Extreme Gradient Research Articles

A Machine Learning-Based Prediction Model for Acute Kidney Injury in Patients With Community-Acquired Pneumonia: Multicenter Validation Study.

Acute kidney injury (AKI) is common in patients with community-acquired pneumonia (CAP) and is associated with increased morbidity and mortality. This study aimed to establish and validate predictive models for AKI in hospitalized patients with CAP based on machine learning algorithms. We trained and externally validated 5 machine learning algorithms, including logistic regression, support vector machine, random forest, extreme gradient boosting, and deep forest (DF). Feature selection was conducted using the sliding window forward feature selection technique. Shapley additive explanations and local interpretable model-agnostic explanation techniques were applied to the optimal model for visual interpretation. A total of 6371 patients with CAP met the inclusion criteria. The development of CAP-associated AKI (CAP-AKI) was recognized in 1006 (15.8%) patients. The 11 selected indicators were sex, temperature, breathing rate, diastolic blood pressure, C-reactive protein, albumin, white blood cell, hemoglobin, platelet, blood urea nitrogen, and neutrophil count. The DF model achieved the best area under the receiver operating characteristic curve (AUC) and accuracy in the internal (AUC=0.89, accuracy=0.90) and external validation sets (AUC=0.87, accuracy=0.83). Furthermore, the DF model had the best calibration among all models. In addition, a web-based prediction platform was developed to predict CAP-AKI. The model described in this study is the first multicenter-validated AKI prediction model that accurately predicts CAP-AKI during hospitalization. The web-based prediction platform embedded with the DF model serves as a user-friendly tool for early identification of high-risk patients.

Machine Learning Correlation of Electron Micrographs and ToF-SIMS for the Analysis of Organic Biomarkers in Mudstone.

The spatial distribution of organics in geological samples can be used to determine when and how these organics were incorporated into the host rock. Mass spectrometry (MS) imaging can rapidly collect a large amount of data, but ions produced are mixed without discrimination, resulting in complex mass spectra that can be difficult to interpret. Here, we apply unsupervised and supervised machine learning (ML) to help interpret spectra from time-of-flight-secondary ion mass spectrometry (ToF-SIMS) of an organic-carbon-rich mudstone of the Middle Jurassic of England (UK). It was previously shown that the presence of sterane molecular biomarkers in this sample can be detected via ToF-SIMS (Pasterski, M. J. et al., Astrobiology 2023, 23, 936). We use unsupervised ML on scanning electron microscopy-electron dispersive spectroscopy (SEM-EDS) measurements to define compositional categories based on differences in elemental abundances. We then test the ability of four ML algorithms─k-nearest neighbors (KNN), recursive partitioning and regressive trees (RPART), eXtreme gradient boost (XGBoost), and random forest (RF)─to classify the ToF-SIM spectra using (1) the categories assigned via SEM-EDS, (2) organic and inorganic labels assigned via SEM-EDS, and (3) the presence or absence of detectable steranes in ToF-SIMS spectra. In terms of predictive accuracy and balanced accuracy, KNN was the best performing model and RPART the worst. The feature importance, or the specific features of the ToF-SIM spectra used by the models to make classifications, cannot be determined for KNN, preventing posthoc model interpretation. Nevertheless, the feature importance extracted from the other models was useful for interpreting spectra. We determined that some of the organic ions used to classify biomarker containing spectra may be fragment ions derived from kerogen which is abundant in this mudstone sample.

Rain rate retrieval from Sentinel-1 synthetic aperture radar images during a tropical cyclone based on machine learning

In this paper, some algorithms for the rain rate from Sentinel-1 (S-1) synthetic aperture radar (SAR) images is proposed to increase the accuracy of rainfall retrieval during tropical cyclone (TC). The proposed algorithms contain the extreme gradient boosting (XGBoost), random forest (RF), and support vector regression (SVR). The SAR rain rate retrieval results using the XGBoost are validated against the GPMs data, yielding a root mean squared error (RMSE) of 2.43 mm h–1, correlation (COR) of 0.92, and scatter index (SI) of 0.65, which are better than the 5.3 mm h–1 RMSE, 0.51 COR, and 1.38 SI achieved using the re-tuned empirical model CRAIN2_S1, the RFof the 2.50 RMSE, 0.91 COR, and 0.67 SI, and the SVR model with a RMSE of 4.18, a COR of 0.73, and a SI of 1.11. It is concluded that the trained XGBoost is recommended for use in SAR rain rate retrieval during TCs.

