of newborns with CHD and 2) To develop and validate predictive models of infant mortality based on the ACC-CHD. Materials and Methods: This study is based on data from a population-based, prospective cohort study: Epidemiological Study of Children with Congenital Heart Defects (EPICARD). The final study population comprised 1881 newborns with CHD after excluding cases that were associated with chromosomal and other anomalies. Statistical analysis included non-parametric survival analysis and flexible parametric survival models. The predictive performance of models was assessed by Harrell’s C index and the Royston-Sauerbrei R2 with internal validation by bootstrap. Results: The overall 8-year survival rate for newborns with isolated CHD was 0.96 [0.93- 0.95]. There was a substantial difference between the survival rate of the categories of ACC-CHD. The highest and lowest 8-year survival rates were 0.995 [0.989-0.997] and 0.34 [0.21-0.50] for “interatrial communication abnormalities and ventricular septal defects” and "functionally univentricular heart", respectively. Model discrimination as measured by Harrell’s C was 87% and 89% for the model with ACC-CHD alone and the full model, which included other known predictors of infant mortality, respectively. The predictive performance as measured by R2 was 45% and 50%, for the ACC-CHD alone and the full model. These measures were essentially the same after internal validation by bootstrap. Conclusion: The ACC-CHD classification provided the basis of a highly discriminant survival model with good predictive ability for the 8-year survival of newborns with CHD. Prediction of individual outcomes remains an important clinical and statistical challenge.

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.

Heavy rains result in significant threats to human health and life. Floods and other natural disasters, which have a global impact annually, can be attributed to extended periods of intense precipitation. Accurate rainfall prediction is crucial in nations such as Bangladesh, where agriculture is the predominant field of occupation. The efficiency of machine learning methods is enhanced by the nonlinearity of rainfall, surpassing the effectiveness of other approaches. This study proposes the novel combination of rainfall occurrence prediction, rainfall amount prediction, and daily average temperature prediction. This research implements machine learning techniques and an ensemble-based classifier to predict rainfall occurrence, as well as machine learning regressor models and an ensemble-based regressor to predict the rainfall amount and daily average temperature, using the Bangladesh Weather Dataset. The ensemble classifier demonstrated an accuracy of 83.41% and a recall of 78.17%, exhibiting the best performance in predicting when it will rain, but its precision was the lowest, at 51.16%. The ensemble regression model outperformed the base models, including linear regression, random forest, and support vector regression in rainfall amount prediction, with the lowest mean absolute error of 0.36 and root mean squared error of 0.90. Additionally, this model provided the most precise daily average temperature prediction results with the lowest mean absolute error of 0.42 and root mean squared error of 0.54, highlighting its superiority over the other regression models in forecasting temperature. Ensemble approaches consistently exhibit superior task performance metrics.

The objective of this study is to develop a predictive model for low-carbon bainitic steel utilising the P and λ parameters. The tempering activation energy of the steel was calculated through statistical methods. Kinetic curves for the hardness equivalents and a nomograph for tempering process parameters were plotted. The error analysis indicates that the predicted values based on the λ and P parameters had errors within 15% and 10%, respectively. The model can be effectively utilised to predict mechanical properties and optimise parameters during the tempering process.

Background/Objectives: Determining the outcome of epilepsy is crucial for making proactive and timely treatment decisions, as well as for counseling patients. Recent research efforts have focused on using various imaging techniques and EEG for prognostication; however, there is insufficient evidence regarding the role of blood parameters. Our study aimed to investigate the additional prognostic value of routine blood parameters in predicting epilepsy outcomes. Methods: We analyzed data from 1,782 patients who underwent routine blood tests within 90 days of their first visit and had a minimum follow-up duration of three years. The etiological types were structural (35.1%), genetic (14.2%), immune (4.7%), infectious (2.9%), and unknown (42.6%). The outcome was defined as the presence of seizures in the last year. Results: Initially, a multivariate analysis was conducted based on clinical variables, MRI, and EEG data. This analysis revealed that sex, age of onset, epileptiform discharge, structural etiology, and the number of antiseizure medications were related to the outcome, with an area under curve (AUC) of 0.708. Among the blood parameters, fibrinogen, bilirubin, uric acid, and aPTT were significant, with AUCs of 0.602, 0.597, 0.455, and 0.549, respectively. Including these blood parameters in the analysis slightly improved the AUC to 0.713. Conclusions: Some blood parameters were found to be related to the final outcome, potentially paving the way to understanding the mechanisms of epileptogenesis and drug resistance.

Artificial intelligence (AI) is revolutionizing the textile industry by improving the prediction of fabric properties and handfeel, which are essential for assessing textile quality and performance. However, the practical application and translation of AI-predicted results into real-world textile production remain unclear, posing challenges for widespread adoption. This paper systematically reviews AI-driven techniques for predicting these characteristics by focusing on model mechanisms, dataset diversity, and prediction accuracy. Among 811 papers initially identified, 26 were selected for in-depth analysis through both bibliometric and content analysis. The review categorizes and evaluates various AI approaches, including machine learning, deep learning, and hybrid models, across different types of fabric. Despite significant advances, challenges remain, such as ensuring model generalization and managing complex fabric behavior. Future research should focus on developing more robust models, integrating sustainability, and refining feature extraction techniques. This review highlights the critical gaps in the literature and provides practical insights to enhance AI-driven prediction of fabric properties, thus guiding future textile innovations.

Multimodal knowledge graph completion necessitates the integration of information from multiple modalities (such as images and text) into the structural representation of entities to improve link prediction. However, most existing studies have overlooked the interaction between different modalities. To address this issue, this paper proposed a Transformer-based knowledge graph link prediction model (MM-Transformer) that fuses multimodal features. Different modal encoders are employed to extract structural, visual and textual features, and hybrid key-value calculations are performed on features from different modalities based on the Transformer architecture. The similarities of textual tags to structural tags and visual tags are calculated and aggregated respectively, and multimodal entity representations are modeled and optimized to reduce the heterogeneity of the representations. Experimental results demonstrate that, compared to the current multimodal state-of-the-art methods, the proposed method achieves significant performance improvements in knowledge graph link prediction tasks. This proves that the proposed method effectively addresses the problem of multimodal feature fusion in knowledge graph link prediction tasks.

By using the particle swarm optimization algorithm for crystal structure prediction, we reveal a newly orthorhombic Cmcm structure of HfB4, which is more energetically superior to the previously proposed YB4-, ReP4-, FeB4-, CrB4-, and MnB4-type structures in the considered pressure range. The phonon dispersion and elastic constants calculations confirm that the new phase is dynamically and mechanically stable. The calculated large shear modulus (240 GPa) and high hardness (45.7 GPa) imply that the predicted Cmcm-HfB4 is a potential superhard material. Meanwhile, the directional dependences of the Young's modulus, bulk modulus, and shear modulus for HfB4 are systematically investigated. Further analyses of the density of states and electronic localization function indicate that the strong B-B and B-Hf covalent bonds greatly contribute to its high hardness and stability.

Background/Objectives: Congenital Myasthenic Syndromes (CMS) are caused by variants in >30 genes with increasing numbers of variants of unknown significance (VUS) discovered by next generation sequencing. Establishing VUS pathogenicity requires in vitro studies that slow diagno-sis and treatment initiation. Recent protein structure prediction softwares, AlphaFold2/ColabFold, have revolutionised structural biology; such predictions have also been leveraged in AlphaM-issense which predicts ClinVar variant pathogenicity with 90% accuracy. Few reports, however, have tested these tools on rigorously-characterised clinical data. We therefore assessed ColabFold and AlphaMissense as diagnostic aids for CMS, using variants of the CHRN genes that encode the nicotinic acetylcholine receptor (nAChR). Methods: Utilising a dataset of 61 clinically-validated CHRN variants, (1) we evaluated the pos-sibility of a ColabFold metric (either predicted structural disruption, prediction confidence, and prediction quality), that distinguishes variant pathogenicity. (2) We assessed AlphaMissenses’ ability to differentiate variant pathogenicity. (3) We compared AlphaMissense to existing patho-genicity prediction programmes, AlamutVP and EVE. Results: Analysing variant effects on ColabFold CHRN structure prediction, prediction confi-dence, and prediction quality, doesn’t yield any pathogenicity-indicative metric. However, Al-phaMissense predicts variant pathogenicity with 63.93% accuracy on our dataset – a much greater proportion than AlamutVP (27.87%) and EVE (28.33%). Conclusions: Emerging in silico tools can revolutionise genetic disease diagnosis – however, im-provement, refinement, and clinical validation is imperative prior to practical acquisition.

This paper presents the PEnsemble 4 model, a sophisticated machine learning framework that integrates IoT-based environmental data to accurately forecast maize yield. With the projected significant growth in global maize demand over the next decade, the inherent risks posed by the crop’s dependence on weather conditions necessitate improved prediction capabilities. The PEnsemble 4 model, developed with high accuracy, incorporates comprehensive datasets encompassing soil attributes, nutrient composition, weather conditions, and UAV-captured vegetation imagery. By employing a combination of Huber and M estimates, the PEnsemble 4 model effectively analyzes temporal patterns in vegetation indices, specifically CIre and NDRE, which serve as reliable indicators of canopy density and plant height. In addition, this research significantly contributes to precision agriculture by offering an efficient and sustainable alternative to conventional farming practices through precise yield predictions. Notably, the PEnsemble 4 model enables earlier estimation, advancing the timeline for yield prediction from the conventional day 100 in the R6 stage to day 79 in the R2 stage. This improvement enhances decision-making processes in farming operations. The remarkable accuracy rate of 91% underscores the importance of adopting a multifaceted data approach that harnesses IoT-derived environmental insights. Additionally, the PEnsemble 4 model extends its benefits beyond yield prediction, facilitating the detection of water and crop stress, as well as disease monitoring in broader agricultural contexts. Ultimately, the PEnsemble 4 model establishes a new standard in maize yield prediction, revolutionizing crop management and protection through the synergistic utilization of IoT and machine learning technologies.

Pump-as-turbines (PAT) have been widely used during the last decade as one of the most interesting technologies in the field of energy recovery. A large number of studies and papers have been published in which the performance of the pumps in the turbine operating regime are analysed. Since horizontal single stage centrifugal norm pumps are most commonly used as PATs, their performances are analysed in this paper. Most of the research was related to individual pump aggregates or smaller groups and to obtaining their performance curves in turbine random mode. In this work, extensive experimental, numerical and theoretical investigations are conducted to obtain complete dimensionless performance characteristics of the single stage centrifugal norm pumps operating as turbines. The main goal of this research was to form a simple analytical expression that will, for this type of aggregate, map the pump operating characteristic to the appropriate turbine operating regime. By using the expressions obtained and presented in the work, engineers are enabled to make the appropriate choice of pump aggregate for operation in the turbine random mode for potential locations. This can allow us to quickly make selection of potential locations and to carry out appropriate techno-economic analyses and analyses of possible energy savings.

This work focuses on identifying the most effective machine learning techniques and supervised learning models to precisely estimate power output from Photovoltaic (PV) plants. The performance of various regression models is analyzed by harnessing experimental data, including Random Forest, Support Vector Regression (SVR), Multi-layer Perceptron (MLP), Linear Regressor (LR), Gradient Boosting, and k-Nearest Neighbors (KNN). The methodology applied starts with meticulous data preprocessing steps aimed at ensuring dataset integrity. Following the preprocessing phase, which entails eliminating missing values and outliers using Isolation Feature selection based on a correlation threshold, is performed to identify relevant parameters for accurate prediction in PV systems. Subsequently, Isolation Forest is employed for outlier detection, followed by model training and evaluation using key performance metrics such as Root Mean Squared Error (RMSE), Normalized Root Mean Squared Error (NRMSE), Mean Absolute Error (MAE), and R-squared (R2). Among the array of models evaluated, Random Forest emerges as the top performer, highlighting promising results with an RMSE of 19.413, NRMSE of 0.048% and an R2 score of 0.968. Furthermore, the best-performing model is integrated into a MATLAB application for real-time predictions, thereby enhancing usability and accessibility for a wide range of applications in renewable energy.

Accurate forecasting of crop yields holds paramount importance in guiding decision-making processes related to breeding efforts. This study focused on the application of multi-sensor data fusion and machine learning algorithms based on unmanned aerial vehicles (UAVs) in wheat yield prediction. Five machine learning (ML) algorithms namely random forest (RF), partial least squares (PLS), ridge regression (RR), K-Nearest Neighbor (KNN) and eXtreme Gradient Boosting Decision Tree (XGboost) were utilized for multi-sensor data fusion, and three ensemble methods including the second-level ensemble methods (stacking and feature-weighted) and the third-level ensemble method (simple average) for wheat yield prediction. The 270 wheat hybrids were used as planting materials under full and limited irrigation treatments. A cost-effective multi-sensor UAV platform, equipped with red–green–blue (RGB), multispectral (MS), and thermal infrared (TIR) sensors, was utilized to gather remote sensing data. The results revealed that the XGboost algorithm exhibited outstanding performance in multi-sensor data fusion, with the RGB+MS+Texture+TIR combination demonstrating the highest fusion performance (R2=0.660, RMSE= 0.754). Compared with the single ML model, the employment of three ensemble methods significantly enhanced the prediction accuracy of wheat yield. Notably, the third-layer simple average ensemble method demonstrated superior performance (R2 = 0.733, RMSE= 0.668 t ha-1). It significantly outperformed both the second-layer ensemble methods of Stacking (R2= 0.668, RMSE= 0.673 t ha-1) and feature-weighted (R2= 0.667, RMSE= 0.674 t ha-1), thereby exhibiting superior predictive capabilities. This finding demonstrated that the third-layer ensemble method not only augments the predictive ability of the model but also fine-tuned the accuracy of wheat yield prediction through the employment of simple average ensemble learning. Consequently, it offers a novel perspective for crop yield prediction and breeding selection.

