Search Results (905)

Earthquakes are sudden and destructive natural events caused by tectonic movements in the Earth’s crust. Although they cannot be predicted with certainty, rapid and reliable detection is essential to reduce loss of life and property. This study aims to automatically distinguish earthquake and noise signals from real seismic data by analyzing time-frequency features. Signals were scaled using z-score normalization, and extracted with Empirical Mode Decomposition (EMD), Discrete Wavelet Transform (DWT), and combined EMD+DWT methods. Feature selection methods such as Lasso, ReliefF, and Student’s t-test were applied to identify the most discriminative features. Classification was performed with Ensemble Bagged Trees, Decision Trees, Random Forest, k-Nearest Neighbors (k-NN), and Support Vector Machines (SVM). The highest performance was achieved using the RF classifier with the Lasso-based EMD+DWT feature set, reaching 100% accuracy, specificity, and sensitivity. Overall, DWT and EMD+DWT features yielded higher performance than EMD alone. While k-NN and SVM were less effective, tree-based methods achieved superior results. Moreover, Lasso and ReliefF outperformed Student’s t-test. These findings show that time-frequency-based features are crucial for separating earthquake signals from noise and provide a basis for improving real-time detection. The study contributes to the academic literature and holds significant potential for integration into early warning and earthquake monitoring systems. Full article

This study aims to evaluate the ability of an artificial intelligence (AI) model developed for use in the field of orthodontics to accurately and reliably classify skeletal maturation stages of individuals using hand–wrist radiographs. A total of 809 grayscale hand–wrist radiographs (250 × 250 px; pre-peak n = 400, peak n = 100, post-peak n = 309) were analyzed using four complementary image-based feature extraction methods: Local Binary Pattern (LBP), Histogram of Oriented Gradients (HOG), Zernike Moments (ZM), and Intensity Histogram (IH). These methods generated 2355 features per image, of which 2099 were retained after variance thresholding. The most informative 1250 features were selected using the ANOVA F-test and classified with a stacking-based machine learning (ML) architecture composed of Light Gradient Boosting Machine (LightGBM) and Logistic Regression (LR) as base learners, and Random Forest (RF) as the meta-learner. Across all evaluation folds, the average performance of the model was Accuracy = 83.42%, Precision = 84.48%, Recall = 83.42%, and F1 = 83.50%. The proposed model achieved 87.5% accuracy, 87.8% precision, 87.5% recall, and an F1-score of 87.6% in 10-fold cross-validation, with a macro-average area under the ROC curve (AUC) of 0.96. The pre-peak stage, corresponding to the period of maximum growth velocity, was identified with 92.5% accuracy. These findings indicate that integrating handcrafted radiographic features with ensemble learning can enhance diagnostic precision, reduce observer variability, and accelerate evaluation. The model provides an interpretable and clinically applicable AI-based decision-support tool for skeletal maturity assessment in orthodontic practice. Full article

Cotton leaf mites are pests that cause irreparable damage to cotton and pose a severe threat to the cotton yield, and the application of unmanned aerial vehicles (UAVs) to monitor the incidence of cotton leaf mites across a vast region is important for cotton leaf mite prevention. In this work, 52 vegetation indices were calculated based on the original five bands of spliced UAV multispectral images, and six featured indices were screened using Shapley value theory. To classify and identify cotton leaf mite infestation classes, seven machine learning classification models were used: random forest (RF), support vector machine (SVM), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), K-Nearest Neighbors (KNN), decision tree (DT), and gradient boosting decision tree (GBDT) models. The base model and metamodel used in stacked models were built based on a combination of four models, namely, the XGB, GBDT, KNN, and DT models, which were selected in accordance with the heterogeneity principle. The experimental results showed that the stacked classification models based on the XGB, KNN base model, and DT metamodel were the best performers, outperforming other integrated and single individual models, with an overall accuracy of 85.7% (precision: 93.3%, recall: 72.6%, and F1-score: 78.2% in the macro_avg case; precision: 88.6%, recall: 85.7%, and F1 score: 84.7% in the weighted_avg case). This approach provides support for using UAVs to monitor the cotton leaf mite prevalence over vast regions. Full article