Rapid diagnosis of power battery faults in new energy vehicles based on improved boosting algorithm and big data

In recent years, the new energy vehicle industry has developed rapidly. A fast diagnostic method based on Boosting and big data is proposed to address the low accuracy and efficiency of fault diagnosis in new energy vehicle power batteries. Boosting is a machine learning technique that combines multiple weak learners into a strong learner. Big data refers to large-scale, complex datasets that exceed traditional data processing capabilities. Firstly, analyze and preprocess the big data uploaded by the battery. Subsequently, the importance of indicators in the data was analyzed using the Random Forest algorithm (RF). Finally, three improved Boosting algorithms were proposed, namely Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting Tree (XGBoost), and Gradient Boosting Decision Tree (CatBoost). The experimental results indicate that the LightGBM model effectively detects anomalies in battery big data. The accuracy values of XGBoost, CatBoost, and LightGBM are 97.84%, 98.57%, and 99.16%, respectively. The recall rates of XGBoost, CatBoost, and LightGBM models are all 1. The F1 values of GBoost, CatBoost, and LightGBM are 0.873, 0.983, and 0.985, respectively. The power battery is the core component of new energy vehicles, and its safety performance directly affects the operational safety of the vehicle. Timely identification and diagnosis of battery faults can effectively reduce potential accidents such as battery overheating and short circuits. Research can achieve real-time monitoring and timely reminders of potential faults. By early detection of issues such as battery overheating and voltage imbalance, this method can effectively reduce the risk of serious safety accidents and improve the overall operational reliability of new energy vehicles during driving.

Exploring machine learning algorithms to predict not using modern family planning methods among reproductive age women in East Africa

BackgroundThe use of the modern family planning method provides chances for women to reach optimal child spacing, increase quality of life, increase economic status, achieve the desired family size, and prevent unsafe abortions and maternal and perinatal deaths. However, use modern family planning is low among reproductive age women in East Africa. Therefore, this study aimed at predicting not using modern family planning and identifying its associated factors among reproductive age women in east Africa using machine learning methods.MethodsThe data set was obtained from a demographic health survey in East Africa. This study used data on weighted sample of 92,564 women who were in their reproductive age. Python software was utilized for data processing, and machine learning models such as Random Forest (RF), Decision Tree (DT), XGB (Extreme Gradient Boosting), SVM (Support Victor Machine), and K-Nearest Neighbor Decision Tree (DT) were implemented. In this work, we evaluated the predictive models’ performance using performance assessment criteria such as accuracy, precision, recall, and the AUC curve.ResultIn this study, 92,564 reproductive women’s was used in the final analysis. Among the proposed machine learning models, XGB performed best overall in the proposed classifier, with an accuracy of 98.7%, precision of 99.8%, recall of 98%, 99.9% AUC score, had high specificity 98%, sensitivity 99.8%, and low error rate discovery was 0.013%. The most significant determinants of not using modern family planning in East Africa: lack of education, age 25–29, living in a rural area, being single, not knowing how to use a contraceptive, and smoking cigarette.ConclusionExtreme Gradient Boosting proved effective in predicting not using modern family planning, offering valuable insights for interventions and policy decisions in East Africa. Machine learning could help achieve early prediction and intervention on reproductive women’s not using modern family planning. This leads to a recommendation for policy direction to reduce child and maternal mortality and improve living standards in east Africa.