With the availability of wearable health monitoring sensor modules like 3-Lead Electrocardiogram (ECG), Pulse Oximeter (SpO2), Galvanic Skin Response (GSR), Hall effect sensor (for measuring Respiratory Rate), Blood Pressure and Temperature measuring and sensing elements, it has now become possible to device a composite health status monitoring kit that can measure vital signs and other physiological parameters pertaining to human health in real time. Traditionally, the physiological parameters along with vital signs related examination was possible only in a hospitalized or ambulatory environment, however due to advances in sensing and embedded system technology and miniaturization of data acquisition and processing elements health monitoring has become possible even when individuals remain engaged in their day to day activities at the convenience of space and location. The patients or individuals subject to monitoring may suffer from a traumatic experience due to their medical condition and may need emergent incidence response and the critical care team may have to prepare for the treatment only after the patient arrives, which often is too late, as in case of cardiac arrests or severe injuries. The research focused on real-time health status monitoring and trauma scoring using standard physiological parameters along with standard telemetry protocols to make the critical care team aware of an emergent situation and prepare for a medical emergency. Vital signs and physiological parameters (heart rate, temperature, respiratory rate, and blood pressure, SpO2) were measured in real time from human subjects non-invasively. In order to enable monitoring of the patients engaged in day to day activities, errors due to the motion were removed using stationary wavelet transform correction (correlation coefficient of 0.9 after correction) and signals from various sensors were denoised, filtered and were encoded in a format suitable for further data analysis. A composite sensor kit capable of monitoring vital signs and physiological parameters can be very useful in incident response when an individual undergoes a traumatic experience related to stroke, cardiac arrest, fits or even injury, as along with monitoring information the kit can calculate scores related to trauma like the Injury Severity Score (ISS), National Early Warning Signs (NEWS), Revised Trauma Score (RTS). Trauma Injury Severity Score (TRISS), Probability of Survival (Ps) score. An open access database of vital signs and physiological parameters from Physionet, MIMIC 2 Numerics (mimicdb/numerics) database was used to calculate NEWS and RTS and to generate correlation and regression models using the vital signs/physiological parameters for a clinical class of patients with respiratory failure and admitted to Intensive Care Unit (ICU). NEWS and RTS scores showed no significant correlation (r = 0.25, p<0.001) amongst themselves, however together NEWS and RTS showed significant correlation with Ps (blunt) (r = 0.70, p<0.001). RTS and Ps (blunt) scores showed some correlation (r = 0.63, p<0.001) and NEWS score showed significant correlation (r = 0.79, p<0.001) with Ps (blunt) scores. Furthermore, since individuals have to be monitored regardless of location, these kits have to have a built-in capability to locate the individual so that the incident response team can locate the individual based on Global Positioning System coordinates (GPS). A Quantum GIS (Geographical Information System) application using real-time GPS coordinates (OpenStreetMap coordinates) was used to calculate the shortest path using QGIS Network Analysis tool to demonstrate the calculation of shortest path and direction to locate the nearest service provider in shortest time. Along with locating the nearest healthcare service provider, it would help if the critical care team could be made aware of the physiological parameters and trauma scores using standard protocols accepted across the globe. The physiological parameters from the sensors along with the calculated trauma scores were encoded according to a standard Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT) coding system and International Code of Diseases (ICD) codes and the trauma information was logged to Electronic Health Records (EHR) using Fast Health Interoperability Resources (FHIR) servers. FHIR servers provided interoperable web services to log the event information in real time. It could be concluded that analytical models trained on existing datasets can help in analyzing a traumatic experience or an injury and the information can be logged using a standard telemetry protocol as a telemedicine initiative. These scores enable the healthcare service providers to estimate the extent of trauma and prepare for medical emergency procedures and find applications in general and military healthcare.

Accurately predicting the distance an object will travel to its destination is very important in various sports. Acceleration sensors as a means of real-time monitoring are increasingly gaining increasing attention in sports. Due to the low energy output and power density of Triboelectric Nanogenerators (TENGs), recent efforts have focused on developing various acceleration sensors. However, these sensors suffer from significant drawbacks of large size, complexity, high power input requirements, and high cost. Here, we described a portable and cost-effective real-time refreshable strategy design comprising a series of individually addressable and controllable units based on TENGs embedded in a flexible substrate. This results in a highly sensitive, low-cost, and self-powered acceleration sensor. Putting, which accounts for nearly half of the strokes played, is obviously an important component of the golf game. The developed acceleration sensor has an accuracy controlled within 5 %. The initial velocity and acceleration of the forward movement of a rolling golf ball after it is hit by a putter can be displayed, and the stopping distance quickly calculated and predicted in about 7 seconds. This research demonstrates the application of the portable TENG-based acceleration sensor, while paving the way for designing portable, cost-effective, scalable, and harmless ubiquitous self-powered acceleration sensors.

The burden of hypertension remains unacceptably high globally, particularly in low- and middle-income countries (LMICs). Workplace offer enormous potential as an idea setting for early detection and treatment of hypertension among the working class. Analysis of such a Workplace Screening Programme can reveal information about its potential impact. Machine learning techniques such as k-Means Clustering are untapped tools for such analyses. We set out to deploy this tool for the analysis of our university annual medical screening of workforce for hypertension. An anonymized dataset containing the demography and blood pressure measurements values obtained from staffs of different departments/units in an academic institution was obtained. The total number of samples or data points are 1, 723 in which the input dataset contains six features, including year category (2018, 2019, 2021,2022), Department/Unit (academic and non-academic), gender (male and female), while the target output is the blood pressure status (low, normal and high) respectively. Analysis of the dataset was carried out using machine learning techniques. In this retrospective analysis, it was observed that the mean age for this working class is 42 years old. Similarly, it was discovered that hypertension was prevalent among members of staff above the age of 40 irrespective of their gender or professional category (academic or non-academic). The analysis also revealed that there was a steady decline in the prevalence of hypertension from 2018 to 2022. From the research, it is evident that the adoption of machine learning techniques for periodic analyses of workplace health status screening initiative (especially for hypertension) is effective, feasible, and sustainable to diagnose and control hypertension among the working class.

The intense motion of a ship can greatly impacts the comfort of crew members and the safety of the vessel. Therefore, accurately estimating and predicting ship attitudes has become an important issue. This paper introduces the latest development in functional deep learning model called DeepOnet. It takes wave height as input and ship motion as output, using a cause-to-result prediction approach. The modeling data used in this study is sourced from publicly available experimental data from the Iowa Institute of Hydraulic Research. Firstly, parameters system tuning was conducted for the neural network's hyperparameters to determine the appropriate combination of parameters. Secondly, the DeepOnet model for wave height and multi-degree-of-freedom motion was established, and the influence of increasing time steps on prediction accuracy was examined. Finally, a comparison was made between the DeepOnet model and the classical time series model LSTM. It was found that the DeepOnet model had a 10-fold improvement in accuracy for roll and heave attitudes. Moreover, as the forecast duration increased, the advantage of DeepOnet showed a trend of strengthening. As a functional prediction model, DeepOnet provides a new promising tool for very short-term prediction of ship motion.

Generalized Bayesian (GB) is a Bayesian approach based on the learning rate parameter (LRP) () as a fraction of the power of the likelihood function. In this paper, we consider the GB method to perform inference studies for a class of exponential distributions. Generalized Bayesian estimators (GBE) and generalized empirical Bayesian estimators (GEBE) for the parameters of the considered distributions were obtained based on the censored type II samples. In addition, generalized Bayesian prediction (GBP) and generalized empirical Bayesian prediction (GEBP) were considered using a one-sample prediction scheme. Monte Carlo simulations were performed to compare the performance of the GBE and GEBE estimation results and the GBP and GEBP prediction results for different values of the LRP.

The focus was on developing machine learning models to predict the IC50 values of the compound OTX015 using gene expression levels of cancer cell lines. Through regression-based machine learning models, particularly the SVM model, trained on pre-laboratory data, consistent and generalizable performance with low error scores was achieved. These models underwent enhancement via hyperparameter optimization and were tested on validation data. The results indicate the utility of machine learning in drug discovery processes and personalized medicine, offering rapid and cost-effective predictions of IC50 values. However, for enhanced reliability, further model development, data gathering, and evaluation with diverse compounds are recommended. In conclusion, this research demonstrates the potential of machine learning approaches to optimize experimental processes, reduce costs, and contribute to personalized treatments in healthcare by accurately predicting compound responses.

Background and Objectives: Peripheral vertigo is one of the most common symptoms for which patients are seen by a neurologist in the emergency room. Symptoms of peripheral vertigo can range from lightheadedness to an illusion of spinning. On average, vertigo is diagnosed for older patients as its predicting factors from medical history are yet to be determined. The objective of the study was to predict peripheral vertigo based on medical history and risk factors. Materials and Methods: A prospective case-control study at the Neurology Department of Lithuanian University Hospital was conducted. 71 patients diagnosed with vertigo and 43 controls was included. They completed questionnaires and underwent evaluation by neurologists or otolaryngologists, with statistical analysis performed using IBM SPSS Statistics. Results: 58% of vertigo patients were diagnosed with peripheral vertigo, with significant predictors including age (&gt;60), motion sickness, height intolerance, gastroesophageal reflux disease and dyslipidemia, leading to the development of a risk assessment table for the peripheral vertigo prediction. Conclusions: This study suggest that early identification of these predictors could enhance peripheral vertigo management, while further research with larger cohorts is needed to validate and expand upon these findings, emphasizing the importance of considering medical history and risk factors for predicting peripheral vertigo and improving patient care.

Background: The high global prevalence of prediabetes requires its early identification. Amino acids have emerged as potential predictors of prediabetes. This study aims to investigate the association between BCAAs and prediabetes in the Kazakh population. Materials and Methods: In this case-control study, plasma BCAAs levels were measured using the Trace GC 1310 gas chromatography system coupled with the TSQ 8000 triple quadrupole mass spectrometer (Thermo Scientific, Austin, TX, USA) followed by silylation with the BSTFA + 1% TMCS derivatization method. Biochemical parameters, including total cholesterol, HDL-C, LDL-C, triglycerides, fasting glucose, HbA1c, and creatinine, were assessed for each participant. Anthropometric and physical examinations, including blood pressure, heart rate measurements, and family history collection, were conducted by trained professionals. Results: The final analysis included data from 112 Kazakhs with prediabetes and 55 without prediabetes, aged 36-65 years. Of the thirteen AAs analyzed, only alanine showed a significant association with prediabetes risk. Our findings revealed an inverse relationship between alanine and aspartic acid levels, and direct association of lysine and prediabetes in Kazakh ethnicity. Conclusion: Lower plasma level of alanine and aspartic acid, and higher level of lysine may serve as predictive biomarkers for prediabetes in the Kazakh population. This research is funded by the Science Committee of the Ministry of Education and Science of the Republic of Kazakhstan (grant AP14871855).

Recently, a large number of Transformer-based solutions have emerged for the trajectory prediction task, but there are shortcomings in the effectiveness of Transformers in trajectory prediction. Specifically, while position encoding preserves some of the ordering information, the self-attention mechanism at the core of the Transformer has its alignment invariance that leads to the loss of temporal information, which is crucial for trajectory prediction. For this reason, we design a simple and efficient strategy for temporal information extraction and prediction of trajectory sequences using the self-attention mechanism and linear layers. Experimental results show that the strategy we designed can effectively combine the advantages of the linear layer and self-attention mechanisms, compensating for the shortcomings of the Transformer. Additionally, we conducted an empirical study to explore the effectiveness of the linear layer and sparse self-attention mechanisms in trajectory prediction.

Froth flotation, a widely used mineral beneficiation technique, generates substantial volumes of data, offering the opportunity to extract valuable insights from these data for production line analysis. The quality of flotation data is critical to designing accurate prediction models and process optimisation. Unfortunately, industrial flotation data are often compromised by quality issues such as outliers that can produce misleading or erroneous analytical results. A general approach is to preprocess the data by replacing or imputing outliers with data values that have no connection with the real state of the process. However, this does not resolve the effect of outliers, especially those that deviate from normal trends. Outliers often occur across multiple variables and their values may occur in normal observation ranges, making their detection challenging. An unresolved challenge in outlier detection is how far is far enough for an observation to be considered an outlier. Existing methods rely on domain experts’ knowledge which is difficult to apply when experts encounter large volumes of data with complex relationships. In this paper, we propose an approach to conduct outlier analysis on a flotation dataset. The approach uses a 2σ rule as the threshold to find quasi-outliers and multiple machine learning (ML) algorithms including k-Nearest Neighbour (kNN), Local Outlier Factor (LOF), and Isolation Forest (ISF) to identify true outliers. The approach then analyses the mutual coverage between quasi-outliers and outliers from the ML algorithms to identify the most effective outlier detection algorithm. We found that the outliers by kNN cover outliers of other methods. We use the experimental results to show that outliers affect model prediction accuracy and excluding outliers from training data can reduce the average prediction errors.

This study presents a novel predictive model to address the churn problem in the motor insurance sector using a dual-phase framework. The first phase employs a cave-degree perturbation technique for effective feature selection, while the second phase applies the Magnetic Force Perturbation Technique (MFPT) to optimize the search process and avoid local optima traps. Two metaheuristics are proposed: the Adaptive Random Forest-Assisted Large Neighborhood Feature Optimizer (ARALFO) and the Adaptive Random Forest Particle Swarm Optimizer (ARFPSO) to enhance churn prediction accuracy. The model was evaluated on two real-world motor insurance datasets, achieving a 95% accuracy rate and outperforming state-of-the-art algorithms. An ablation study confirmed the significant impact of the cave-degree and MFPT techniques in boosting predictive performance.