Background/Objective: Esophageal cancer (EC) is a major global health issue due to its high mortality rate, as patients are often diagnosed at advanced stages. This research examines whether the Spectrum-Aided Vision Enhancer (SAVE), a hyperspectral imaging (HSI) technique, enhances endoscopic image categorization for superior diagnostic outcomes compared to traditional White Light Imaging (WLI) and Narrow Band Imaging (NBI). Methods: A dataset including 2400 photos categorized into eight disease types from National Taiwan University Hospital Yun-Lin Branch was utilized. Multiple machine learning and deep learning models were developed, including logistic regression, VGG16, YOLOv8, and MobileNetV2. SAVE was utilized to transform WLI photos into hyperspectral representations, and band selection was executed to enhance feature extraction and improve classification outcomes. The training and evaluation of the model incorporated precision, recall, F1-score, and accuracy metrics across WLI, NBI, and SAVE modalities. Results: The research findings indicated that SAVE surpassed both NBI and WLI by achieving superior precision, recall, and F1-scores. Logistic regression and VGG16 performed with a comparable reliability to SAVE and NBI, whereas MobileNetV2 and YOLOv8 demonstrated inconsistent yet enhanced results. Overall, SAVE exhibited exceptional categorization precision and recall, showcasing impeccable performance across many models. Conclusions: This research indicates that AI hyperspectral imaging facilitates early diagnosis of esophageal diseases, hence enhancing clinical decision-making and improving patient outcomes. The amalgamation of SAVE with machine learning and deep learning models enhances diagnostic capabilities, with SAVE and NBI surpassing WLI by offering superior tissue differentiation and diagnostic accuracy. Full article

The state of Bahia in Brazil possesses significant, yet underexploited, iron ore reserves. To support the initial stages of mineral exploration in this vast region, cost-effective and rapid large-scale mapping methods are essential. This paper presents a workflow based on publicly available remote sensing data for a state mineral prospectivity mapping (MPM) for iron. The methodology employs a Random Forest (RF) classification model on Sentinel-2 multispectral images, trained with a randomly selected dataset in the image at varying distances defined from the location of known iron mines in the state. The Spectral Angle Mapper (SAM) algorithm was used to categorize the samples according to spectral similarity features with laboratory-confirmed ore signatures from samples collected in the mine pit area. The resulting MPM successfully delineated known iron districts and highlighted new, unexplored areas with potential. A quantitative evaluation of the model yielded an overall accuracy of 69.8%, a macro-average F1-score of 0.697, and a Cohen’s Kappa coefficient of 0.623, indicating a reasonable agreement beyond random chance. This work demonstrates a validated, low-cost, and simple approach for regional-scale MPM, offering a valuable reconnaissance tool for preliminary exploration, particularly in extensive and data-scarce regions. Full article

Chronic kidney disease (CKD) impacts over 850 million people globally, representing a critical public health issue, yet existing risk assessment methodologies inadequately address the complexity of disease progression trajectories. Traditional machine learning approaches encounter critical limitations including inefficient hyperparameter selection and lack of clinical transparency, hindering their deployment in healthcare settings. This study introduces an innovative computational framework that integrates adaptive Multi-Armed Bandit (MAB) strategies with BorderlineSMOTE sampling techniques to improve CKD risk assessment. The proposed methodology leverages XGBoost within an ensemble learning paradigm enhanced by Upper Confidence Bound exploration strategy, coupled with a comprehensive interpretability system incorporating SHAP and LIME analytical tools to ensure model transparency. To address the challenge of algorithmic interpretability while maintaining clinical utility, a four-level risk categorization framework was developed, employing cross-validated stratification methods and balanced performance evaluation metrics, thereby ensuring fair predictive accuracy across diverse patient populations and minimizing bias toward dominant risk categories. Through rigorous empirical evaluation on clinical datasets, we performed extensive comparative analysis against sixteen established algorithms using paired statistical testing with Bonferroni correction. The MAB-optimized framework achieved superior predictive performance with accuracy of 91.8%, F1-score of 91.0%, and ROC-AUC of 97.8%, demonstrating superior performance within the evaluated cohort of reference algorithms (p-value < 0.001). Remarkably, our optimized framework delivered nearly ten-fold computational efficiency gains relative to conventional grid search methods while preserving robust classification performance. Feature importance analysis identified albumin-to-creatinine ratio, eGFR measurements, and CKD staging as dominant prognostic factors, demonstrating concordance with established clinical nephrology practice. This research addresses three core limitations in healthcare artificial intelligence: optimization computational cost, model interpretability, and consistent performance across heterogeneous clinical populations, offering a practical solution for improved CKD risk stratification in clinical practice. Full article

