Search Results (2,031)

This study develops a machine-learning-based framework for multiclass soil classification using Cone Penetration Test (CPT) data, aiming to overcome the limitations of traditional empirical Soil Behavior Type (SBT) charts and improve the automation, continuity, robustness, and reliability of stratigraphic interpretation. A dataset of 340 CPT soundings from 26 sites in Shanghai is compiled, and a sliding-window feature engineering strategy is introduced to transform point measurements into local pattern descriptors. An XGBoost-based multiclass classifier is then constructed using fifteen engineered features, integrating second-order optimization, regularized tree structures, and probability-based decision functions. Results demonstrate that the proposed method achieves strong classification performance across nine soil categories, with an overall classification accuracy of approximately 92.6%, an average F1-score exceeding 0.905, and a mean Average Precision (mAP) of 0.954. The confusion matrix, P–R curves, and prediction probabilities show that soil types with distinctive CPT signatures are classified with near-perfect confidence, whereas transitional clay–silt facies exhibit moderate but geologically consistent misclassification. To evaluate depth-wise prediction reliability, an Accuracy Coverage Rate (ACR) metric is proposed. Analysis of all CPTs reveals a mean ACR of 0.924, and the ACR follows a Weibull distribution. Feature importance analysis indicates that depth-dependent variables and smoothed p_s statistics are the dominant predictors governing soil behavior differentiation. The proposed XGBoost-based framework effectively captures nonlinear CPT–soil relationships, offering a practical and interpretable tool for high-resolution soil classification in subsurface investigations. Full article

Facial palsy (FP) impairs voluntary control of facial muscles, resulting in facial asymmetry and difficulties in emotional expression. Traditional assessment methods to define the severity of FP (e.g., House–Brackmann score, HB) rely on visual examinations and, therefore, are highly examiner-dependent. This study proposes an alternative approach using facial surface electromyography (EMG) for automated HB prediction. Time-domain EMG features were extracted during different facial movements (i.e., smile, close eyes, and raise forehead) and analyzed through nine different machine learning (ML) models in 58 subjects (51.98 ± 1.67 years, 20 male) with variable facial nerve function (HB 1: n = 16, HB 2–3: n = 32; HB 4–6: n = 10). Model performances were evaluated based on accuracy, precision, recall, and F1-score. Among the evaluated models, ensemble-based approaches—particularly a random forest model with 100 trees and a decision tree ensemble—proved to be the most effective with classification accuracies ranging from 81.7 to 84.8% and from 81.7 to 84.7%, depending on the evaluated facial movement. The results indicate that ensemble-based ML models can reliably distinguish between different FP grades using non-invasive EMG data. The approach offers a robust alternative to subjective clinical scoring, potentially improving diagnostic consistency and supporting longitudinal monitoring in clinical and research applications. Full article

Background/Objectives: Alzheimer’s disease is the leading cause of dementia, marked by progressive cognitive decline and a severe socioeconomic burden. Early and accurate diagnosis is crucial to enhancing patient outcomes, yet traditional clinical and imaging assessments are often limited in sensitivity, particularly at early stages. This study presents a dual-modal framework that integrates symptom-based clinical data with magnetic resonance imaging (MRI) using machine learning (ML) and deep learning (DL) models, enhanced by explainable AI (XAI). Methods: Four ML classifiers—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF)—were trained on demographic and clinical features. For stage-wise classification, five DL models—CNN, EfficientNetB3, DenseNet-121, ResNet-50, and MobileNetV2—were applied to MRI scans. Interpretability was incorporated through SHAP and Grad-CAM visualizations. Results: Random Forest achieves the highest accuracy of 97% on clinical data, while CNN achieves the best overall performance of 94% in MRI-based staging. SHAP and Grad-CAM were used to find clinically relevant characteristics and brain areas, including hippocampal atrophy and ventricular enlargement. Conclusions: Integrating clinical and imaging data and interpretable AI improves the accuracy and reliability of AD staging. The proposed model offers a valid and clear diagnostic route, which can assist clinicians in making timely diagnoses and adjusting individual treatment. Full article