Due to the increasing use of computer equipment, institutions and companies face challenges, such as sensitive data leaks and the spread of hate speech, which have severe consequences for organizations and their employees. Addressing these challenges is essential to avoid financial losses, reputational damage, and impacts on the psychological health of those involved. This paper presents a solution based on microservices for monitoring computers used by employees in organizations, including capturing information from the equipment using spyware techniques and a web application for managing alerts. The solution seeks to detect data leaks, suspicious behaviour, and hate speech. The results of the evaluation indicate that the proposed solution has an efficient data capture time and can identify unwanted behaviour in a short period. The solution also includes applying prediction models to detect hate speech, achieving an average accuracy of approximately 87%. The performance, scalability, and security evaluation demonstrate that the solution is suitable for dealing with data leakage and hate speech challenges in the corporate environment.

Previous reviews have investigated machine learning (ML) models used to predict the risk of developing preeclampsia but have not described how the ML models are intended to be deployed throughout pregnancy or feature performance. The aim of this study is to provide an overview of the existing ML models and their intended deployment patterns and performance along with identified features of high importance. This review used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines. PubMed, Engineering Village, and the Association for Computing Machinery were searched between January and February 2024. A total of 86 studies were found of which 14 were included. Out of 12 studies, eight showed the intent to use the ML model as a single-use, two intended a dual-use, and two intended multiple-use. A total of seven studies listed the features of the highest importance. Systolic and diastolic blood pressure were listed along with mean arterial pressure to be of high importance. Out of four studies intending to use the ML model more than a single-use, three of them were conducted in the years 2023 and 2024, whereas the remaining study is from 2011. No ML model emerged as superior across the subgroups of PE. Utilizing body mass index and either mean arterial pressure or diastolic blood pressure and systolic blood pressure may benefit the performance. The deployment patterns are mainly single use being within the gestation weeks 11+0 to 14+1.

Forest fires can occur suddenly and have significant environmental, economic, and social consequences. Timely and accurate evaluation and prediction of their progression, particularly the spread speed in difficult-to-access areas, are essential for emergency management departments to proactively implement prevention strategies and scientifically extinguish fires. This paper provides a comprehensive analysis of advanced technologies for predicting forest fire spread in China and globally. Incorporating remote sensing (RS) technology and forest fire science as the theoretical foundation, and utilizing the Wang Zhengfei forest fire spread model as the technical framework, this study constructs a forest fire spread model based on remote sensing interpretation. The model optimizes the method for acquiring parameters and enhances algorithm accuracy. By considering regional landforms (ridge lines, valley lines, slopes) and vegetation coverage, this paper establishes visual interpretation markers for identifying hotspots within the spread model. Utilizing statistical data from pixels within the fire line zone transforms the methodology for predicting forest fire spread speed, resulting in greater accuracy compared to conventional fixed-point predictions. Finally, the model was applied to the case of a forest fire in Mianning County, Sichuan Province, China and verified using high-time resolution mid-infrared image data and previous research findings. The results demonstrate that the predicted fire spread area from this RS-enabled model is consistent with both high-time resolution geostationary satellite data and previous research outcomes, indicating high reliability. This model can provide crucial fire spread information to relevant emergency departments, enabling effective preemptive measures and scientific firefighting strategies.

Market crises pose significant challenges for businesses, emphasizing the importance of effective crisis management strategies. Central to these strategies is the ability to identify and retain loyal customers, who often serve as the bedrock of stability during tumultuous times. This paper investigates the application of deep meta-learning analysis to predict loyal customers as a cornerstone of market crisis management. Drawing upon an extensive literature review, the study explores previous research on market crises, customer loyalty, and the evolution of deep learning and meta-learning in crisis management contexts. Methodologically, the paper outlines data collection, model development, and evaluation procedures tailored for deep meta-learning-based customer prediction. In results, the overall accuracy of model 85%, a precision 0.88, recall 0.82, and F1-score 0.85 were obtained. The analysis demonstrates the effectiveness of deep meta-learning models in accurately identifying loyal customers during market crises, offering insights into their performance and applicability compared to traditional methods. Practical implications include potential applications in crisis management for businesses and considerations for real-world implementation.

This study investigates student performance with the aim to forecast students' academic outcomes using data analytics and machine learning techniques. There is a big drop out per cent especially in the technological study programs at the universities, however, focusing on the successful study process there is important to analyze and to predict some risks on students’ to assure low dropout percent. While Student Performance Prediction (SPP) has potential benefits, such as personalized learning and early interventions, several challenges make the task complex in relation to (1) data quality and availability and (2) incomplete and inconsistent data. Predicting performance requires a range of different data types: academic records, attendance, and engagement in class, socio-economic background, and even behavioral factors. Moreover, according to the fourth Sustainable Development Goal (SDG) we focus on the quality in education.This paper presents a case study of data mining method for SPP by using classification, regression, and clustering are generally used in education to predict student’s performance which is important to control drop out of studies percent. The case presented is to predict risks and to assure academic success and quality based on the CRISP-DM data mining.

Abstract Background: Numerous studies have demonstrated that the amalgamation of populations belonging to the same breed or closely related breeds leads to enhanced accuracies in genomic predictions (GP). Extensive experimentation with diverse Bayesian and Genome-enabled best linear unbiased prediction (GBLUP) models has been conducted to explore multi-breed genomic selection (GS) in livestock, ultimately establishing they as successful approaches for predicting genomic estimated breeding value (GEBV). This study aimed to examine the efficacy of BayesR and GBLUP model with different weighted genomic relationship matrices (GRM) in making genomic predictions for three distinct beef cattle breeds. Subsequently, we conducted a comparative analysis of the predictive accuracy pertaining to various marker densities and genetic correlations across three distinct beef cattle breeds. This investigation aimed to identify the optimal approach for enhancing the predictive accuracy of multi-breed genomic selection in beef cattle. Results：Genetic relationship matrices revealed moderate similarities between YL and the other breeds, with a striking genetic similarity of 0.87 between WG and HX. In HX cattle, BayesR demonstrated an enhancement in prediction accuracy, achieving 0.52 with HD and 0.46 with WGS, a marked improvement over 0.41 with HD and 0.42 with WGS in GBLUP. In WG and YL breeds, both methods showed comparable accuracies with HD, but BayesR slightly outperformed GBLUP with WGS. Further, multi-breed GS analysis indicated that BayesR consistently surpassed GBLUP in prediction accuracy, particularly with WGS data. For instance, in a combined HX and WG reference population, BayesR achieved a superior accuracy of 0.53 with WGS in HX cattle, a significant enhancement over GBLUP models. The study also underscores the advantage of incorporating multiple breeds in the reference population, which improved prediction accuracy, underscoring the value of broad-based genomic selection strategies. Conclusion: The results show that accuracy of multi-breed genomic predictions was higher with BayesR than with GBLUP, especially for the distantly genetic relationship between reference and validation breeds. Further improvements of multi-breed accuracy of genomic predictions could be achieved by increasing the density of the SNP marker. These findings underscore that BayesR providing a substantial improvement in genomic prediction and the importance of considering genetic relationships in the development of GS strategies for multi-breed cattle populations. Further research is warranted to optimize GRM construction and to explore alternative models for genomic prediction across breeds.

This paper describes a system that is used to gather data from Smart Home sensors measuring energy consumption, analyze and predict future consumption by using machine learning algorithm for prediction. It focuses on the architecture of the system as well as the need for such system to exist in practice – why the consumption should be measured at all and how that measurement can be put to good use for achieving energy efficiency.

Falls are a major public health problem among older adults, therefore predicting the risk of having falls in the near future is of great importance for health and social systems worldwide. Nowadays, prospective fall risk assessment relies on clinical and functional mobility assessment tools, such as the Timed Up and Go (TUG) test. Recently, wearable inertial measurement unit (IMU) sensors measurements have been proposed for fall detection. We hypothesize that the IMU readings captured during TUG test realizations can provide prospective fall risk prediction. In this study, analysis by deep learning convolutional neural networks (CNN) and recurrent neural networks (RNN) were used for fall prediction based on features extracted from IMU data acquired during TUG test realizations. Data is obtained from a cohort of 106 older adults wear-ing a wireless inertial sensor with a sampling frequency of 100 Hz while performing the TUG test. Prospective fall incidence was obtained in a six-month follow-up period and used as the ground truth for the supervised training and validations of the deep learning and competing machine learning approaches. Further data collection could lead to potential fall risk biomarker. A repeated hold out cross-validation process using 75 subjects for training and 31 subjects for testing was carried out. Best results were achieved by a bidirectional long short-term memory (BLSTM), obtaining an accuracy of 0.83 and AUC of 0.73 with good sensitivity and specificity values.

Cuproptosis, a copper-dependent cellular death mechanism, is typically overlooked in glioblastoma diagnosis. Lipoylation is needed for cuproptosis, and FDX1 controls this process. Cuproptosis in prognostic models may drive cancer treatment. This study evaluated cuproptosis and glioblastoma cell proliferation. The Cancer Genome Atlas provided annotated clinical, genetic mutation, and RNA sequencing data for the TCGA_GBM and TCGA_LGG cohorts. Patients with gliomas were randomly allocated to the validation or training cohort. Least absolute shrinkage and selection operator (LASSO) and multivariate Cox regression models were utilized to evaluate which model best predicted prognosis in the training cohort. The models' independent predictive power was evaluated throughout the cohort. A previous study revealed 19 genes related to ferroptosis. LncRNAs associated with cuproptosis were identified by coexpression analysis. Cox discovered 17 cuproptosis-associated lncRNAs and established a predictive model. The median risk score classified patients as high- or low-risk. K‒M survival analysis demonstrated significant differences in overall survival among risk categories. Principal component analysis (PCA) and receiver operating characteristic (ROC) curve analysis were used to test the model’s predictive power. Univariate and multivariate Cox regression analyses revealed risk score-related independent prognostic factors. Multivariate Cox regression analysis was used to construct a nomogram for marker-based prognosis. The risk category affected the tumour mutation rate. High-risk glioma patients benefit from immunotherapy. Glioma drug sensitivity was also substantially linked with the risk score. The expression of 17 cuproptosis-related long noncoding RNAs (lncRNAs) may assist in the stratification of glioma patient prognosis, molecular characteristics, cell cycle gene regulation pathways, the TME, and clinicopathological aspects. Our clinical sample and database analysis revealed that cuproptosis influences glioma prognosis and may guide therapy.

Background: Alzheimer's disease (AD) is a leading cause of dementia, significantly influenced by the Apolipoprotein E4 (APOE4) gene and gender. This study aims to use machine learning (ML) algorithms to predict brain age and assess AD risk by considering the effects of APOE4 genotype and gender. Methods: We collected brain volumetric MRI data and medical records from 1100 cognitively unimpaired individuals and 602 AD patients. We applied three ML regression models—XGBoost, Random Forest (RF), and Linear Regression (LR)—to predict brain age. Additionally, we introduced two novel metrics, Brain Age Difference (BAD) and Integrated Difference (ID), to evaluate model performance and analyze the influence of APOE4 genotype and gender on brain aging. Results: AD patients displayed significantly older brain ages compared to their chronological ages, with BADs ranging from 6.5 to 10 years. The RF model outperformed both XGBoost and LR in terms of accuracy, delivering higher ID values and more precise predictions. Comparing APOE4 carriers with non-carriers, the models showed enhanced ID values and consistent brain age predictions, improving overall performance. Gender-specific analyses indicated slight enhancements, with models performing equally well on both genders. It indicates that APOE4 may be a more robust predictor of brain age than gender. Conclusion: Robust ML models for brain age prediction can be pivotal in the early detection of AD risk via MRI brain structural imaging, especially for APOE4 carriers. Such early identification may facilitate timely preventive interventions for AD.

Proton Exchange Membrane Fuel Cell (PEMFC) is a fast-developing battery technology, and the key to its reliability and lifespan improvement lies in the accurate assessment of durability. However, the degradation mechanism of PEMFC is hard to determine and its internal parameters are highly coupled. Thus, the development of the more accurate life prediction model that meets the actual scenarios is urgent to investigate. To solve this problem, a multi-feature fusion life prediction method based on Temporal Convolutional Network-Gated Recurrent Unit (TCN-GRU) is proposed. A TCN algorithm is used as the prediction base model, and two GRU modules are included to the model to strengthen the model expression ability and improve its predictive accuracy. Two widely recognized datasets and two operating conditions are utilized for model training and prediction, respectively. Comparisons are made with single-feature parameter models in terms of Root Mean Square Error (RMSE) and Determination Coefficient (R2). The results show that the prediction accuracy of the TCN-GRU multi-feature fusion model is higher than that of the single-feature models in terms of stability and anti-interference under both operating conditions. Furthermore, with the increase of input feature parameters, the TCN-GRU model is closer to the real value, which proves once again that the proposed model can meet the accuracy requirements of the life prediction of PEMFC.

The article evaluates the use of machine learning methods to predict valve plate failures in hydraulic pumps. To conduct this assessment, a laboratory setup was developed that allowed the creation of a training dataset containing both the normal operating state of the pump and the operating state with three different valve plate damages. Five different predictive models were evaluated, including three composite models based on decision trees: Random Forest, Gradient-Boosted Trees, and Rotation Forest, as well as the kNN algorithm and a neural network. The analysis showed that neural networks achieved the highest prediction accuracy, enabling a prediction accuracy level of 89%. The kNN algorithm ranked second, and tree-based algorithms performed 4% worse than the neural network. Additionally, the attribute importance analysis revealed that leak flow, pressure output together with output flow, are the most important parameters for accurate prediction.