Background: Metabolic syndrome (MetS) is a rising public health concern in Southern China, with limited evidence available on dietary and metabolic factors. This cross-sectional study employed an interpretable machine learning (ML) approach to identify factors that could inform clinical and community interventions. Methods: Data were obtained from the Guangdong Nutrition Surveys conducted in 2015 and 2022, including sociodemographic information, lifestyle patterns, physical examinations, laboratory measurements and dietary intake information (collected via repeated 24-h dietary recalls). Potentially relevant variables were selected using the Least Absolute Shrinkage and Selection Operator (LASSO) regression and incorporated into seven ML models. Model performance was primarily assessed using the area under the receiver operating characteristic curve (AUC), and the contribution of identified features was interpreted through SHapley Additive exPlanations (SHAP). Results: This analysis included 5593 participants, of whom 1103 were classified as having MetS. After removing collinear features, the ML models retained 19 candidate variables, which were selected through LASSO regression. XGBoost achieved the best performance (AUC: 0.834; F1 score: 0.537) with a misclassification rate of 27.1%. SHAP analysis highlighted body mass index (BMI), age, and uric acid levels as major risk factors, while insoluble dietary fiber, carbohydrate and specific micronutrients exhibited protective associations. Conclusions: Machine learning identified key dietary and metabolic factors of MetS. Integrating these factors into clinical practice and public health initiatives may enhance early detection and support personalized prevention strategies for MetS in Southern China. Full article

Dengue is a life-threatening disease that is transmitted by mosquitoes. Dengue fever has no proper treatment. Early, proper diagnosis is essential to minimize complications and enhance outcomes in patients. This research uses a clinical and hematological dataset of dengue to assess the effectiveness of the Gradient Boosting (GB) classification model with and without feature selection. It initially employs a standalone GB model, achieving impeccable results for classification, at 100% accuracy, F1-score, precision, and recall. In addition, the Bird Swarm Algorithm (BSA)-based metaheuristic technique is implemented on the GB classifier to execute wrapper-based feature selection so that features are reduced and achieve better results. The BSA-GB model yielded an accuracy of 99.49%, F1-score of 99.62%, recall of 99.24%, and precision of 100%, but it only selected five features in total. An additional test with a five-fold cross-validation was employed for better performance and model evaluation. Folds 1 and 2 showed especially good results. Although fold 2 selected only four features, it still showed high results, compared to fold 1, which selected five features. In this context, fold 2 achieved an accuracy of 99.49%, F1-score of 99.65%, recall of 99.30%, and precision of 100%. Means of hyperparameters were also calculated across folds to make a generalized GB model, which maintained 99.49% of accuracy with just three features, namely, Hemoglobin, WBC Count, and Platelet Count. To enhance transparency, counterfactual explanations were performed to analyze the misclassified cases, which indicated that minimum changes in input features modify the predictions. Also, an evaluation of the SHAP value result designated WBC Count and Platelet Count as the most important features. Full article