Background/Objectives: Cardiovascular diseases are the leading cause of mortality worldwide according to the World Health Organization (WHO), highlighting the need for accessible tools for early detection. Automated classification systems based on signal processing and machine learning offer a non-invasive alternative to support clinical diagnosis. Methods: This study implements and evaluates machine learning models for distinguishing normal and abnormal heart sounds using a hybrid feature extraction approach. Recordings labeled as normal, murmur, and extrasystolic were obtained from the PASCAL dataset and subsequently binarized into two classes. Multiple numerical datasets were generated through statistical features derived from Mel-Frequency Cepstral Coefficients (MFCCs) and Daubechies wavelet analysis. Each dataset was standardized and used to train four classifiers: support vector machines, logistic regression, random forests, and decision trees. Results: Model performance was assessed using accuracy, precision, recall, specificity, F1-score, and area under curve. All classifiers achieved notable results; however, the support vector machine model trained with 26 MFCCs and Daubechies-4 wavelet coefficients obtained the best performance. Conclusions: These findings demonstrate that the proposed hybrid MFCC–Wavelet framework provides competitive diagnostic accuracy and represents a lightweight, interpretable, and computationally efficient solution for computer-aided auscultation and early cardiovascular screening. Full article

Objective: The aim of this preliminary study was to recognize motion patterns by classifying time series features extracted from electromyography (EMG) data of the upper limb muscles. Methods: In this study, we tested six machine learning (ML) classification models (decision trees, support vector machines, linear discriminant, quadratic discriminant, k-nearest neighbors, and efficient logistic regression) to classify time series features segmented from processed EMG data that were acquired from eight superficial muscles of two upper limbs over performing given physical activities in two main stages (supination and neutral forearm configuration) in initial and target (isometric) positions. Results: Findings indicate that in aiming to classify stages of the upper limb with the highest performance, the following ML models should be used: (1) K-NN cityblock (F1 equals 0.973/0.992) and K-NN minkowski (0.966/0.992) for the left limb in initial or target position; (2) K-NN seuclidean (0.959/0.985) and K-NN minkowski (0.957/0.986) for the right limb in initial position; (3) K-NN cityblock (0.966/0.986), K-NN seuclidean (0.959/0.985), and K-NN minkowski (0.957/0.986) for the right limb in target position. Conclusions: Upper limb positions tested in this study can be recognized based on classification of surface EMG data by using the k-nearest neighbors models (K-NN cityblock, K-NN seuclidean or K-NN minkowski) that have to be trained separately for the right and left upper limbs. Full article

China’s coastal wetlands play a crucial role in maintaining biodiversity and providing essential ecosystem services. However, the absence of high-resolution wetland type maps poses substantial challenges for effective conservation and management. This study proposes a two-step classification framework that integrates pixel-based Random Forest algorithms with object-based hierarchical decision trees, utilizing Landsat-8 time-series imagery to generate a detailed wetland map comprising 10 wetland types and 5 non-wetland categories. The results reveal distinct spatial patterns along China’s coastline: freshwater wetlands and riverine systems dominate the northern regions, whereas southern coastal zones feature extensive tidal flats, aquaculture ponds, and mangrove ecosystems. The proposed method achieved an overall accuracy of 89.76% and a Kappa coefficient of 0.891, demonstrating its effectiveness for large-scale wetland mapping. This study provides robust technical support for the sustainable conservation and ecological management of coastal wetlands. Full article

The aim of this study was to develop a model that classifies companies into high or low categories based on their return on equity (RoE), the most important indicator of financial performance, using sustainability and governance-related committee reports and reports shared with the public. As a sample, the RoE, sustainability, and governance variables of all 427 companies traded on the Istanbul Stock Exchange in 2024 were used. Using a 70:30 stratified split between the training and test sets, three tree-based models (XGBoost, LightGBM, and Random Forest) were used to perform a binary classification task. The findings show that tree-based models perform only slightly better than the naive majority class rule, and therefore, have limited overall classification power. A noteworthy finding from the study is that SHAP-based explainability analysis shows that the Corporate Governance Report (IMNG), the Integrated Report (IREP) and the existence of a Sustainability Committee (ICOM) rank higher in terms of SHAP-based global importance in the High RoE classification model, although their average contributions are small and, in the case of IMNG, predominantly negative for the probability of belonging to the High RoE class. Methodologically, the article moves away from traditional econometric methods based on ESG scores, instead combining a predictive classification structure with TreeSHAP-based explanations. These findings indicate a need for reporting practices that offer deeper content, clearer evidence of governance quality, and stronger data integrity to better support investors’ decision-making processes through sustainability and governance. Full article

Ecosystem disservices (EDS)—ecosystem properties and functions that cause discomfort or harm—often shape public attitudes to urban biodiversity more strongly than ecosystem services, yet they remain weakly integrated into inclusive spatial planning. This study develops and tests an EDS classification and a decision-making tree intended to help planners recognise disservices, assess ES–EDS trade-offs, and select proportionate responses without defaulting to ecological simplification. The framework was derived from literature, survey evidence, and expert–stakeholder input from Eastern European cities, and then examined through five contrasting urban action situations in Estonia and Belarus. The cases show that a shared decision logic for EDS is transferable across settings, but that its practical uptake depends on governance conditions. Where communication was proactive and explanatory, participation was meaningful, and long-term management was institutionally secured, disservices were reframed or mitigated while ecological objectives were maintained. Where disservices were framed late, trust was low, or political intervention truncated deliberation, even modest nature-based interventions were stalled or redirected toward grey alternatives. These findings justify treating EDS as a routine planning concern and demonstrate how an EDS-aware approach can strengthen inclusive planning by making both benefits and burdens of urban nature explicit. Full article