The AUC-ROC is a widespread measure to assess the performance of a binary classification model across various discrimination thresholds. Yet, it is not apt for unbalanced class problems and is misleading for early retrieval. For instance, link prediction in complex networks is an unbalanced early retrieval problem, whose goal is to offer a ranking of the nonobserved network links, prioritizing a small cohort of positive links (for which we are sure the labels are reliable) on top of a list largely populated by unlabeled links (for which the labels are uncertain). Differently from binary classification, here the evaluation focuses on how the predictor prioritizes the positive class, because the negative class does not exist and is replaced by an unlabeled class. For decades, scholars have been investigating the necessity to correct and to generalize the AUC-ROC to work for both unbalanced classification and early retrieval evaluation, this is requested in many applied domains of computational science. Here we propose the area under the magnified ROC (AUC-mROC), a new measure that adjusts the standard AUC-ROC to work for unbalanced early retrieval problems such as link prediction. Finally, we introduce the area under the generalized ROC (AUC-gROC), which unifies both AUC-mROC and AUC-ROC to provide a universal and reliable evaluation measure that can work for both classification and early retrieval problems, regardless of class proportion.This discovery represents a critical achievement, culminating in success after decades of contentious research. Its solution promises to significantly impact various domains within applied computational science.

The prediction of tertiary RNA structures is significant to the field of medicine (e.g. mRNA vaccines, genome editing), and the exploration of viral transcripts. Though many RNA folding software exist, few studies have condensed their locus of attention solely to viral pseudoknotted RNA. These regulatory pseudoknots play a role in genome replication, gene expression, and protein synthesis. This study explores five RNA folding engines that compute either the minimum free energy (MFE) or the maximum expected accuracy (MEA). These folding engines were tested against 26 experimentally derived short pseudoknotted sequences (20-150nt) using metrics that are commonly applied to software prediction accuracy (e.g. F1 scoring, PPV). This paper reports higher accuracy RNA prediction engines (pKiss) when compared to previous iterations of the software, and when compared to older folding engines. They show that MEA folding software does not always outperform MFE folding software in prediction accuracy when assessed with metrics such as percent error, sensitivity, PPV, and F1 scoring when applied to viral pseudoknotted RNA. Moreover, the results suggest that thermodynamic model parameters will not ensure accuracy if auxiliary parameters such as Mg2+ binding, dangling end options, and H-type penalties are not applied. The observations reported in this paper highlight the quality between different ab initio prediction methods while enforcing the idea that a better understanding of intracellular thermodynamics is necessary for a more efficacious screening of RNAs.

Longitudinal cutting is a most common process in steel structure manufacturing, and the man-hours of the process provide an important basis for enterprises to generate production schedules.However, currently the man-hours in factories are mainly estimated by experts, and the accuracy of this method is relatively low.In this study,we propose a system that predicts man-hours with history data in the manufacturing process and that can be applied in practical structural steel fabrication.The system addresses the data inconsistency problem by one-hot encoding and data normalization techniques,Pearson correlation coefficient for feature selection,and the Random Forest Regression(RFR) for prediction.Compared with the other three Machine Learning(ML) algorithms, the Random Forest algorithm has the best performance.The results demonstrate that the proposed system outperforms the conventional approach and has better forecast accuracy, so that it is suitable for man-hours prediction.

Context: CYP21A2 deficiency represents 95% of congenital adrenal hyperplasia cases (CAH), a group of genetic disorders that affect steroid biosynthesis. The genetic and functional analysis provides critical tools to elucidate complex CAH cases. One of the most accessible tools to infer the pathogenicity of new variants is in silico prediction. Objective: Analyze the performance of in silico prediction tools to categorize missense single nucleotide variants (SNVs) of the CYP21A2. Methods: SNVs of the CYP21A2 characterized in vitro by functional assays were selected to assess the performance of online single and meta predictors. SNVs were tested separately or in combination with the related phenotype (severe or mild CAH form). In total, 103 SNVs of the CYP21A2 (90 pathogenic and 13 neutral) were used to test the performance of 13 single-predictors and four meta-predictors. Results: SNVs associated with the severe phenotypes were well categorized by all tools, with an accuracy between 0.69 (PredictSNP2) and 0.97 (CADD), and Matthews' correlation coefficient (MCC) between 0.49 (PoredicSNP2) and 0.90 (CADD). However, SNVs related to the mild phenotype had more variation, with the accuracy between 0.47 (S3Ds&GO and MAPP) and 0.88 (CADD), and MCC between 0.18 (MAPP) and 0.71 (CADD). Conclusion: From our analysis, we identified four predictors of CYP21A2 pathogenicity with good performance. These results can be used for future analysis to infer the impact of uncharacterized SNVs' in CYP21A2.

Link prediction is a significant field in network science, which focuses on predicting the probability of the existence or formation of a link between nodes in a social network based on currently observed connections. The effectiveness of traditional algorithms can vary depending on the type of network, making some methods more suitable than others for specific scenarios. Recently, several efficient link prediction algorithms have been developed, demonstrating robust results in both prediction accuracy and interpretability. However, existing research has not clearly established the relationship between network characteristics and link creation mechanisms for community influence analysis and anomaly detection. The ability to predict complex networks with diverse features still requires further investigation. In light of this, we introduce a novel framework designed to combine the best features of different link prediction algorithms when applied to the network, with the aim of achieving more reliable predictions about how networks will evolve. According to the proposed framework, we first focus on the feature extraction stage. During this phase, we systematically identify and extract a comprehensive set of features from the network before moving onto the classification phase. Here, we utilize state-of-the-art ensemble learning models to assess and classify potential links within the network. By training our machine learning models on the extracted features, we can effectively predict whether a particular link is likely to form (positive link) or unlikely to form (negative link). The ML models were trained and evaluated using two datasets: Twitch and Facebook. Results: Additionally, we assessed their performance on these datasets by conducting specific preprocessing and hyperparameter tuning steps. The final prediction model achieves AUC values between 94% and 99.3%. This research contributes significantly to efforts aimed at enhancing link prediction in dynamic socisal network contexts, providing valuable insights into the effectiveness of different ML algorithms in predicting future connections and enhancing our understanding of network dynamics.

Credit card payment platforms are increasingly used for e-commerce activities. Credit cards are payment cards issued to individuals so they can purchase products and services based on their accumulated debt. Since credit cards are becoming very popular and widely used, the number of related fraud cases is likewise increasing. Whereas, there are large numbers of credit card transactions daily; thus, it becomes complex to differentiate between fraudulent and non-fraudulent transactions. Accordingly, different machine learning (ML) tools have been deployed in the literature to filter credit card transactions to prevent cardholders and financial institutions from losing money. In this article, the ensemble hidden Markov model (EHMM) approach is deployed to predict credit card fraud. EHMM is a popular and flexible ML tool that can easily model randomly changing datasets. Yet, the performance of the EHMM solely depends on the adopted feature extraction technique. The more reliable the feature extraction technique, the better the performance of the EHMM. In this vein, this article analyses two feature extraction techniques that can be combined with the EHMM for the prediction of credit card fraud. First, the principal component analysis (PCA) feature extraction techniques are combined with the EHMM to effectively predict credit card fraud. Yet, the PCA increases the computational time complexity of the EHMM. Therefore, this article adapts some statistical features to reduce the computational time complexity imposed on the EHMM. These robust but simple statistical features termed MRE; Mean, Relative Amplitude, and Entropy, are merged to form a feature vector that can be combined with the EHMM to effectively predict credit card frauds. The performance of the PCA-EHMM and MRE-EHMM are evaluated using the credit card transactions dataset of European cardholders gathered within two days in September 2013. The results were documented using different performance metrics such as recall/sensitivity, specificity, precision, and F1-score. The findings of this article will offer solutions to the loss experienced by cardholders and financial institutions as a result of online banking which requires credit card details.

Predicting anomalies in manufacturing assembly lines is crucial for reducing time and labor costs and improving processes. For instance, in rocket assembly, premature part failures can lead to significant financial losses and labor inefficiencies. With the abundance of sensor data in the Industry 4.0 era, machine learning (ML) offers potential for early anomaly detection. However, current ML methods for anomaly prediction have limitations, with F1-measure scores of only 50% and 66% for prediction and detection, respectively. This is due to challenges like the rarity of anomalous events, scarcity of high-fidelity simulation data (actual data is expensive), and the complex relationships between anomalies not easily captured by traditional ML approaches. Specifically, these challenges relate to two dimensions of anomaly prediction: predicting when anomalies will occur and understanding the dependencies between them. This paper introduces a new method called Robust and Interpretable 2D Anomaly Prediction (RI2AP) designed to address both dimensions effectively. RI2AP is demonstrated on a rocket assembly simulation, showing up to a 30-point improvement in F1 measure compared to current ML methods. This highlights its potential to enhance automated anomaly prediction in manufacturing. Additionally, RI2AP includes a novel interpretation mechanism inspired by a causal-influence framework, providing domain experts with valuable insights into sensor readings and their impact on predictions. Finally, the RI2AP model is deployed in a real manufacturing setting for assembling rocket parts. Results and insights from this deployment demonstrate the promise of RI2AP for anomaly prediction in manufacturing assembly pipelines.

Accurate measurement of systemic financial risk is critical to maintaining the stability of financial markets. Taking China as the subject of investigation, the Chinese Financial Stress Index (CFSI) indicator system was con-structed by integrating six dimensions and employing Gray Relation Analysis (GRA) for dimensionality reduction of the indicators. The CFSI was derived using the Attribute Hierarchy Model (AHM) method with the Criteria Importance Through the Intercriteria Correlation (CRITIC) method, and an Improved Gravitational Search Algorithm (IGSA) optimized Radial Basis Function Neural Network (RBFNN) was proposed for out-of-sample prediction of CFSI trends from 2024 to 2026. By analyzing the trend of financial pressure indicators, the relationship between financial pressure and economic activity can be effectively identified. The research findings indicate that: (1) The CFSI is capable of accurately reflecting the current financial stress situation in China; (2) The IGSA-RBFNN demonstrates good robustness and generalization capabilities, predicting that the CFSI index will reach a peak value of 0.543 by the end of 2024, and there exists a regular pattern of stress rebound towards the end of each year. The novel methodology benefits policymakers and regulatory authorities to formulate preventive measures and risk management by identifying potential risks and vulnerabilities in advance.

In the last decade, a higher level of reliability became a compulsory demand when it comes to modern DC-DC converters. This work addresses the main reliability metrics: the failure rate λλ and MTBF of an output capacitor bank used within a high current low voltage buck converter due to many studies have shown that the output capacitor bank was demonstrated being the most critical component within the converter. Many authors treated this issue, usually by doing reliability predictions. The majority of the papers use only one specific Standard Prediction to solve the problem. Herein calculation was done using both the older standard MIL-HDBK-217 and the latest one Telcordia SR-332, providing a benchmark comparison between the two which is a helpful tool for the output capacitor selection in the early stage design. Military standard was well accepted for decades in order to reliability prediction even on industrial electronics and is still used today under a critical manner because no more update after the latest version MIL-HDBK-217F - Notice 2 released in 1995. Since then, newer prediction standards had appeared in the electronics reliability market. Over time, this standard was mostly used but it does not accurately model the reliability because lack of taking account of mission profile. The above-mentioned newer standard – i.e., Telcordia SR-332 is trying to compensate also the lack of the newest component technology in the older standard (which is the first standard released on the market) supplying useful design data for design engineers who use the so-called “design with the reliability in mind” concept. Within the paper were established the environmental condition for the passive components by means of a PoL (Point of load) buck converter that is used for both calculation methods. The influence of temperature and several specific concepts like reference conditions, operating conditions, ripple, and internal self-heating were taking account in order to display the results. The temperature for the capacitor’s capsule needed in π_T stress factor calculation was derived by PSPICE simulation. High fidelity and dedicated SPICE models provided by the manufacturer were used for MOSFETs, polymer electrolytic, and MLCC capacitors that compose the converter.

Precision medicine (PM), also termed stratified, individualised, targeted or personalised medicine, embraces a rapidly expanding area of research, knowledge, and practice. It brings together two emerging health technologies to deliver better individualised care: the many “-omics” arising from increased capacity to understand the human genome; and “big data” and data analytics including Artificial Intelligence (AI). PM has the potential to transform an individual��s health, moving from population-based disease prevention to more personalised management. There is however a tension between the two, with a real risk that this will exacerbate health inequalities and divert funds and attention from basic healthcare requirements leading to worse health outcomes for many. All areas of medicine should consider how this will affect their practice, with PM now strongly encouraged and supported by government initiatives and research funding. In this review we discuss examples of PM in current practice and its emerging applications in primary care, such as clinical prediction tools that incorporate genomic markers and pharmacogenomic testing. We look towards potential future applications and consider some key questions for PM including evidence of real-world impact, its affordability, the risk of exacerbating health inequalities, and the computational and storage challenges of applying PM technologies at scale.