Machine learning models predict the progression of long-term renal insufficiency in patients with renal cancer after radical nephrectomy

BackgroundChronic Kidney Disease (CKD) is a common severe complication after radical nephrectomy in patients with renal cancer. The timely and accurate prediction of the long-term progression of renal function post-surgery is crucial for early intervention and ultimately improving patient survival rates.ObjectiveThis study aimed to establish a machine learning model to predict the likelihood of long-term renal dysfunction progression after surgery by analyzing patients’ general information in depth.MethodsWe retrospectively collected data of eligible patients from the Affiliated Hospital of Qingdao University. The primary outcome was upgrading of the Chronic Kidney Disease stage between pre- and 3-year post-surgery. We constructed seven different machine-learning models based on Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (Lightgbm), Gaussian Naive Bayes (GaussianNB), and K-Nearest Neighbors (KNN). The performance of all predictive models was evaluated using the area under the receiver operating characteristic curve (AUC), precision-recall curves, confusion matrices, and calibration curves.ResultsAmong 360 patients with renal cancer who underwent radical nephrectomy included in this study, 185 (51.3%) experienced an upgrade in Chronic Kidney Disease stage 3-year post-surgery. Eleven predictive variables were selected for further construction of the machine learning models. The logistic regression model provided the most accurate prediction, with the highest AUC (0.8154) and an accuracy of 0.787.

Data-Driven Modeling of Lateral and Cracking Loads in Confined Masonry Walls Using Machine Learning

Confined masonry (CM) is becoming a widely adopted construction building method even in earthquake-prone regions due to its economic viability, construction simplicity, and material availability. However, existing empirical models for predicting lateral and cracking loads often fall short due to varied material properties, detailing of confining elements and construction practices. In this study, machine learning (ML) algorithms, such as Extreme Gradient Boosting (XGB), Random Forest (RF), and Extremely Randomized Tree (ERT), were employed to predict the seismic performance of CM walls, focusing on maximum lateral load capacity and cracking load based on an experimental dataset from 84 published studies, with 59 samples for training and 25 for testing. Different material, load, geometrical, and reinforcement detailing, related to the lateral load capacity of CM, were considered. This study also compares the performance of the existing empirical equations against the proposed ML models. The ML models demonstrated strong predictive capabilities, outperforming empirical equations in both maximum lateral load and cracking load predictions, with XGBoost yielding the highest accuracy, reflected by R2 values of 0.903 for lateral load and 0.876 for cracking load predictions, and lowest the RMSE (28.742 for lateral and 23.982 for cracking load). Additionally, a comparative analysis shows that while some empirical equations produce reasonably accurate predictions, most exhibit significant deviations from experimental results. This study finally employs Partial Dependence Plot (PDP) analysis to explain the importance and contribution of the factors that influence the lateral strength, and concludes that ML models, especially XGBoost, are highly effective in capturing the complex behavior of CM walls under vertical and lateral loads, making them valuable tools for enhancing the accuracy of seismic performance evaluations.

Urban Built Environment as a Predictor for Coronary Heart Disease—A Cross-Sectional Study Based on Machine Learning

The relationship between coronary heart disease (CHD) and complex urban built environments remains a subject of considerable uncertainty. The development of predictive models via machine learning to explore the underlying mechanisms of this association, as well as the formulation of intervention policies and planning strategies, has emerged as a pivotal area of research. A cross-sectional dataset of hospital admissions for CHD over the course of a year from a hospital in Dalian City, China, was assembled and matched with multi-source built environment data via residential addresses. This study evaluates five machine learning models, including decision tree (DT), random forest (RF), eXtreme gradient boosting (XGBoost), multi-layer perceptron (MLP), and support vector machine (SVM), and compares them with multiple linear regression models. The results show that DT, RF, and XGBoost exhibit superior predictive capabilities, with all R2 values exceeding 0.70. The DT model performed the best, with an R2 value of 0.818, and the best performance was based on metrics such as MAE and MSE. Additionally, using explainable AI techniques, this study reveals the contribution of different built environment factors to CHD and identifies the significant factors influencing CHD in cold regions, ranked as age, Digital Elevation Model (DEM), house price (HP), sky view factor (SVF), and interaction factors. Stratified analyses by age and gender show variations in the influencing factors for different groups: for those under 60 years old, Road Density is the most influential factor; for the 61–70 age group, house price is the top factor; for the 71–80 age group, age is the most significant factor; for those over 81 years old, building height is the leading factor; in males, GDP is the most influential factor; and in females, age is the most influential factor. This study explores the feasibility and performance of machine learning in predicting CHD risk in the built environment of cold regions and provides a comprehensive methodology and workflow for predicting cardiovascular disease risk based on refined neighborhood-level built environment factors, offering scientific support for the construction of sustainable healthy cities.