Artificial Intelligence (AI) is increasingly used to enhance project management practices, especially in risk analysis, where traditional tools often lack predictive capabilities. This study introduces an AI-based tool that supports project teams in identifying and interpreting risks through machine learning and integrated documentation features. A synthetic dataset of 5000 project instances was generated using deterministic rules across 27 input variables, enabling the training of multi-output Decision Tree and Random Forest models to predict risk type, impact, probability, and response strategy. Due to the rule-based structure of the dataset, both models achieved near-perfect classification performance, with Random Forest showing slightly better regression accuracy. These results validate the modelling pipeline but should not be interpreted as real-world predictive accuracy. The trained models were deployed within a web platform offering prediction visualization, automated PDF reporting, result storage, and access to a structured risk management plan template. Survey feedback highlights strong user interest in AI-assisted mitigation suggestions, dashboards, notifications, and mobile access. The findings demonstrate the potential of AI to improve proactive risk assessment and decision-making in project environments. Full article

Detecting active failures is important for the Industrial Internet of Things (IIoT). The IIoT aims to connect devices and machinery across industries. The devices connect via the Internet and provide large amounts of data which, when processed, can generate information and even make automated decisions on the administration of industries. However, traditional active fault management techniques face significant challenges, including highly imbalanced datasets, a limited availability of failure data, and poor generalization to real-world conditions. These issues hinder the effectiveness of prompt and accurate fault detection in real IIoT environments. To overcome these challenges, this work proposes a data augmentation mechanism which integrates generative adversarial networks (GANs) and the synthetic minority oversampling technique (SMOTE). The integrated GAN-SMOTE method increases minority class data by generating failure patterns that closely resemble industrial conditions, increasing model robustness and mitigating data imbalances. Consequently, the dataset is well balanced and suitable for the robust training and validation of learning models. Then, the data are used to train and evaluate a variety of models, including deep learning architectures, such as convolutional neural networks (CNNs) and long short-term memory networks (LSTMs), and conventional machine learning models, such as support vector machines (SVMs), K-nearest neighbors (KNN), and decision trees. The proposed mechanism provides an end-to-end framework that is validated on both generated and real-world industrial datasets. In particular, the evaluation is performed using the AI4I, Secom and APS datasets, which enable comprehensive testing in different fault scenarios. The proposed scheme improves the usability of the model and supports its deployment in a real IIoT environment. The improved detection performance of the integrated GAN-SMOTE framework effectively addresses fault classification challenges. This newly proposed mechanism enhances the classification accuracy up to 0.99. The proposed GAN-SMOTE framework effectively overcomes the major limitations of traditional fault detection approaches and proposes a robust, scalable and practical solution for intelligent maintenance systems in the IIoT environment. Full article

In urban underground space construction using shield tunnelling, the geological conditions ahead of the tunnel face are often uncertain. Without timely and accurate classification of the ground type, mismatches in operational parameters, uncontrolled costs, and schedule risks are likely to occur. Using observations from an earth pressure balance (EPB) project on an urban railway, a data-driven classification framework is developed that integrates shield tunnelling operating measurements with physically derived quantities to discriminate among soft soil, hard rock, and mixed strata. Principal component analysis (PCA) is performed on the training set, followed by a systematic comparison of tree-based classifiers and hyperparameter optimization strategies to explore the attainable performance. Under unified evaluation criteria, a categorical bosting (CatBoost) model optimized by a Nevergrad combination strategy (NGOpt) attains the highest test accuracy of 0.9625, with macro-averaged precision and macro-averaged recall of 0.9715 and 0.9716, respectively. To mitigate optimism from single-point estimates, stratified bootstrap intervals are reported for the test set. A Monte Carlo experiment applies independent perturbations to the PCA-transformed features, producing low label-flip rates across the three classes, with only minor changes in probability calibration metrics, which suggests consistent decisions under sensor noise and sampling bias. Overall, within the scope of the considered EPB project, the study delivers a compact workflow that demonstrates the feasibility of uncertainty-aware ground-type classification and provides a methodological reference for developing decision-support tools in underground tunnel construction. Full article