Schistosomiasis, acquired by skin-penetrating cercariae of dioecious digenean schistosomes during freshwater contact, afflicts nearly 260 and 440 million people with active infections and residual morbidity, respectively; about 10 million women at reproductive age contract schistosomiasis during gestation every year. Acute schistosomiasis is characterized by pre-patent pro-inflammatory CD4+ T-helper 1 or CD4+ Th1/T-helper 17 reactivity against immature schistosomulae. Chronic schistosomiasis is dominated by post-patent anti-inflammatory CD4+ T-helper 2 reactivity against ova epitopes; flukes co-exist in immunocompetent definitive hosts as they are capable of evading their defense mechanisms. Preventive measures should be complemented by vaccination, inducing long-term protection against transmission, infection, and disease recurrence, given the latest advancements in schistosomal vaccines. Transmission models incorporating vaccination available in PubMed, Embase and Web of Science up to December 31, 2023 are presented. Besides conceptual model differences, predictions meant to guide decision- and policymaking reveal continued worm harboring facilitating transmission besides residual infections, and increased susceptibility to re-infection and rebound morbidity, both shifted to later life stages following the intervention. Consequently, a vaccination schedule is pivotal considering the optimal age for initial immunization, i.e., pre-schoolchildren or schoolchildren, in a cohort-based or population-based manner while incorporating potential non-adherers promoting ongoing transmission; longevity over magnitude of vaccine protection to antigenic schistosomal moieties is crucial including accounting for existing pre-acquired immunity from natural exposure, in utero priming besides herd immunity, and induced by chemotherapy. Combining as one multi-component approach long-term effects of vaccination with short-term effects of chemotherapy as regular repeated vaccine-linked therapy in contrast to a single-component intervention seems most promising for achieving WHO’s endpoints of transmission elimination and morbidity control.

This paper investigates generalized Bayesian (GB) inference in the context of a one-parameter Pareto distribution. The study focuses on the derivation of generalized Bayesian estimators (GBE) and generalized empirical Bayesian estimators (GEBE) for the parameters of the Pareto distribution using type II censored data. In addition, the study investigates a one-sample prediction approach to examine generalized Bayesian prediction (GBP) and generalized empirical Bayesian prediction (GEBP). To evaluate the performance of these estimation and prediction methods, Monte Carlo simulations were performed comparing GBE with GEBE and GBP with GEBP for different parameter values and learning rate parameters (LRP).

A PLS-based quality prediction method is proposed for batch processes using two-dimensional extended windows. To realize the adoption of information in the direction of sampling time and batch, a new definition region of support (ROS), k-i-back-extended region of support (KIBROS), is proposed to establish the extended window, which including the data of the previous sampling times in the same batch, the data of the same sampling time in the historical batches, the data of the previous sampling times in the historical batches and the data of the later sampling times in the historical batches. According to these regions of support, extended windows are established, and different models are proposed based on the extended windows for batch processes quality prediction. Further, using a typical batch process as an example, the injection molding process, the proposed quality prediction method is experimentally verified, proving that the proposed methods have higher prediction accuracy than the traditional method and the prediction stability is also improved.

It has been an outstanding challenge for global climate models to simulate and predict East Asia (EA) summer monsoon (EASM) rainfall. This study evaluates the dynamical hindcast skills with the newly developed Nanjing University of Information Science and Technology Earth System Model version 3.0 (NESM3.0). To improve the poor prediction of an earlier version of NESM3.0, we have modified convective parameterization schemes to suppress excessive deep convection and enhance insufficient shallow and stratiform clouds. The new version of NESM3.0 with modified parameterizations (MOD hereafter) yields significantly improved rainfall prediction in the northern and southern China but not over the Yangtze River Valley. The improved prediction is primarily attributed to the improvements in the predicted climatological summer mean rainfall and circulations, seasonal march of the subtropical rain belt, Nino 3.4 SST anomaly, and the rainfall anomalies associated with the development and decay of El Nino events. However, the MOD still has notable biases in the predicted leading mode of interannual variability of precipitation. The leading mode captures the dry (wet) anomalies over the South China Sea (northern EA) but misplaced precipitation anomalies over the Yangtze River Valley. The model can capture the interannual variation of the circulation indices very well, but the bias in the circulation-rainfall connection caused predicted rainfall errors. The results here suggest that over EA land regions, the skillful rainfall prediction relies on not only model’s capability in predicting better summer mean and seasonal march of rainfall and ENSO teleconnection with EASM, but also accurate prediction of the leading modes of interannual variability.

With the significant annual increase in the market demand for biopesticides, the industrial production demand for predatory mites, which hold the largest market share among biopesticides, has also been rising.To achieve efficient and low energy consumption control of predatory mite breeding environmental parameters, accurate estimation of breeding environmental parameters is necessary. This paper collects and pre-processing hourly time-series data of temperature and humidity from industrial breeding environments. Time series prediction models such as SVR, LSTM, GRU, and LSTNet are applied to model and predict historical data of the breeding environment. Experiments validate that the LSTNet model is more suitable for such environmental modeling. To further improve prediction accuracy, the training data for the LSTNet model is enhanced using hierarchical clustering of time-series features. After augmentation, the root mean square error (RMSE) of temperature prediction decreased by 27.3%, and the RMSE of humidity prediction decreased by 32.8%, significantly improving the accuracy of multi-step predictions and providing substantial industrial application value.

This study addresses the prediction of recurring failures in water supply networks, a complex and costly task, but essential for the effective maintenance of these vital infrastructures. Using historical failure data provided by Companhia de Água e Esgotos da Paraíba (CAGEPA), the research focuses on predicting the time until the next failure at specific points in the network. The authors divided the failures into two categories: Occurrences of New Faults (ONF) and Recurrences of Faults (RF). To make the predictions, they used predictive models based on Machine Learning, more specifically on MLP (Multi Layer Perceptron) neural networks. The study revealed that, by analyzing data from past failures and considering factors such as altitude, number of failures on the same street and days between failures, it is possible to achieve an accuracy greater than 80% in predicting failures within a 90-day interval. This demonstrates the feasibility of using fault history to predict future water supply outages with significant accuracy. These forecasts allow water utilities to plan and optimize their maintenance, minimizing inconvenience and losses. The article contributes to the field of water infrastructure management by suggesting that the data-driven approach can be applied in other cities or in networks of different types, such as energy or communication networks. The conclusions highlight the importance of data collection and analysis in preventing failures and optimizing water utilities’ resources.

The dynamic evolution and variation of electrical loads is now a priority for optimum management and, above all, forecasting. Indeed, these dynamic load variations require computer tools able to implement optimal load forecasting models. Scientific research into automated models for forecasting electrical loads therefore represents a challenge for scientific researchers. Several research studies have therefore been carried out. These include machine learning approaches such as: LSTM (Long Short-Term Memory), Support Vector Machine (SVM) and others. This article proposes a comparison study between a hybrid model based on the wavelet transform coupled with the adaboost method, and LSTM, for forecasting electricity consumption loads. Python 3.10 was used for the studies. The first results obtained consisted in the study of electricity load forecasts over four (04) data sets of the year (January, April, August and December). These results are very satisfactory, showing a good correlation between the real results of the electrical load consumption data, and the results of the implemented model. The electrical load consumption data are collected from a renewable energy production source: photovoltaic solar energy. The model test results (R2) obtained range from 0.919 to 0.958. These results are representative of real data and reflect the model's performance. The second set of results concerns a comparative study between the methods used by Y. Xie et al (CNN, MLP, LSTM-AM and LSTM-AM-MLP), and our approach. The prediction results obtained between the approaches show a prediction gap ranging from 0.15 to 0.78 for RMSE and 0.83 for MAPE. These results show significant differences between the methods. The minimization of errors by our model, therefore, reflects the model's performance in terms of accuracy, which is necessary for the optimal management of consumer electricity load forecasts in order to ensure balance between supply and demand.

This study aims to evaluate the potential of machine learning algorithms (Random Forest and Support Vector Machine) in predicting the open porosity of a general-use industrial mortar applied to different substrates based on the characteristics of both the mortar and substrates. For this purpose, an experimental database comprising 1592 samples of industrial mortar applied to five different substrates (hollowed ceramic brick, solid ceramic brick, concrete block, concrete slab, and lightweight concrete block) was generated by an experimental program. The samples were characterized by bulk density, open porosity, capillary water absorption coefficient, drying index, and compressive strength. This database was then used to train and test the machine learning algorithms to predict the open porosity of the mortar. The results indicate that it is possible to predict the open porosity of the mortar with good prediction accuracy and that both Random Forest (RF) and Support Vector Machine (SVM) algorithms (RF =0.880; SVM = 0.896) are suitable for this task. Regarding the main characteristics that influence the open porosity of the mortar, bulk density and the open porosity of the substrate are significant factors. Furthermore, the study employs a straightforward methodology with a machine learning no-code platform, enhancing the replicability of its findings for future research and practical implementations.

To overcome the time-consuming drawbacks of Computational Fluid Dynamics (CFD) numerical simulations, this paper proposes a hybrid model based on a parallel architecture based on the concept of intelligent aerodynamics, named PA-TLA (Parallel Architecture combining TCN, LSTM, and Attention mechanism). This model utilizes CFD data to drive efficient predictions of aircraft wake evolution at different initial altitudes during the approach phase. Initially, CFD simulations of continuous initial altitudes during the approach phase are used to generate aircraft wake evolution data, which are then validated against real-world LIDAR data to verify their reliability. The PA-TLA model is designed based on a parallel architecture, combining Long Short-Term Memory networks (LSTM), Temporal Convolutional Networks (TCN), and a tensor concatenation module based on the attention mechanism, which ensures computational efficiency while fully leveraging the advantages of each component in a parallel processing framework. The study results show that the PA-TLA model outperforms both the LSTM and TCN models in predicting the three characteristic parameters of aircraft wake: vorticity, circulation, and Q-criterion. Compared to the serially structured TCN-LSTM, PA-TLA achieves an average reduction in mean squared error (MSE) by 6.80%, mean absolute error (MAE) by 7.70%, and root mean square error (RMSE) by 4.47%, with an average increase in the coefficient of determination (R²) by 0.36%, and a 35% improvement in prediction efficiency. Lastly, this study combines numerical simulation and the PA-TLA deep learning architecture to analyze the characteristics of wake evolution during the near-ground phase, providing theoretical value for further reducing aircraft wake intervals and enhancing airport operational efficiency.

Background: Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, are limited. Objectives: The aim of this work is to develop a binary outcome mixed effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aims to assess its performance and compare it to fixed effects Xgboost and traditional logistic regression models. Methods: A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 Jan 2012 and 31 Mar 2019 were included. The dataset was split into two cohorts: Training/Validation (n = 157196; 2012-2016) and Holdout (n = 69891; 2017-2019). The outcome variable was 30 days mortality with hospitals considered as clustering variable. The logistic regression, mixed effects logistic regression, Xgboost and binary outcome mixed effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach. Results: The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of mixed effects models. Unstandardized Xgboost BME demonstrated marked improvements in predictor power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glm) and generalized linear mixed-effects models (glmer) models followed similar results, with Xgboost models excelling also at greater sample sizes. Conclusions: These findings suggest that integrating mixed effects into machine learning models can enhance their applicability in clinical settings where sample size is small such as rare conditions.

This study addresses the challenge of predicting the dynamic behavior of the structures under seismic excitation. Accurate prediction of such systems' responses is critical for the design and evaluation of buildings and infrastructure. Traditional methods, including numerical models and differential equation solvers, often face significant computational burdens, especially with nonlinear hysteretic behaviors and large-scale problems. To overcome these limitations, a novel Fuzzy-based Convolutional Neural Network (FuzzyCNN) model is developed. This model integrates fuzzy logic principles with convolutional neural networks to effectively manage the uncertainties and complexities inherent in soil-structure interaction under seismic loads. The model's performance is validated through both numerical simulations and experimental data from a mid-rise concrete building subjected to seismic events. Comparative analysis with a traditional Physics-informed CNN (PhyCNN) model demonstrates the superior accuracy and robustness of the FuzzyCNN in predicting seismic responses. Key results show that the FuzzyCNN model not only enhances prediction accuracy but also handles uncertainties more effectively than the PhyCNN model. The findings suggest that the FuzzyCNN model can significantly improve the efficiency and accuracy of dynamic response predictions. This advancement offers valuable implications for engineering design, seismic risk assessment, and the development of more resilient infrastructure.

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 ultra-sparse 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 against 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 non-observed 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 power-law 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 puts ESML at its heart. We conduct experiments on 7 datasets and 5 network structures comparing CHT to dynamic sparse training SOTA algorithms and the fully connected counterparts. The results indicate that, with a mere 1% of links retained during training, CHT surpasses fully connected networks on VGG16, GoogLeNet, ResNet50, and ResNet152. 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 that 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 the first examples of parsimony dynamic sparse training because, in many datasets, it can retain network performance by percolating and significantly reducing the node network size. Our code is available at: https://github.com/biomedical-cybernetics/Cannistraci-Hebb-training.

Aiming at the development of the application of massive and heterogeneous LEO constellations, the influence of typical perturbation forces on the orbit prediction of LEO satellites at different altitudes is analyzed. Firstly, the main perturbation force model of LEO satellites is introduced. Then experiments for analyzing the influence of orbit prediction on LEO satellites at different altitudes are designed. Finally, the influence of typical perturbation forces on the orbit prediction under different prediction durations by numerical analysis is assessed systematically, and the orbit prediction of LEO satellites with different non-spherical gravitational field orders, ocean tide orders and atmospheric density models were compared and calculated. The research results show that different orders of non-spherical gravitational fields should be considered when the altitude of satellites is different, the reasonable gravitational field orders for LEO satellites at 500km, 1000km, 1500km and 2000km under 1-hour forecast time are 140x140, 80x80, 60x60 and 40x40 orders, the reasonable orders of ocean tide perturbation for 1500km and 2000km satellites are 20x20 orders. Under the 24-hour forecast time, atmospheric resistance has a great influence on the precision of LEO satellites at orbit altitude below 1,000km. The forecast deviation of the LEO satellites orbit at 500km reaches 8751.576m. The difference of orbit precision between different atmospheric density models is in the meter level. The orbit deviation by the Standard Atmosphere 1976 and NRLMSISE 2000 atmospheric models respectively reaches 25.494m. Relevant conclusions provide support for the optimization and selection of dynamical models in high precision orbit determination and fast orbit prediction of LEO satellites.