Intrusion Detection Systems (IDS) are vital to cybersecurity but suffer from severe class imbalance in benchmark datasets such as NSL-KDD and UNSW-NB15. Conventional oversampling methods (e.g., SMOTE, ADASYN) are efficient yet fail to preserve the latent semantics of rare attack behaviors. This study introduces the Minority-class Intrusion Detection Synthesizer GAN (MIDS-GAN), a divergence-minimization framework for minority data augmentation under structured feature constraints. MIDS-GAN integrates (i) correlation-based structured feature selection (SFS) to reduce redundancy, (ii) trainable ACON activations to enhance generator expressiveness, and (iii) KL-divergence-guided alignment to ensure distributional fidelity. Experiments on NSL-KDD and UNSW-NB15 demonstrate significant improvement on detection, with recall increasing from 2% to 27% for R2L and 1% to 17% for U2R in NSL-KDD, and from 18% to 44% for Worms and 69% to 75% for Shellcode in UNSW-NB15. Weighted F1-scores also improved to 78%, highlighting MIDS-GAN’s effectiveness in enhancing minority-class detection through a principled, divergence-aware approach. Full article

Postpartum haemorrhage is one of the leading causes of maternal morbidity and mortality worldwide. The early identification of bleeding risk in individual women is crucial for enabling timely interventions and improving patient outcomes.This study aims to evaluate various exploratory and classification methodologies, alongside optimisation strategies, for identifying predictors of postpartum haemorrhage. K-means clustering was employed on a retrospective cohort of patients, incorporating demographic, obstetric, and laboratory variables, to delineate patient profiles and select pertinent features. Initially, a classical logistic regression model, implemented without cross-validation, facilitated the identification of six significant predictors for postpartum haemorrhage: lactate dehydrogenase, urea, platelet count, non-O blood group, gestational age, and first-degree lacerations, all of which are variables routinely available in clinical practice. Furthermore, machine learning algorithms—including stepwise logistic regression, ridge logistic regression, and random forest—were utilised, applying cross-validation to optimise predictive performance and enhance generalisability. Among these methodologies, ridge logistic regression emerged as the most effective model, achieving the following metrics: sensitivity 0.857, specificity 0.875, accuracy 0.871, F1-score 0.759, and AUC 0.907. While machine learning techniques demonstrated superior performance, the integration of classical statistical methods with machine learning approaches provides a robust framework for generating reliable predictions and fostering significant clinical insights. Full article

Background: The automated analysis of intestinal organoids in microscopy images are essential for high-throughput morphological studies, enabling precision and scalability. Traditional manual analysis is time-consuming and subject to observer bias, whereas Machine Learning (ML) approaches have recently demonstrated superior performance. Purpose: This study aims to evaluate YOLO (You Only Look Once) for organoid segmentation and classification, comparing its standalone performance with a hybrid pipeline that integrates DL-based feature extraction and ML classifiers. Methods: The dataset, consisting of 840 light microscopy images and over 23,000 annotated intestinal organoids, was divided into training (756 images) and validation (84 images) sets. Organoids were categorized into four morphological classes: cystic non-budding organoids (Org0), early organoids (Org1), late organoids (Org3), and Spheroids (Sph). YOLO version 10 (YOLOv10) was trained as a segmenter-classifier for the detection and classification of organoids. Performance metrics for YOLOv10 as a standalone model included Average Precision (AP), mean AP at 50% overlap (mAP50), and confusion matrix evaluated on the validation set. In the hybrid pipeline, trained YOLOv10 segmented bounding boxes, and features extracted from these regions using YOLOv10 and ResNet50 were classified with ML algorithms, including Logistic Regression, Naive Bayes, K-Nearest Neighbors (KNN), Random Forest, eXtreme Gradient Boosting (XGBoost), and Multi-Layer Perceptrons (MLP). The performance of these classifiers was assessed using the Receiver Operating Characteristic (ROC) curve and its corresponding Area Under the Curve (AUC), precision, F1 score, and confusion matrix metrics. Principal Component Analysis (PCA) was applied to reduce feature dimensionality while retaining 95% of cumulative variance. To optimize the classification results, an ensemble approach based on AUC-weighted probability fusion was implemented to combine predictions across classifiers. Results: YOLOv10 as a standalone model achieved an overall mAP50 of 0.845, with high AP across all four classes (range 0.797–0.901). In the hybrid pipeline, features extracted with ResNet50 outperformed those extracted with YOLO, with multiple classifiers achieving AUC scores ranging from 0.71 to 0.98 on the validation set. Among all classifiers, Logistic Regression emerged as the best-performing model, achieving the highest AUC scores across multiple classes (range 0.93–0.98). Feature selection using PCA did not improve classification performance. The AUC-weighted ensemble method further enhanced performance, leveraging the strengths of multiple classifiers to optimize prediction, as demonstrated by improved ROC-AUC scores across all organoid classes (range 0.92–0.98). Conclusions: This study demonstrates the effectiveness of YOLOv10 as a standalone model and the robustness of hybrid pipelines combining ResNet50 feature extraction and ML classifiers. Logistic Regression emerged as the best-performing classifier, achieving the highest ROC-AUC across multiple classes. This approach ensures reproducible, automated, and precise morphological analysis, with significant potential for high-throughput organoid studies and live imaging applications. Full article