Development and validation of a radiomics-based nomogram for predicting pathological grade of upper urinary tract urothelial carcinoma

BackgroundUpper urinary tract urothelial carcinoma (UTUC) is a rare and highly aggressive malignancy characterized by poor prognosis, making the accurate identification of high-grade (HG) UTUC essential for subsequent treatment strategies. This study aims to develop and validate a nomogram model using computed tomography urography (CTU) images to predict HG UTUC.MethodsA retrospective cohort study was conducted to include patients with UTUC who underwent radical nephroureterectomy and received a CTU examination prior to surgery. In the CTU images, tumor lesions located in the renal calyces, renal pelvis and ureter were segmented, and radiomics features from the unenhanced, medullary, and excretory phases were extracted. The maximum relevance minimum redundancy algorithm, least absolute shrinkage and selection operator, and various machine learning (ML) algorithms—including random forest, support vector machine, and eXtreme gradient boosting—were employed to select radiomics features and calculate radiomics scores. Logistic regression (LR) analysis was performed to identify the independent influencing factors of clinical baseline characteristics. Multiple datasets of radiomics features were constructed by integrating single-phase radiomics features with the most significant independent factor. Both LR and ML algorithms were utilized to develop predictive models. The area under the receiver operating characteristic curve (AUC values), accuracy, sensitivity, and specificity were assessed for model performance evaluation. Decision curve analysis was conducted to evaluate the clinical net benefits.ResultsA total of 167 patients were enrolled in this study. Among them, 56 were diagnosed with low-grade UTUC (including papillary urothelial neoplasms with low malignant potential and low-grade urothelial carcinoma) as confirmed by postoperative pathological examination results, and 111 were of HG. These patients were randomly allocated to the training set and the validation set at a ratio of 7:3. The training set comprised 116 patients with a mean age of 63.5 ± 9.38 years and 38 males. The validation set comprised 51 patients with a mean age of 65.6 ± 11.1 years and 18 males. Hydronephrosis was identified as the most significant independent factor in the clinical baseline features. Models that include mixed-phase development achieve better performance compared to models that rely simply on single-phase development. The nomogram model had excellent predictive ability for HG UTUC, with AUC values of 0.844 and an accuracy of 0.793 in the validation sets. The nomogram model can enhance accuracy by 14.1% (79.3% vs. 65.2%) and sensitivity by 32.8% (93.2% vs. 60.4%) compared to urinary cytology.ConclusionsThis study developed a nomogram model, which significantly improved the diagnostic ability for HG UTUC compared to urinary cytology. Furthermore, the results of the decision curve analysis showed that the model had a net benefit and could provide a non-invasive and potentially diagnostic reference tool for HG UTUC.

Radiomics and deep learning features of pericoronary adipose tissue on non-contrast computerized tomography for predicting non-calcified plaques

Background Inflammation of coronary arterial plaque is considered a key factor in the development of coronary heart disease. Early the plaque detection and timely treatment of the atherosclerosis could effectively reduce the risk of cardiovascular events. However, there is no study combining radiomics with deep learning techniques to predict non-calcified plaques (NCP) in coronary artery at present. Objective To investigate the value of combination of radiomics and deep learning features based on non-contrast computerized tomography (CT) scans of pericoronary adipose tissue (PCAT), integrating with clinical risk factors of patients, in identifying coronary inflammation and predicting the presence of NCP. Methods The clinical and imaging data of 353 patients were analyzed. The region of interest (ROI) of PCAT was manually outlined on non-contrast CT scan images, like coronary CT calcium score sequential images, then the radiomics and deep learning features in ROIs were extracted respectively. In training set (Center 1), after performing feature selection, radiomics and deep learning feature models were established, meanwhile, clinical models were built. Finally, combined models were developed out via integrating clinical, radiomics, and deep learning features. The predictive performance of the four feature model groups (clinical, radiomics, deep learning, and three combination) was assessed by seven different machine learning models through generation of receiver operating characteristic curves (ROC) and the calculation of area under the curve (AUC), sensitivity, specificity, and accuracy. Furthermore, the predictive performance of each model was validated in an external validation set (Center 2). Results For the single model comparation, eXtreme Gradient Boosting (XGBoost) showed the best performance among the clinical model group in the validation set. And Random Forest (RF) exhibited the best indicative performance not only among the radiomics feature group but also in the deep learning feature model group. What's more, among the combined model group, RF still displayed the best predictive performance, with the value of AUC, sensitivity, specificity, and accuracy in the validation set are 0.963, 0.857, 0.929, and 0.905. Conclusion The RF model in the combined model group based on non-contrast CT scan PCAT can predict the presence of NCP more accurately and has the potential for preliminary screening of the NCP.