The branch prediction units (BPUs) generally have security vulnerabilities, which can be used by attackers to obtain the execution status, jump directions, and jump address of conditional branches, and the existing protection methods cannot defend against these attacks. Therefore, this article proposes a hardware security protection method for conditional branches of embedded systems. This method calculates the number of updates to the branch target buffer (BTB). When it exceeds the threshold, BTB is locked to prevent attackers from analyzing the execution status of branches based on the time difference of whether BTB is updated. Moreover, the hybrid physical unclonable function (PUF) circuit is designed to provide confidentiality protection for the jump directions, jump addresses, and their indexes, preventing attackers from stealing these critical data. If these mechanism fails and attackers successfully tamper with conditional branches, this paper proposes a control flow integrity (CFI) protection mechanism based on branch labels to timely detect tampering with instruction codes, jump addresses, and jump directions. The proposed method is implemented and tested on FPGA. The experimental results show that this method can achieve fine-grained security protection for conditional branches, with about 5.4% resource overhead and less than 5.5% performance overhead.

This study introduces a novel method that combines Generative Adversarial Networks (GANs) with conformal prediction to revolutionize the domain of stock ticker forecasting. Our approach enhances prediction accuracy and offers dependable prediction intervals to gauge uncertainty, surpassing current GAN-based techniques in unpredictable market scenarios. We made a validation using AAPL stock data, showing the ability of our model to generate accurate forecasts and reliable assessments of prediction uncertainty. The prediction intervals generated provide investors and risk managers with a powerful tool to make informed decisions. Our approach represents a notable advancement in financial prediction as it improves the clarity and reliability of forecasts. By incorporating conformal prediction into the GAN framework, the reliability of forecasts is improved, providing a thorough evaluation of uncertainty that is crucial for successful risk management. This framework has the potential to transform the field of predictive analytics in finance. It shows a solution that balances accuracy and uncertainty quantification. The results clearly show the effectiveness of this method, paving the way for its potential application in a wide range of financial prediction scenarios.

Predictive numerical models in the study of ground-borne vibrations generated by railway sys-tems have traditionally relied on the segmented approach of subsystems. In this approach, loads are individually applied, and the cumulative effect of rolling stock is obtained through superposi-tion. While this method serves to mitigate computational costs, it may not fully capture the com-plex interactions involved in ground-borne vibrations. Recent advancements in computational and software tools have enabled the development of more sophisticated vibrational pollution models. These advanced models encompass the entire dynamic system, from the rolling stock to the terrain, allowing for continuous simulations with a defined time step. Furthermore, the incorporation of computational contact tools between various ele-ments not only ensures temporal accuracy but also extends the analysis to the frequency domain. This paper explores the evolution of predictive numerical models in the context of ground-borne vibrations generated by trains on ballasted tracks. It highlights the shift from segmented models to continuous simulations, demonstrating the progressive advancement towards more comprehen-sive and accurate representations of railway-induced and generated vibrations in the track sur-roundings as an additional way of evaluate sustainability of infrastructures. In particular, this development of a numerical model from its inception aimed to expand upon ex-isting emission - prediction models by enriching the data with frequency-domain information. This approach has been driven by the aspiration to bridge the gap between numerical predictions and measured signals, striving for a higher level of accuracy in our obtained results. This model can predict the impact of a high-speed rail (HSR) vehicle passing on its own track. It possesses sufficient information in both the time and frequency domains to precisely characterize vibrations. This initiative marks a pivotal advancement, enabling us to more effectively capture the intricacies of ground-borne vibrations and their impact on the surrounding environment due to a deeper comprehension of the occurrences in the frequency domain, there's a heightened ca-pability to accurately characterize vibrations.

Traffic accidents are among the most common causes of death worldwide. According to statistics from the World Health Organization (WHO), 50 million people are involved in traffic accidents every year. Canada, particularly Montreal, is not immune to this problem. Data from the Société de l’Assurance Automobile du Québec (SAAQ) shows that there were 392 deaths on Québec roads in 2022, 38 of them related to the city of Montreal. This value represents an increase of 29.3% for the city of Montreal compared to the average for the years 2017 to 2021. In this context, it is important to take concrete measures to improve traffic safety in the city of Montreal. In this article, we present a web-based solution based on machine learning that predicts the severity of traffic accidents in the city of Montreal. This solution uses dataset of traffic accidents that occurred in Montreal between 2012 and 2021. Classification algorithms such as eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Random Forest (RF) and Gradient Boosting (GB) were used to develop the prediction model. When evaluating the prediction model, performance metrics such as precision, recall, F1 score, and accuracy are taken into account. The performance analysis shows an excellent accuracy of 96% for the prediction model based on the XGBoost classifier. The other models (CatBoost, RF, GB) achieved 95%, 93% and 89% accuracy, respectively. The prediction model based on the XGBoost classifier was deployed using a client-server web application managed by Swagger-UI and the Flask Python framework.

By repeated unloading and loading of the excavation dynamic and static loads, repeated train dynamic and static loads of multi-factors, the underpass tunnel, cross tunnel engineering influence area rock layer, the existing tunnel structure of the three constitutes a multifaceted structure, multi-factor interaction system. Existing tunnels into the prediction theory model of the new tunnel excavation process of dynamic and static loads, dynamic and static loads of existing tunnels are mostly analyzed individually, the results of synergistic analysis needs to be improved. Based on the theory of the current layer method, the paper comprehensively considers the stiffness of the existing tunnel, the stiffness of the new tunnel, the excavation method load and the existing tunnel load, coupled with Peck's empirical formula, the theoretical model of deformation prediction for excavation of a two-lane highway tunnel under the tunnel through the existing railroad is proposed, and verified and optimized by numerical calculations and monitoring data, which proves the applicability and reliability of the theoretical model in the similar strata and the project promotion.

This study introduces a novel predictive model for atomization droplet size, developed through comprehensive data collected under elevated temperature and pressure conditions using a twin swirl airblast nozzle. The model, grounded in flow instability theory, has been meticulously parameterized using the Particle Swarm Optimization (PSO) algorithm. Through rigorous analysis, including analysis of variance (ANOVA), the model has demonstrated robust reliability and precision, with a maximum relative error of 19.3% and an average relative error of 6.8%. Compared to the classical atomization model by Rizkalla and Lefebvre, this model leverages theoretical insights and incorporates a range of interacting variables, enhancing its applicability and accuracy. Spearman correlation analysis reveals that air pressure and the air pressure drop ratio significantly negatively impact droplet size, whereas the fuel-air ratio (FAR) shows a positive correlation. Experimental validation at ambient conditions shows that the model is applicable with a reliability threshold of ≥0.13 and highlight the predominance of the pressure swirl mechanism over aerodynamic atomization at higher fuel flow rates (q > 1.25 kg/h). This research effectively bridges theoretical and practical perspectives, offering critical insights for the optimization of airblast nozzle design.

5-Pentadecylresorcinol (C15) is a natural alkylresorcinol that has been shown to protect against complications caused by imbalanced nutrition. Although the exact mechanisms of beneficial activity of C15 are not known, we assume that the protective effects of C15 on metabolic health are mediated by their modulatory influence on the composition of the intestinal microbiota and functional activity. Cobamides and vitamin B12 are believed to be crucial modulators of mammalian gut ecosystems. We proposed that C15 may influence the representation of enzymes and pathways for vitamin B12 synthesis in the gut microbiome, providing compositional and functional changes in the microbial community. High-throughput metagenome sequencing of the contents of the small and large intestines of C57Bl6 mice fed a regular or high-fat diet with or without C15 supplementation was performed followed by reconstruction of the metabolic activity of the microbiota to clarify the role of C15 in vitamin B12 synthesis by the gut microbiota. It has been established that C15 significantly increases the representation of the cobalamin salvage pathway and enzymes in the microbiome of the large intestine of mice fed a high-fat diet. The genera Clostridium, AF12, and [Ruminococcus] had shown the highest number of correlations with enzymes for B12 synthesis and were negatively associated with the representation of probiotic bacteria. Therefore, the beneficial effect of C15 on the gut microbiota community can be achieved by modulating B12 synthesis that, in turn, serves as one of the key regulators of gut microbiota ecology.

Every year, the Montreal police are confronted with countless crimes committed by criminals. These crimes affect the quality of life of city residents and impose a socio-economic burden on the city. In this study, we conduct a comparative analysis based on several machine learning algorithms to develop a model to predict the crime category in Montreal. The performance of algorithms such as eXtreme Gradient Boosting (XGBoost), Decision Trees (DT) and Random Forest (RF) were analyzed. The performance analysis takes into account the performance metrics such as precision, accuracy, recall and F1-score. This analysis was based on crime data in Montreal from 2015 to 2023. This data is characterized by a strong imbalance between crime categories. To address the data imbalance problem, a data balancing approach based on the SMOTE-ENN algorithm was adopted. In the exploratory data analysis phase, temporal trends by crime category were highlighted. The results of the analysis showed that the XGBoost algorithm outperformed the other two. Specifically, the XGBoost algorithm achieves an accuracy of 92%, while DT and RF achieve an accuracy of 86% and 84%, respectively. As a result, XGBoost was deployed via a web application using the Flask and Swagger UI Python frameworks. This study provides the Montreal police with an effective tool to better utilize their resources in fighting crime. In addition, policymakers in the city of Montreal can use this tool to identify high-risk areas and give them more attention.

Rising incidences of cutaneous melanoma have fueled the development of statistical models that predict the individual melanoma risk. Our aim was to assess the validity of published prediction models for incident cutaneous melanoma using a standardized procedure based on PROBAST (Prediction model Risk Of Bias ASsessment Tool). We included studies that were identified by a recent systematic review and updated the literature search to ensure that our PROBAST rating included all relevant studies. Six reviewers assessed the risk of bias (ROB) for each study using the published “PROBAST Assessment Form” that consists of four domains and an overall rating of ROB. We further examined a temporal effect regarding changes in overall and domain-specific ROB rating distributions. Altogether 42 studies were assessed, of which a vast majority (n=34; 81%) was rated as having high ROB. Only one study was judged as having low ROB. The main reasons for high ROB ratings were the use of hospital controls in case-control studies and the omission of any validation of prediction models. However, our results of the temporal analysis showed a significant reduction in the number of studies with high ROB for the domain analysis. Nevertheless, the evidence base of high-quality studies that can be used to draw conclusions on the prediction of incident cutaneous melanoma is currently much weaker than the high number of studies on this topic would suggest.

The effects of environmental media on the corrosion fatigue fracture behavior of 25CrMo steel were investigated. The media include air, and a 3.5 wt.% and a 5.0 wt.% NaCl solutions. Experimental results indicate that the media induces the initiation of corrosion fatigue cracks at multiple sites. The multi-cracking sites cause the changes in the crack growth directions, the crack growth rate during the coupling action of the media and the stress amplitude. The coupling effects are important for engineering applications and research. The probability and predictions of the corrosion fatigue characteristic life can be estimated using the 3-parameter Weibull distribution function.

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2-2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

With the rapid development of wireless communication networks, using AI to predict complex city-scale network traffic has become a significant research challenge. This paper, based on a Graph Convolutional Network (GCN) architecture, proposes a novel wireless network traffic prediction algorithm focused on predicting city-level communication traffic data at an hourly granularity. The algorithm enhances prediction accuracy through two key innovations: first, we introduce a hierarchical attention architecture that combines dynamic and static attention mechanisms. The static attention mechanism, based on wireless channel models, captures fixed spatial relationships between base stations, such as inter-station distances and stable connections. The dynamic attention mechanism, on the other hand, dynamically adjusts to account for time-varying traffic patterns, such as rush hours and holiday effects, enabling the model to adapt to temporal variations in network traffic. These two attention mechanisms are seamlessly integrated within the model through feature concatenation and interactive learning, allowing the model to capture both spatial and temporal characteristics of network traffic simultaneously. Secondly, we innovatively introduce a strategy for adjusting the aggregation iterations of the Graph Convolutional Network (GCN) based on the Laplacian matrix. By leveraging the spectral information provided by the Laplacian matrix, we dynamically determine the depth of the graph convolutional network, thereby avoiding issues of over-smoothing or underfitting and ensuring stable performance in complex network structures. Experimental results demonstrate that the proposed algorithm significantly outperforms existing methods across multiple dataset, particularly in predicting network traffic data with intricate spatiotemporal characteristics.

Without an established energy management plan, human lifestyle improvement is incomprehensible. Adequate energy assets are the key to human lifestyle development, however, energy assets are restricted and exorbitant too. In this paper, an energy control system for a green environment called PMC (Power Management and Control) is proposed. The system is based on hybrid energy optimization, energy prediction, and multi-preprocessing. The blend of GA (Genetic Algorithm) and PSO (Particle Swarm Optimization) is utilized to make a fusion methodology to improve occupant comfort index (OCI) and decrease energy utilization. The main theme of the proposed PMC technique is to improve OCI and decrease energy utilization. The proposed framework gives better OCI when compared with its counterpart Ant Bee Colony along with Knowledge Base framework (ABCKB), GA-based prediction framework (GAP), Hybrid Prediction with Single Optimization framework (SOHP), and PSO-based power consumption framework. Compared with the existing AEO framework, the proposed PMC methodology gives practically the same OCI, but consumes less energy. The proposed PMC methodology additionally accomplished the most extreme OCI (i-e 1) when compared with the existing model FA-GA (i-e 0.98). The proposed PMC model consumed less energy as compared to existing models ABCKB, GAP, PSO and AEO. The proposed model consumed more energy than SOHP but provided better OCI. The comparative outcomes show the viability of the proposed PMC framework in lessening energy utilization and improving the OCI. Unlike other existing mythologies except for the AEO framework, the proposed PMC technique is additionally confirmed through a simulated climate by controlling indoor climate using actuators, like Fan, light, AC and boiler.