Driver emotion recognition is vital for intelligent driver assistance systems, where the accurate detection of emotional states enhances both safety and user experience. Current approaches, however, require extensive labeled datasets, perform poorly under real-world conditions, and degrade with class imbalance. To overcome these challenges, we propose the Active Learning and Deep Attention Mechanism (ALDAM) framework. ALDAM introduces three key innovations: (1) an active learning cycle that reduces labeling effort by ~40%; (2) a weighted-cluster loss that mitigates class imbalance; and (3) a deep attention mechanism that strengthens feature selection under occlusion, pose variation, and illumination changes. Evaluated on four benchmark datasets (FER-2013, AffectNet, CK+, and EMOTIC), ALDAM achieves an average accuracy of 97.58%, F1-score of 98.64%, and AUC of 98.76% surpassing CNN-based models and advanced baselines such as SE-ResNet-50. These results establish ALDAM as a robust and efficient solution for real-time driver emotion recognition. Full article

Objective: Axillary lymph node (ALN) status in breast cancer is pivotal for guiding treatment and determining prognosis. The study aimed to explore the feasibility and efficacy of a radiomics model using voxel-wise dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) time-intensity-curve (TIC) profile maps to predict ALN metastasis in breast cancer. Methods: A total of 615 breast cancer patients who underwent preoperative DCE-MRI from October 2018 to February 2024 were retrospectively enrolled and randomly allocated into training (n = 430) and testing (n = 185) sets (7:3 ratio). Based on wash-in rate, wash-out enhancement, and wash-out stability, each voxel within manually segmented 3D lesions that were categorized into 1 of 19 TIC subtypes from the DCE-MRI images. Three feature sets were derived: composition ratio (type-19), radiomics features of TIC subtypes (type-19-radiomics), and radiomics features of third-phase DCE-MRI (phase-3-radiomics). Student’s t-test and the least absolute shrinkage and selection operator (LASSO) was used to select features. Four models (type-19, type-19-radiomics, type-19-combined, and phase-3-radiomics) were constructed by a support vector machine (SVM) to predict ALN status. Model performance was assessed using sensitivity, specificity, accuracy, F1 score, and area under the curve (AUC). Results: The type-19-combined model significantly outperformed the phase-3-radiomics model (AUC = 0.779 vs. 0.698, p < 0.001; 0.674 vs. 0.559) and the type-19 model (AUC = 0.779 vs. 0.541, p < 0.001; 0.674 vs. 0.435, p < 0.001) in cross-validation and independent testing sets. The type-19-radiomics showed significantly better performance than the phase-3-radiomics model (AUC = 0.764 vs. 0.698, p = 0.002; 0.657 vs. 0.559, p = 0.037) and type-19 model (AUC = 0. 764 vs. 0.541, p < 0.001; 0.657 vs. 0.435, p < 0.001) in cross-validation and independent testing sets. Among four models, the type-19-combined model achieved the highest AUC (0.779, 0.674) in cross-validation and testing sets. Conclusions: Radiomics analysis of voxel-wise DCE-MRI TIC profile maps, simultaneously quantifying temporal and spatial hemodynamic heterogeneity, provides an effective, noninvasive method for predicting ALN metastasis in breast cancer. Full article