Predicting maternal risk level using machine learning models

BackgroundMaternal morbidity and mortality remain critical health concerns globally. As a result, reducing the maternal mortality ratio (MMR) is part of goal 3 in the global sustainable development goals (SDGs), and previously, it was an important indicator in the Millennium Development Goals (MDGs). Therefore, identifying high-risk groups during pregnancy is crucial for decision-makers and medical practitioners to mitigate mortality and morbidity. However, the availability of accurate predictive models for maternal mortality and maternal health risks is challenging. Compared with traditional predictive models, machine learning algorithms have emerged as promising predictive modelling methods providing accurate predictive models.MethodsThis work aims to explore the potential of machine learning (ML) algorithms in maternal risk level prediction using a nationwide maternal mortality dataset from Oman for the first time. A total of 402 maternal deaths from 1991 to 2023 in Oman were included in this study. We utilised principal component analysis (PCA) in the ML algorithms and compared them to the results of model performance without PCA. We employed and compared ten ML algorithms, including decision tree (DT), random forest (RF), K—Nearest Neighbors (KNN), Naïve Bayes (NB), Extreme Gradient Boosting (xgboost), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), Support Vector Machine (SVM) and Artificial Neural Network (ANN). Different metrics, including, accuracy, sensitivity, precision, and the F1- score, were utilised to assess Model performance.ResultsThe results indicated that the RF model outperformed the other methods in predicting the risk level (low or high) with an accuracy of 75.2%, precision of 85.7% and F1- score of 73% after PCA was applied.ConclusionsWe applied several machine learning models to predict maternal risk levels for the first time using real data from Oman. RF outperformed the other algorithms in this classification problem. A reliable estimate of maternal risk level would facilitate intervention plans for medical practitioners to reduce maternal death.

Core genes and immune dysregulation in primary open-angle glaucoma: A molecular insight

Background Primary open-angle glaucoma (POAG) is a chronic, progressive and irreversible eye disease. Currently, there is no effective way to prevent optic nerve damage. Objective This study explored POAG gene markers to identify high-risk groups at an early stage and to find new effective therapeutic targets. Methods The mRNA and clinical information of POAG patients and normal samples were downloaded from the Gene Expression Omnibus (GEO) database. Through Weighted correlation network analysis (WGCNA) and generalized linear models (GLM), random forests (RF), support vector machines (SVM), and extreme gradient boosting (xGB) models, key risk genes were identified and an early diagnosis model was established. Functional enrichment analysis and CIBERSORT algorithm were used to further reveal the changes in the POAG immune environment and find emerging therapeutic targets. Results HERPUD1, IQCK, MRPL40, SRSF7 and TMEM243 were identified as risk genes, and the prediction model and nomogram constructed based on them had good early prediction efficiency. At the mechanistic level, the heterogeneity of T cell subsets seems to be a key factor affecting the progression of POAG and has potential therapeutic value. Conclusions HERPUD1, IQCK, MRPL40, SRSF7, and TMEM243 are of great significance for the early prediction and disease progression of POAG and have the potential value of becoming therapeutic targets.