Research in complex network analysis, including tasks such as information dissemination and link prediction, has traditionally advanced by examining groups of nodes with similar characteristics. In multilayer complex networks, these analyses are performed layer-wise, with each layer representing a distinct feature. However, this approach often neglects interlayer interactions, leading to limited predictive power, underestimation of network resilience, and incomplete identification of influential nodes. This article introduces a novel block modeling technique that integrates dominant features from multiple layers, addressing these shortcomings. Our approach introduces a new centrality metric that combines layer weight and PageRank centrality to identify influential nodes within multilayer networks. Nodes are aggregated into blocks centered around these influencers, accounting for both intra- and interlayer connections. Empirical evaluation of various datasets demonstrates that our method effectively identifies influential nodes, thereby enhancing information dissemination and link prediction across diverse multilayer network structures. This technique offers significant potential for improving decision-making processes in various fields, including social network analysis, transportation systems, and biological networks.

Drug development is a lengthy process with a high failure rate. Increasingly, machine learning is utilized to facilitate the drug development processes. These models aim to enhance our understanding of drug characteristics, including their activity in biological contexts. However, a major challenge in drug response (DR) prediction is model interpretability as it aids in the validation of findings. This is important in biomedicine, where models need to be understandable in comparison with established knowledge of drug interactions with proteins. drGAT, a graph deep learning model, leverages a heterogeneous graph composed of relationships between proteins, cell lines, and drugs. drGAT is designed with two objectives: DR prediction as a binary sensitivity prediction and elucidation of drug mechanism from attention coefficients. drGAT has demonstrated superior performance over existing models, achieving 78\% accuracy (and precision), and 76\% F1 score for 269 DNA-damaging compounds of the NCI60 drug response dataset. To assess the model's interpretability, we conducted a review of drug-gene co-occurrences in Pubmed abstracts in comparison to the top 5 genes with the highest attention coefficients for each drug. We also examined whether known relationships were retained in the model by inspecting the neighborhoods of topoisomerase-related drugs. For example, our model retained TOP1 as a highly weighted predictive feature for irinotecan and topotecan, in addition to other genes that could potentially be regulators of the drugs. Our method can be used to accurately predict sensitivity to drugs and may be useful in the identification of biomarkers relating to the treatment of cancer patients.

Reliable prediction of building-level energy demand is crucial for the building managers to optimize and regulate energy consumption. Conventional prediction models omit the uncertainties associated with demand over time; hence, they are mostly inaccurate and unreliable. In this study, a Bayesian neural network (BNN)-based probabilistic prediction model is proposed to tackle this challenge. By quantifying the uncertainty, BNNs provide probabilistic predictions that capture the variations in the energy demand. The proposed model is trained and evaluated on a subset of the building operations dataset of Lawrence Berkeley National Laboratory (LBNL), Berkeley, California, which includes diverse attributes related to climate and key building performance indicators. We have performed thorough hyperparameter tuning and used fixed-horizon validation to evaluate trained models on various test data to assess generalization ability. To validate the results, quantile random forest (QRF) was used as a benchmark. The study compared BNN with LSTM, showing that BNN outperformed LSTM in uncertainty quantification.

The high reliable correlations between CBR and DCP in general proposed are presented in this paper. We analyzed the test data and correlations from many researchers to find the best equation for prediction the CBR from DCP test. The findings show that all correlations from existing paper are based on local material and cannot apply to soil in a different location in general purpose. New correlations between CBR and DCP were proposed and validated in this paper for general uses. The validation confirmed that these new correlations can predict well with higher R2.

OBJECTIVES: To assess the predictive value of serum trypsin and Trypsinogen Activation Peptide (TAP) for the severity of AP by means of a single center cohort study as well as a systematic review of the current literature. METHODS: The literature search was conducted using Medline (PubMed), EMBASE and the Cochrane Central Register. A total of 142 patients with acute pancreatitis (AP) were included in the cohort study and parameters of the revised Atlanta criteria of 2012 and the APACHE II were assessed. RESULTS: The review showed promising results for the predictive value of serum trypsinogen-2, but conflicting results for serum TAP and trypsin. In the cohort study, patients were observed for 4 days after diagnosis of AP: 9 patients had severe AP, 35 patients had moderate AP and 81 patients had mild AP. The ratio of the geometric mean of severe vs mild AP for trypsin was 0.72 (95% CI: 0.51-1.00), p=0.053 and for TAP 0.74 (95% CI: 0.54-1.01), p=0.055 respectively. CONCLUSION: The cohort study showed an inverse correlation of serum levels of TAP and trypsin with severity of AP. Serum TAP and trypsin have an inferior predictive value of severity of AP compared to the clinical APACHE II score.

This study aims to address the inefficiencies and time-consuming nature of traditional hot-air anti-icing system designs by introducing reduced order models (ROM) and machine learning techniques to predict anti-icing surface temperature distributions. This study compares several classic neural networks, ultimately proposing two models: POD-AlexNet and multi-CNNs with GRU (MCG). Design variables of the hot-air anti-icing cavity are used as inputs, and the corresponding surface temperature distribution data serve as outputs. The performance of these models is evaluated on the test set. The POD-AlexNet model achieves a mean prediction accuracy of over 95%, while the MCG model reaches 96.97%. Both models significantly outperform traditional numerical simulation methods, delivering faster predictions. The proposed models achieve fast prediction of anti-icing surface temperature distribution while ensuring acceptable prediction accuracy. These models greatly enhance the prediction efficiency over existing numerical simulation approaches, contributing to the design of aircraft hot-air anti-icing systems based on optimization methods such as genetic algorithms.

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.

Ensuring the accuracy of wind power prediction is paramount for the reliable and stable operation of power systems. This study introduces a novel approach aimed at enhancing the precision of wind power prediction through the development of a multiscale hybrid model. This model integrates advanced methodologies including Improved Intrinsic Mode Function with Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Permutation Entropy(PE), Least Squares Support Vector Regression (LSSVR), Regularized Extreme Learning Machine(RELM), Multi-head Attention (MHA), and Bidirectional Gated Recurrent Unit (BiGRU). Firstly, the ICEEMDAN technique is employed to decompose the non-stationary raw wind power data into multiple relatively stable sub-modes, while concurrently utilizing PE to assess the complexity of each sub-mode. Secondly, the dataset is reconstituted into three distinct components: high-frequency, mid-frequency, and low-frequency, to alleviate data complexity. Following this, the LSSVR, RELM, and MHA-BiGRU models are individually applied to predict the high, mid,and low-frequency components, respectively. Thirdly, the parameters of the low-frequency prediction model are optimized utilizing the Dung Betele Optimizer(DBO) algorithm. Ultimately, the predicted results of each component are aggregated to derive the final prediction. Empirical findings illustrate the exceptional predictive performance of the multiscale hybrid model incorporating LSSVR, RELM,and MHA-BiGRU. In comparison to other benchmark models, the proposed model exhibits a reduction in Root Mean Square Error(RMSE) values of over 10%, conclusively affirming its superior predictive accuracy.

This study investigates the correlation between the California Bearing Ratio (CBR) and the Dynamic Cone Penetrometer (DCP) for subgrade soil analysis. The paper aims to provide practical equations for predicting CBR values from DCP test results, enhancing the efficiency of soil assessments in engineering practice. By analyzing test data and proposing correlations for different soil groups, the study introduces recalibrated correlations that demonstrate high accuracy in predicting CBR values. The newly proposed equations offer reliable predictions with R2 values of 0.89, 0.92, and 0.94 for clean sand, silty sand or sandy silt, and cohesive soil, respectively. These correlations serve as valuable tools for engineers, enabling rapid and accurate CBR estimations for improved decision-making in various engineering projects.

Objectives: To develop and validate the Communities Geriatric Mild Cognitive Impairment Risk Calculator (CGMCI-Risk), aimed at aiding community healthcare workers in the early identification of individuals at high risk of Mild Cognitive Impairment (MCI); Methods: Based on nationally representative community survey data, backward stepwise regression was employed to screen the variables, and logistic regression was utilized to construct the CGMCI-Risk. Internal validation was conducted using bootstrap resampling, while external validation was performed using temporal validation. The area under the receiver operating characteristic curve (AUROC), calibration curve, and decision curve analysis (DCA) were employed to evaluate the CGMCI-Risk in terms of discrimination, calibration, and net benefit, respectively; Results: The CGMCI-Risk model included variables such as age, educational level, sex, exercise, garden work, TV watching or radio listening, Instrumental Activity of Daily Living (IADL), hearing, and masticatory function. The AUROC was 0.781 (95% CI = 0.766 to 0.796). Calibration curve showed strong agreement, and the DCA suggested substantial clinical utility. In external validation, the CGMCI-Risk model maintained similar performance with an AUROC of 0.782 (95% CI = 0.763 to 0.801); Conclusions: CGMCI-Risk is an effective tool for assessing cognitive function risk within the community. It uses readily predictor variables, allowing community healthcare workers to identify the risk of MCI in older adults over a three-year span.

The Mara River basin (MRB) has a world-famous ecosystem, but the vegetation has been damaged due to economic development in recent years, and there is little known about the area that will experience severe vegetation damage in the future. Based on the vegetation vulnerability system, principal component analysis, and three CMIP6 scenarios (SSP1-2.6, SSP2-4.5, SSP5-8.5), vegetation vulnerability was calculated in the base period (2010-2019), near-term period (2020-2059) and long-term period (2060-2099) in the MRB. The spatial cluster of vegetation vulnerability was revealed by spatial correlation analysis, and the transition of vegetation vulnerability of different periods was analyzed by stochastic matrix. The results showed that in all periods, the vulnerability showed a high-high cluster in the east, and a low-low cluster midstream and downstream. From the stochastic matrix, the area of high vulnerability increased the least under the SSP1-2.6, while it increased the most under the SSP5-8.5. The vegetation vulnerability upstream increased the most from the base period to the near-term period and long-term period in the MRB. By comparing the vegetation vulnerability under different scenarios, and pointing out the areas with the highest vulnerability increase, this study can better provide comprehensive decision-making for vegetation protection in the MRB.

Accurate forecasting of available energy portion that corresponds to the reservoir inflow of the month(s) ahead provides important decision support for the hydropower plants in energy pro-duction planning for revenue maximization, as well as for the environmental impact prevention, and flood control at the upstream and downstream of a basin. Therefore, a reliable forecasting tool or model is deemed necessary and crucial. Considering the fluctuation and nonlinearity of data which significantly influence the forecasting results, this study develops an effective hybrid model by integrating Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) called “PSO-ANN” model based on the hydrological and meteorological data pre-processed by cross-correlation function (CCF), autocorrelation function (AFC), and normalization techniques for predicting the available energy portion corresponding to the reservoir inflow mentioned above for a case study hydropower plant in Laos namely, Theun-Hinboun hydropower plant (THHP). The model was evaluated by using correlation coefficient (r), relative error (RE), root mean square error (RMSE), and Taylor diagram plots in comparison with the popular single algorithm approaches such as ANN, and NARX models. Results demonstrated the superiority of the proposed PSO-ANN approach over the other two models.

Background: Despite the tremendous effort in hamstring injury prevention, injury rates in soccer remain elevated. Hypothesis: Hamstring and hip/pelvic isometric strength imbalances may increase the likelihood of hamstring strain injury (HSI) occurrence amongst soccer players.Study design: Case-control study.Methods: In 120 male soccer players (mean age: 20.0 +/- 6.96 years) pre-season maximum isometric strength of the hip adductors, abductors, flexors, and knee flexors were measured, and strength ratios were calculated. Previous injury and anthropometric data were registered. Injury data were collected following the FIFA/UEFA consensus. A multivariate and Machine learning-based Logistic Regression model was employed to estimate the likelihood of players sustaining a hamstring injury.Results: 21 players sustained 32 hamstring injuries. Players with higher abduction strength in the dominant leg had an 18.5% lower risk of sustaining a hamstring injury (OR = 0.818, CI 95% = [(0.695-0.964]). No other significant contributor variables were found to be significant predictors of hamstring injury in the player group (p> 0.05).Conclusion: Isometric strength of the abductor muscles in the dominant limb had a significant association with hamstring injury.Clinical relevance: Our findings indicate the utilization of hip strength measurements as an integral component of the pre-season screening assessment, thereby affirming prior research on the correlation between lumbo-pelvic stability and incidence of hamstring injuries. Consequently, clinicians should contemplate incorporating hip strengthening exercises into regular training sessions, rehabilitation programs, and injury prevention protocols especially indicated when lower hip strength levels are observed.

In this paper, we conduct a comprehensive analysis of the RounD dataset to enhance the understanding of motion forecasting for autonomous vehicles in complex roundabout environments. We implement a trajectory prediction framework that combines Long Short-Term Memory (LSTM) networks with graph-based modules to model vehicle interactions. Our primary objective is to assess the generalizability of a standard trajectory prediction model across diverse training and testing datasets. Through extensive experiments, we analyze how varying data distributions, including different road configurations and recording times, influence the model’s prediction accuracy and robustness. This study provides key insights into the challenges of domain generalization in autonomous vehicle trajectory prediction.