Background/Objectives: Non-variceal upper gastrointestinal bleeding (NVUGIB) is associated with considerable morbidity and mortality, particularly in emergency department (ED) settings. While traditional clinical scores such as the Glasgow-Blatchford Score (GBS), AIMS65, and Pre-Endoscopic Rockall are widely used for risk stratification, their accuracy in mortality prediction is limited. This study aimed to evaluate the performance of multiple supervised machine learning (ML) models in predicting 30-day all-cause mortality in NVUGIB and to compare these models with established risk scores. Methods: A retrospective cohort study was conducted on 1233 adult patients with NVUGIB who presented to the ED of a tertiary center between January 2022 and January 2025. Clinical and laboratory data were extracted from electronic records. Seven supervised ML algorithms—logistic regression, ridge regression, support vector machine, random forest, extreme gradient boosting (XGBoost), naïve Bayes, and artificial neural networks—were trained using six feature selection techniques generating 42 distinct models. Performance was assessed using AUROC, F1-score, sensitivity, specificity, and calibration metrics. Traditional scores (GBS, AIMS65, Rockall) were evaluated in parallel. Results: Among the cohort, 96 patients (7.8%) died within 30 days. The best-performing ML model (XGBoost with univariate feature selection) achieved an AUROC > 0.80 and F1-score of 0.909, significantly outperforming all traditional scores (highest AUROC: Rockall, 0.743; p < 0.001). ML models demonstrated higher sensitivity and specificity, with improved calibration. Key predictors consistently included age, comorbidities, hemodynamic parameters, and laboratory markers. The best-performing ML models demonstrated very high apparent AUROC values (up to 0.999 in internal analysis), substantially exceeding conventional scores. These results should be interpreted as apparent performance estimates, likely optimistic in the absence of external validation. Conclusions: While machine-learning models showed markedly higher apparent discrimination than conventional scores, these findings are based on a single-center retrospective dataset and require external multicenter validation before clinical implementation. Full article

Pesticide poisoning remains a significant public health issue, characterized by high morbidity and mortality, particularly among patients presenting to the emergency department. This study aimed to develop a 14-day in-hospital mortality prediction model for patients with acute pesticide poisoning using early clinical and laboratory data. This retrospective cohort study included 1056 patients who visited Soonchunhyang University Cheonan Hospital between January 2015 and December 2020. The cohort was randomly divided into train (n = 739) and test (n = 317) sets using stratification by pesticide type and outcome. Candidate predictors were selected based on univariate Cox regression, LASSO regularization, random forest feature importance, and clinical relevance derived from established prognostic scoring systems. Logistic regression models were constructed using six distinct feature sets. The best-performing model combined LASSO-selected and clinically curated features (AUC 0.926 [0.890–0.957]), while the final model—selected for interpretability—used only LASSO-selected features (AUC 0.923 [0.884–0.955]; balanced accuracy 0.835; sensitivity 0.843; specificity 0.857; F1.5 score 0.714 at threshold 0.450). SHapley Additive exPlanations (SHAP) analysis identified paraquat ingestion, Glasgow Coma Scale, bicarbonate level, base excess, and alcohol history as major mortality predictors. The proposed model outperformed the APACHE II score (AUC 0.835 [0.781–0.888]) and may serve as a valuable tool for early risk stratification and clinical decision making in pesticide-poisoned patients. Full article