Auxiliary identification of depression patients using interpretable machine learning models based on heart rate variability: a retrospective study

ObjectiveDepression has emerged as a global public health concern with high incidence and disability rates, which are timely imperative to identify and intervene in clinical practice. The objective of this study was to explore the association between heart rate variability (HRV) and depression, with the aim of establishing and validating machine learning models for the auxiliary diagnosis of depression.MethodsThe data of 465 outpatients from the Affiliated Hospital of Southwest Medical University were selected for the study. The study population was then randomly divided into training and test sets in a 7:3 ratio. Logistic regression (LR), support vector machine (SVM), random forest (RF) and eXtreme gradient boosting (XGBoost) algorithm models were used to construct risk prediction models in the training set, and the model performance was verified in the test set. The four models were evaluated by the area under the receiver operating characteristic curve (ROC), calibration curve and the decision curve analysis (DCA). Furthermore, we employed the SHapley Additive exPlanations (SHAP) method to illustrate the effects of the features attributed to the model.ResultsThere were 237 people in the depressed group and 228 in the non-depressed group. In the training set (n = 325) and test set (n = 140), the area under of the curve(AUC) values of the XGBoost model are 0.92 [95% confidence interval (CI) 0.888,0.95] and 0.82 (95% CI 0.754,0.892)] respectively, which are higher than the other three models. The XGBoost model has excellent predictive efficacy and clinical utility. The SHAP method was ranked according to the importance of the degree of influence on the model, with age, heart rate, Standard deviation of the NN intervals (SDNN), two nonlinear parameters of HRV and sex considered to be the top 6 predictors.ConclusionWe provided a feasibility study of HRV as a potential biomarker for depression. The proposed model based on HRV provides clinicians with a quantitative auxiliary diagnostic tool, which is assist to improving the accuracy and efficiency of depression diagnosis, and can also be utilized for the monitoring and prevention of depression.

Enhanced forecasting of emergency department patient arrivals using feature engineering approach and machine learning

BackgroundEmergency department (ED) overcrowding is an important problem in many countries. Accurate predictions of ED patient arrivals can help management to better allocate staff and medical resources. In this study, we investigate the use of calendar and meteorological predictors, as well as feature-engineered variables, to predict daily patient arrivals using datasets from eleven different EDs across three countries.MethodsSix machine learning (ML) algorithms were tested on forecasting horizons of 7 and 45 days. Three of them – Light Gradient Boosting Machine (LightGBM), Support Vector Machine with Radial Basis Function (SVM-RBF), and Neural Network Autoregression (NNAR) – were never before reported for predicting ED patient arrivals. Algorithms’ hyperparameters were tuned through a grid-search with cross-validation. Prediction performance was assessed using fivefold cross-validation and four performance metrics.ResultsThe eXtreme Gradient Boosting (XGBoost) was the best-performing model on both prediction horizons, also outperforming results reported in past studies on ED arrival prediction. XGBoost and NNAR achieved the best performance in nine out of the eleven analyzed datasets, with MAPE values ranging from 5.03% to 14.1%. Feature engineering (FE) improved the performance of the ML algorithms.ConclusionAccuracy in predicting ED arrivals, achieved through the FE approach, is key for managing human and material resources, as well as reducing patient waiting times and lengths of stay.

Predicting Intensive Care Unit Admission in COVID-19-Infected Pregnant Women Using Machine Learning

Background: The rapid onset of COVID-19 placed immense strain on many already overstretched healthcare systems. The unique physiological changes in pregnancy, amplified by the complex effects of COVID-19 in pregnant women, rendered prioritization of infected expectant mothers more challenging. This work aims to use state-of-the-art machine learning techniques to predict whether a COVID-19-infected pregnant woman will be admitted to ICU (Intensive Care Unit). Methods: A retrospective study using data from COVID-19-infected women admitted to one hospital in Astana and one in Shymkent, Kazakhstan, from May to July 2021. The developed machine learning platform implements and compares the performance of eight binary classifiers, including Gaussian naïve Bayes, K-nearest neighbors, logistic regression with L2 regularization, random forest, AdaBoost, gradient boosting, eXtreme gradient boosting, and linear discriminant analysis. Results: Data from 1292 pregnant women with COVID-19 were analyzed. Of them, 10.4% were admitted to ICU. Logistic regression with L2 regularization achieved the highest F1-score during the model selection phase while achieving an AUC of 0.84 on the test set during the evaluation stage. Furthermore, the feature importance analysis conducted by calculating Shapley Additive Explanation values points to leucocyte counts, C-reactive protein, pregnancy week, and eGFR and hemoglobin as the most important features for predicting ICU admission. Conclusions: The predictive model obtained here may be an efficient support tool for prioritizing care of COVID-19-infected pregnant women in clinical practice.