Marker-assisted selection (MAS) and genomic selection (GS) have been used to select individuals with desirable traits. MAS used a few markers associated with a specific trait to select individuals with desirable traits, which are determined after a Genome-wide association studies (GWAS). On the contrary, GS uses a large number of markers distributed across the genome to predict the genomic breeding values for a further selection of the individuals. In general, MAS has shown a high prediction accuracy but is not suitable for traits that are controlled for multiple genes, and has another constraint, it is required the phenotypic data; on the contrary, GS has not shown the highest prediction accuracy as MAS but it takes into account the effect of multiple genes controlling a target trait and it can be used without phenotypic data. Including GWAS-selected markers in GS can enhance the reduced prediction accuracy that GS shows in comparison with MAS. Thus, the objective of this study was to compare the prediction accuracy of MAS, and some models of genomic prediction (gBLUP, gBLUP including GWAs-selected markers, and some Bayesian models such as Bayes A, Bayes B, Bayes LASSO and Bayesian Ridge Regression) with GWAS-selected markers incorporated in gBLUP in order to confirm if the incorporation of GWAS in GS increases the prediction accuracy of GS. As a model for this study, it was used data from Sorghum which has shown population structure, to evaluate if the incorporation of GWAs-selected markers into GS improves prediciton accuracy. It was used a sample of 6000 SNPs out of the 265.487 reported in the study conducted by Morris et al (2013), and also it was considered some parameters that affect the efficiency of the selection such as the size of the training population, the heritability, and the number of QTNs. The GWAS-selected SNPs were identified after using the model BLINK. The results showed that the incorporation of GWAS-selected markers enhanced the performance of the genomic selection with similar prediction accuracy as MAS, the number of QTNs and size of the training population affected the accuracy, with higher accuracy with a bigger size of the training population and with a lower number of QTNs, but it seems that the heritability does not have any impact in the model where GWAS-selected SNPs were included in gBLUP.

The solar energy can mitigate the power supply shortage in remote regions for portable irrigation systems. The accurate prediction of solar irradiance is crucial for determining the quantity of solar panels and the power capacity of photovoltaic power generation (PVPG) systems for mobile sprinkler machines. In this study, a prediction method is proposed to forecast the solar irradiance of typical irrigation areas. The impact of the meteorological parameters on the solar irradiance is studied, and four different parameter combinations are formed and considered as input to the prediction model. Based on meteorological data provided by ten typical radiation stations uniformly distributed nationwide, an Extreme Gradient Boosting (XGBoost) model optimized using the Whale Optimization Algorithm (WOA) is developed to predict the solar radiation. The prediction accuracy and stability of the proposed method are then evaluated for different input parameters through training and testing. The differences between the prediction performances of models trained based on single-station data and mixed data from multiple stations are also compared. The obtained results show that the proposed model achieves the highest prediction accuracy when the maximum temperature, minimum temperature, sunshine hours ratio, relative humidity, wind speed, and extraterrestrial radiation are used as the input parameters. The prediction effectiveness is also verified based on measured data. The WOA-XGBoost model has higher prediction accuracy than the XGBoost model, with predicted values falling within acceptable ranges. The model developed using mixed data of multiple stations can be applied for forecasting solar irradiance in different regions. This study provides a foundation for the optimization of the configuration of PVPG systems for mobile sprinkler machines.

In today’s data-driven marketing landscape, accurately predicting customer responses to marketing campaigns is critical for optimizing engagement and return on investment (ROI). This study utilizes a Decision Tree (DT) model to identify key factors influencing customer behaviour. Initially, the model achieved a high accuracy of 87.3% but struggled with precision and recall due to class imbalance. By applying a resampling technique, the model’s performance improved significantly, with a recall increase from 44% to 83.1% and an F1-score improvement from 49% to 74.2%. Key influential features identified include how recently a customer made a purchase, the number of days they have been a customer, and the number of previous campaigns they responded to. The study highlights the DT model’s interpretability, making it a practical tool for marketing professionals to improve campaign effectiveness and customer targeting.

This research deals with risk assessment for human life, man-made infrastructure, and agriculture in a landslide-prone area using GIS-based spatial methods. The study area landslide inventory map was prepared based on previous landslide information, aerial photograph analysis, and several field observations. A total of 550 landslides have been included with 182 debris flow and 368 soil slides. All included landslides were classified into two groups by random selection; half were used for model calibration and the rest were used for cross-validation. In the analysis, fourteen causative factors were vastly used, such as aspect, slope, curvature, elevation, topographic wetness index, forest timber diameter, forest type, forest crown density, forest age, land-use, geology, soil drainage, soil depth, and soil texture. Moreover, to identify the interaction between occurred landslides and causative factors, the affected pixels were divided into different sub-classes using a frequency ratio method. Based on the total dataset, three landslide susceptibility maps were constructed using Bayesian prediction, likelihood ratio, and fuzzy set method. By evaluating cross-validation and success rate curve, model susceptibility results were plotted with a receiver operating characteristic (ROC) curve and the area under the curve (AUC) was estimated. In addition, for risk assessment, each social data layer such as agriculture, house, industry, business, road, river, population intensity, monetary value, and vulnerability level was added based on the local standard and incident time and was converted into US dollars. During the analysis, each method hazard map was used with a specific group of thematic data layers. Subsequently, for preparing the probability table, study area total pixels and predictive landslide affected pixels were considered. Matching with the affected pixels, a standard of 5000 pixels was selected to run the final evaluation. Based on the results, the agricultural field showed the highest vulnerability and estimated risk of US $ 16.3 million. Further, the man-made infrastructure map showed a risk of US $ 31.3 million. The total estimated population casualties were 6.77, which was relatively similar to the published data.

As the coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country with more than 34.1 million total confirmed cases up to June 1, 2021. In this work, we investigate correlations between online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the predictive accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet search and tweeting about COVID-19, indicating that earlier collective awareness on Twitter/Google correlates with lower infection rate. Lastly, we demonstrate that correlations between online social media and search trends are sensitive to time, mainly due to the attention shifting of the public.

1) Landsat operational land imager (OLI) data and consequent laboratory measurements were used to predict Chlorophyll-a (Chl-a) concentration and the trophic states for an inland lake within the East Kolkata Wetland, India; 2) The most suitable band ratio was identified by performing Pearson correlation analysis between Chl-a concentrations and possible OLI band and band ratios from the study points; 3) The results showed highest correlation coefficient from the band ratio OLI5/OLI4 with an R value of 0.85. The prediction model was then developed by applying regression analysis between the band ratio OLI5/OLI4 and Chl-a concentration of the study points. The reflectance ratios of the validation points were given as input on the prediction model and the model output was considered as predicted Chl-a values of the validation points to check the efficiency of the prediction model. The regression model between laboratory-derived Chl-a value and model-fitted Chl-a value of the validation points revealed a high correlation with an R² value of 0.78. Trophic State Index (TSI) of the lake was also calculated from laboratory-derived Chl-a value and model-fitted Chl-a value of the validation points. The study presented a high correlation of TSI determined from predicted data with TSI from laboratory reference data (R = 0.88). The TSI values of the lake ranged from 65 to 75 which indicate that the lake is appeared to be eutrophic to hypereutrophic conditions. 4) This empirical study showed that Landsat 8 OLI imagery can be effectively applied to estimate Chl-a levels and trophic states for inland lakes.

The present research project entitled "Development of a method for predicting the optimal maturity level of avocado using machine learning" aims to establish an accurate and efficient approach to assess the maturity of avocados using machine learning methodologies. This research specifically focuses on identifying the relevant physical and chemical characteristics of avocados, creating a dataset containing categorized images of maturity levels, and creating machine learning models capable of accurately predicting fruit maturity. The studies reveal that the application of machine learning, in particular convolutional neural networks and multisensor models, has the potential to transform the prediction of avocado maturity and thus improve product quality and customer satisfaction. The findings indicate that the proposed techniques achieve an accuracy rate of over 90%, demonstrating their viability for integration into mobile applications that can benefit growers and suppliers in their decision-making processes.

This paper explores the application of machine learning (ML) in predicting functional recovery in patients with ischemic stroke. As technology advances, ML shows significant potential in the field of stroke medicine, especially in the areas of big data analytics and personalized medicine. Studies have shown that ML algorithms can improve the accuracy of stroke image analysis, subtype classification, risk assessment, treatment guidance, and prognosis prediction. However, the widespread use of ML still faces challenges such as data standardization, model validation, privacy, and bias. This paper reviews the current application status of ML in the field of stroke, discusses the challenges faced, and looks forward to the future development direction, aiming to promote the practical application of ML technology in the diagnosis and treatment of stroke to improve the prognosis and quality of life of patients.

Despite ongoing efforts, the relationship between groin strength and injury remains unclear. The challenge of accurately predicting injuries presents an opportunity for researchers to develop pre-vention strategies to reduce the occurrence of such injuries. Consequently, this issue requires further investigation to obtain insights into effective mitigation strategies. In 120 male soccer players the maximum isometric strength of the hip muscle groups was measured, and the strength ratios were calculated. Previous injury and anthropometric data were registered. Injury data were collected following the FIFA/UEFA consensus. The K- Nearest Neighbour (k-NN), was used to predict the incidence of injury, while the significant predictive variables of the k-NN algorithm were fitted into a multivariate logistic regression model (LR) to analyze the likelihood of players sustaining a groin injury. The LR model determined two variables as significant predictors of groin injury. Players were less likely to sustain a groin injury by 76% for each decrease of the Adductors/Abductors isometric strength ratio in the non-dominant limb (OR = 0.238, CI 95%= [(0.098-0.572]). Players with a history of previous injury had a 67% greater risk of sustaining an injury (OR = 0.333, CI 95%= [(0.1068-1.038]). Isometric hip adductor and abductor strength im-balances of the non-dominant lower limb and a history of previous injury were risk factors for groin injury in soccer players.

This paper employs the Finite Element Method (FEM) to simulate and analyze the effects of corrosion defect parameters on the stress and failure pressure of pipelines. It investigates how the boundary conditions of the pipeline model influence stress and examines the sensitivity of failure pressure to corrosion defect parameters. A nonlinear regression equation has been developed from a dataset obtained through simulation experiments to predict the failure pressure of corroded pipelines. To validate the effects of corrosion defect parameters on failure pressure, a hydrostatic test platform for an API 5L X65 pipeline with corrosion defects was established to measure stress levels and failure pressures across varying corrosion defects. The study reveals that failure pressure is negatively correlated with corrosion length and depth, while positively correlated with corrosion width. Among these parameters, corrosion depth exerts a more significant influence on the pipeline's failure pressure than corrosion length and width. Within the range of corrosion defect parameters examined, the maximum deviation of the prediction equation's results from the simulation results is 8.71%, with an average deviation of 5.81%. The standard deviation of the fitted residuals is 0.01837. Additionally, the maximum deviation between the predicted results and experimental measurements is 8.39%, with an average deviation of 7.77%. The strong agreement between the predicted results from the equation and the actual measured data underscores the effectiveness of the nonlinear regression equation.

Amidst the escalating demands for efficient Intelligent Transportation Systems (ITS) management, the significance of accurate Origin-Destination (OD) data prediction has emerged as a paramount concern, given its indispensable role in the ITS domain. This paper introduces a groundbreaking integrated model, creatively fusing the unique strengths of Graph Convolutional Network (GCN), Residual Neural Network (ResNet), and Long Short-Term Memory Network (LSTM) into a single architecture, which we name GraphResLSTM, to exploit road segment average speed data for OD prediction. Compared with conventional road segment traffic volume data, average speed data is more readily available, significantly reducing the data accessibility barrier for OD prediction. We underscore the critical role of selection of key road segments and employs a combination of Entropy Weight Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to identify 41 representative road segments from the experimental road network. In the experimental phase, we simulate 86400000 seconds of traffic conditions, generating a total of 1440000 data records. Utilizing these simulated data, we design and conduct comparative experiments between models as well as data types. The results demonstrate that both the GraphResLSTM model and road segment average speed data outperform other models and data types notably in OD prediction tasks.

This study develops a hybrid machine learning (ML) algorithm integrated with IoT technology to improve the accuracy and efficiency of soil monitoring and tomato crop disease prediction in Anakapalle, a south Indian station. An IoT device collected one-minute and critical soil parameters—humidity, temperature, pH values, nitrogen (N), phosphorus (P), and potassium (K)—essential for assessing soil health and optimizing crop growth. Kendall's correlations were computed to rank these parameters for utilization in hybrid ML techniques. Various ML algorithms including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Tree (DT), Random Forest (RF), and Logistic Regression (LR) were evaluated. A novel hybrid algorithm, 'Bayesian Optimization with KNN', was introduced to combine multiple ML techniques and enhance predictive performance. The hybrid algorithm demonstrated superior results with 95% accuracy, precision, and recall, and an F1 score of 94%, while individual ML algorithms achieved varying results: KNN (80% accuracy), SVM (82%), DT (77%), RF (80%), and LR (81%) with differing precision, recall, and F1 scores. This hybrid ML approach proved highly effective in predicting tomato crop diseases in natural environments, underscoring the synergistic benefits of IoT and advanced ML techniques in optimizing agricultural practices.

The philosophy of testing statistical hypothesis is a natural consequence and functional extension of mathematical analysis of Probability. Along with the concept of recurrence when applied to random sequences and functions, it leads to the analysis of a priori and posterior which implies testing statistical hypothesis. Testing statistical hypothesis also involves algebraic, functional and dimensional considerations, which are found in the works of Laplace. Aspects of mathematical analysis such as universality of solutions, Laws of Large Numbers, Entropy, Information, and various functional dependencies are the main factors explained in the five properties that lead to implication of testing statistical hypothesis. Various interesting examples with modern scientific significance from genetics, astrophysics, and other areas give methodological access to answers of different problems and phenomena which are involved in the logic of testing statistical hypothesis.