This study presents a decision tree model-based approach to classify rural net migration across Colombian departments using sociodemographic and economic variables. In the model formulation, immigration is considered the movement of people to a destination area to settle there, while emigration is the movement of people from that specific area to other places. The target variable was defined as a binary category representing positive (when the immigration is greater than emigration) or negative net migration. Four classification models were trained and evaluated: Decision Tree, Random Forest, AdaBoost, and XGBoost. Data were preprocessed using cleaning techniques, categorical variable encoding, and class balance assessment. Model performance was evaluated using various metrics, including accuracy, precision, sensitivity, $F_1$ score, and the area under the ROC curve. The results show that Random Forest achieves the highest accuracy, precision, sensitivity, and $F_1$ score in the 10-variable and 15-variable settings, while XGBoost is competitive but not dominant. Furthermore, the importance of the model was analyzed to identify key factors influencing migration patterns. This approach allows for a more precise understanding of regional migration dynamics in Colombia and can serve as a basis for designing informed public policies. Full article

The aim of this work is to implement decision tree classifiers (DTCs) capable of distinguishing bee honey by geographical origin. The case study focuses on honeys from the lowland and highland regions of Chiriquí, Panama. Characterization was conducted by analyzing their typical physicochemical and aromatic profiles using AOAC, IHC, and e-Nose methodologies, respectively. Data mining provided insights into the most relevant features, enabling the reduction of an otherwise extensive and resource-intensive dataset. The critical markers identified include reducing sugars, ash, antioxidant capacity, HMF, as well as aromatic, aliphatic, hydrocarbon, and sulfur compounds. This simplified set of features produced an intuitive classification scheme, achieving up to 86% accuracy. This proof-of-concept demonstrates that interpretable models can effectively leverage easily measurable characteristics for regional differentiation, offering a valuable tool for traceability in the Panamanian honey industry. Full article

To overcome the limitations of existing automatic modulation classification (AMC) methods that mainly target single-signal scenarios in radio-over-fiber (RoF) system, a mixed-signal AMC scheme based on phase noise-insensitive high-order cumulants (PNI-HOC) and distribution characteristics is proposed. The approach enables accurate classification of mixed signals in RoF system. Specifically, a PNI-HOC algorithm is first introduced to mitigate the influence of laser linewidth-induced phase noise. Then, distribution characteristics derived from the signal amplitude histogram are extracted to construct a two-dimensional characteristics space. These characteristics are subsequently fed into decision tree and support vector machine (SVM) classifiers for signal identification. To validate the effectiveness of the scheme, a 10 GBaud RoF system with a 70 km fiber link is implemented. The simulation results show that, compared with the conventional high-order cumulant method, the approach solely based on amplitude histogram distribution characteristics and the scheme based on deep neural networks (DNN) classifier using histogram characteristics, the proposed scheme achieves significantly higher classification accuracy at low optical signal–noise ratios (OSNRs). In particular, when the fiber length is 70 km and the OSNR is ≥16 dB, the classification accuracy of mixed signals is consistently maintained at 100%. Furthermore, the robustness of the proposed method is verified under various system impairments, including laser phase noise, chromatic dispersion and nonlinear effects, amplified spontaneous emission noise, multipath fading, etc., confirming its superior and stable performance. Full article

Background/Objectives: Dental caries is among the most common oral health problems, resulting from demineralization of dental hard tissues in acidic environments. Early diagnosis is essential to prevent severe tissue destruction, systemic complications and costly treatments. Conventional visual interpretation of panoramic radiographs, though widely used, remains subjective and variable. This study evaluated the effectiveness of image processing techniques and artificial intelligence (AI)-assisted models for automated detection and classification of dental caries on panoramic radiographs, emphasizing numerical image data analysis. Methods: From 1084 panoramic radiographs, 405 were selected and classified into interproximal, occlusal and secondary caries groups. Each was segmented and one representative region was analyzed using the image data representation method. Numerical descriptors—brightness, contrast, entropy and histogram parameters—were extracted and evaluated with several machine learning algorithms. Results: Among tested models, the Decision Tree algorithm achieved the highest classification accuracy (0.988 at the 0.2 train-test ratio), showing superior and consistent results across caries types. Random Forest also demonstrated strong performance with limited training data, while Gaussian Naïve Bayes, KNN and RBFNN were less effective. Conclusions: The integration of numerical image features with AI-based models demonstrated high diagnostic accuracy and clinical interpretability, particularly with Decision Tree algorithm. These results highlight the potential of AI-assisted analysis of panoramic radiographs to enhance diagnostic reliability, reduce subjectivity and support more effective treatment planning. Further multicentre studies with larger and more diverse datasets are recommended to validate generalizability. Full article