Analysis of cellular and molecular biomechanical correlates in emotional response monitoring via biosensors and their impact on teaching strategy modification in Japanese language instruction

Emotion states have a significant impact on language acquisition and learning outcomes. In Japanese language teaching, traditional strategies often overlook students' emotional responses, which can lead to stress and disengagement, affecting performance. To address this, the study focuses on incorporating bio-sensor-based emotional reaction monitoring. At the cellular and molecular biomechanical level, emotions can trigger a cascade of physiological changes. For example, stress can activate the hypothalamic-pituitary-adrenal (HPA) axis, leading to the release of stress hormones like cortisol. These hormonal changes can affect neurotransmitter systems and cellular signaling pathways in the brain, influencing cognitive functions related to language learning. During Japanese language sessions, teachers' emotional states are recorded using surveys and EEG monitoring. The EEG signals can provide insights into the neural activity and related cellular and molecular events. Participants are divided into experimental and control groups. In the experimental group, teaching strategies are adjusted based on emotional monitoring data. The Extreme Gradient Boosting (XGBoost) model classifier is used for EEG signal feature selection to create a stress level identification model. This model can help in understanding the cellular and molecular correlates of stress during teaching. Statistical analysis evaluates the relationship between EEG features and stress levels, as well as the effectiveness of adjusted teaching strategies. Tailored teaching strategies based on these insights can enhance teacher resilience and improve the classroom environment. By considering the cellular and molecular biomechanical aspects of emotions, the study aims to improve teacher well-being and student learning experiences, leading to more effective Japanese language instruction.

On the use of meteorological parameters and satellite image-based indices for improving solar radiation estimation.

Solar radiation (Rs) is a major renewable energy source and also a crucial factor in designing solar panels, determining water requirement, and irrigation scheduling. In this study, meteorological parameters (air temperature, average air temperature, and relative humidity; Scenario 1), satellite image-based indices (normalized difference vegetation index: NDVI and land surface temperature: LST; Scenario 2), and their combination (Scenario 3) were used as predictors of Rs simulator models in Mashhad watershed (2005-2015). To this end, three different transfer function algorithms of the multi-layer perceptron (MLP), namely Levenberg-Marquardt backpropagation (MLP-LVM), gradient descend backpropagation (MLP-GDB), and batch training with weight and bias learning rules (MLP-BTWB), as well as two other machine learning models, M5 Tree and XGB (eXtreme Gradient Boosting), were employed. In addition, hybrid models obtained through coupling the best MLP transfer function with genetic algorithm (MLP-LVM-GA) and coupling Variational Mode Decomposition with M5 Tree and XGB (VMD-M5 Tree and VMD-XGB, respectively) were also investigated. In the case of MLP-based models, the third scenario proved to be more efficient, with RMSEs equal to 404.2, 424.5, and 423.8J.cm-2.day-1 for the aforementioned transfer functions, respectively. The results showed that GA coupled with the best transfer function algorithm of MLP improved Rs estimates, decreasing estimation error by 14.7, 30.65, and 32.67% in the three defined scenarios, respectively. In training set, VMD-M5 Tree and VMD-XGB hybrid models outperformed corresponding base models under all three scenarios; but in testing set, estimation error was decreased only in the third scenario (by 37 and 42%, respectively). Overall, all models (base and hybrid) had the least Rs estimation errors in the third scenario (application of both meteorological parameters and satellite image-based data).

Mapping Soil Properties in Tropical Rainforest Regions Using Integrated UAV-Based Hyperspectral Images and LiDAR Points

For tropical rainforest regions with dense vegetation cover, the development of effective large-scale soil mapping methods is crucial to improve soil management practices to replace the time-consuming and laborious conventional approaches. While machine learning (ML) algorithms demonstrate superior predictability of soil properties over linear models, their practical and automated application for predicting soil properties using remote sensing data requires further assessment. Therefore, this study aims to integrate Unmanned Aerial Vehicles (UAVs)-based hyperspectral images and Light Detection and Ranging (LiDAR) points to predict the soil properties indirectly in two tropical rainforest mountains (Diaoluo and Limu) in Hainan Province, China. A total of 175 features, including texture features, vegetation indices, and forest parameters, were extracted from two study sites. Six ML models, Partial Least Squares Regression (PLSR), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP), were constructed to predict soil properties, including soil acidity (pH), total nitrogen (TN), soil organic carbon (SOC), and total phosphorus (TP). To enhance model performance, a Bayesian optimization algorithm (BOA) was introduced to obtain optimal model hyperparameters. The results showed that compared with the default parameter tuning method, BOA always improved models’ performances in predicting soil properties, achieving average R2 improvements of 202.93%, 121.48%, 8.90%, and 38.41% for soil pH, SOC, TN, and TP, respectively. In general, BOA effectively determined the complex interactions between hyperparameters and prediction features, leading to an improved model performance of ML methods compared to default parameter tuning models. The GBDT model generally outperformed other ML methods in predicting the soil pH and TN, while the XGBoost model achieved the highest prediction accuracy for SOC and TP. The fusion of hyperspectral images and LiDAR data resulted in better prediction of soil properties compared to using each single data source. The models utilizing the integration of features derived from hyperspectral images and LiDAR data outperformed those relying on one single data source. In summary, this study highlights the promising combination of UAV-based hyperspectral images with LiDAR data points to advance digital soil property mapping in forested areas, achieving large-scale soil management and monitoring.

Mitigating saturation effects in rice nitrogen estimation using Dualex measurements and machine learning

Nitrogen is essential for rice growth and yield formation, but traditional methods for assessing nitrogen status are often labor-intensive and unreliable at high nitrogen levels due to saturation effects. This study evaluates the effectiveness of flavonoid content (Flav) and the Nitrogen Balance Index (NBI), measured using a Dualex sensor and combined with machine learning models, for precise nitrogen status estimation in rice. Field experiments involving 15 rice varieties under varying nitrogen application levels collected Dualex measurements of chlorophyll (Chl), Flav, and NBI from the top five leaves at key growth stages. Incremental analysis was performed to quantify saturation effects, revealing that chlorophyll measurements saturated at high nitrogen levels, limiting their reliability. In contrast, Flav and NBI remained sensitive across all nitrogen levels, accurately reflecting nitrogen status. Machine learning models, particularly random forest and extreme gradient boosting, achieved high prediction accuracy for leaf and plant nitrogen concentrations (R2 > 0.82), with SHAP analysis identifying NBI and Flav from the top two leaves as the most influential predictors. By combining Flav and NBI measurements with machine learning, this approach effectively overcomes chlorophyll-based saturation limitations, enabling precise nitrogen estimation across diverse conditions and offering practical solutions for improved nitrogen management in rice cultivation.

Ultimate load bearing of helical piles prediction and evaluation using machine learning-based algorithms

ABSTRACT This study aims to predict the Ultimate Load-Bearing (ULB) capacity of Helical Piles (HP) using six Machine Learning Algorithms (MLA) on an in situ-based 110 pile load tests including a wide range of pile properties: shaft diameters (73–406 mm), helix diameters (254–762 mm), helix spacing (300–1000 mm), number of helices (1–6), pile lengths (2.4–16 m), and helix thicknesses (6–12 mm). The measured axial ULB is analysed using the Brinch-Hansen 80% criterion and 5% criterion of the average diameter of the helices. Load-displacement curves were fitted using the Hyperbolic Function. MLA including Multi Linear Regression (MLR), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest, eXtreme Gradient Boosting, and Support Vector Regression were optimised to grid search for hyperparameters like neighbour count, tree depth, learning rate, and kernel type. Input parameters were categorised into Geometric and Soil Properties packages. Results indicate that the DT algorithm excelled in pullout loading, KNN in compression loading, and MLR for Brinch-Hansen 80% criterion estimations. The input parameters related to the soil surrounding the pile helices have the most impact on the ULB prediction of HP. This study enhances HP foundation design by enabling data-driven decisions for optimal pile selection and configuration.