Search Results (17,680)

Recently, visual odometry and SLAM (Simultaneous Localization and Mapping) have shown tremendous performance improvements compared to LiDAR and 3D sensor techniques. Unfortunately, attempts to achieve these improvements always face numerous challenges due to their complexity and insufficient compatibility for real-time environments. This paper presents an enhanced deep-learning-based SLAM system, primarily for Monocular Visual SLAM, by utilizing a Mini-GRU (gated recurrent unit). The proposed system, MINI-DROID-SLAM, demonstrates significant improvements and robustness through persistent iteration of the camera position. Similar to the original DROID SLAM, the system calculates pixel-wise depth mapping and enhances it using the BA (Bundle Adjustment) technique. The architecture introduced in this research reduces the time used and computation complexity compared to the original DROID-SLAM network. The introduced model is trained locally on a single GPU using monocular camera images from the TartanAir datasets. The training time and reconstruction metric, assessed using ATE (Absolute Trajectory Error), show robustness and high performance compared to the original DROID-SLAM. Full article

Background/Objectives: Workplace conflict and aggression pose significant psychosocial risks across diverse professional sectors. This protocol outlines a novel, university-based educational intervention. Developed by a multidisciplinary team from the University Hospital of Pisa, Italy, including occupational physicians and a psychiatrist specializing in work and organizational psychology, its primary purpose is to enhance conflict prevention and crisis management skills. While initially developed and tested within the veterinary sector due to its identified vulnerabilities, the intervention is inherently generalizable to any high-stress professional environment characterized by intense client, customer, or public interactions. Methods: The intervention integrates didactic instruction with active, immersive learning through tailored role-playing scenarios simulating real-world challenging encounters. This study protocol details the structured methodology for evaluating the immediate effectiveness of this training. We are using a specifically developed efficacy scale to assess outcomes. Results: The results demonstrate a significant improvement in all assessed skills from the pre-training to the post-training evaluation. For every item on the scale, the median scores increased, indicating a positive shift in overall group performance. The p-value for each item was <0.001, confirming that the observed improvements were statistically significant. These results demonstrate enhanced conflict resolution skills, improved communication, and an increased sense of self-efficacy among participants. Conclusions: This protocol offers a comprehensive and generalizable approach to addressing workplace psychosocial risks through an innovative educational intervention. A key future goal involves advancing this training methodology by integrating virtual reality (VR) environments with AI-driven avatars for role-playing, aiming to achieve a more realistic and impactful learning experience and sustained behavioral change. Full article

Background: Torque Teno Virus (TTV) viremia has been proposed as a marker for infection risk in kidney transplant (KT) recipients. This study aimed to evaluate the prognostic value of TTV levels for predicting infections post-KT. Methods: A cohort of 82 KT patients was analyzed. TTV loads were measured before KT and at the time of cutoff analysis (mean time since KT: 20.2 ± 10.3 months). Infections were tracked within six months following the time of cutoff analysis. Univariable analyses and a supervised machine learning approach (logistic regression with leave-one-out cross-validation) were conducted to rigorously assess TTV’s predictive ability for post-transplant infection. Results: Seventy-two patients (87.8%) had detectable TTV before KT. Of these, 30.5% developed infections, predominantly viral. TTV loads increased significantly from 3.35 ± 1.67 log₁₀ cp/mL before KT to 4.53 ± 1.93 log₁₀ cp/mL at the time of cutoff analysis. Infected patients had significantly higher TTV loads (5.39 ± 1.68 log₁₀ vs. 4.16 ± 1.94 log₁₀ cp/mL, p = 0.0057). The optimal TTV threshold for predicting infection at the time of cutoff analysis was 5.16 log₁₀ cp/mL, with 60% sensitivity and 81% specificity. Machine learning models improved performance, with sensitivity and specificity 0.805 and 0.735, respectively. Conclusions: TTV viremia may serve as a biomarker for infection risk, particularly when used with other clinical variables. The identified TTV threshold of 5.16 log₁₀ cp/mL offers a practical tool for clinical decision-making, particularly when integrated with a machine learning model. Further studies with larger cohorts are needed to validate these findings and refine clinical applications. Full article

In the context of retrofitting existing buildings into nearly zero-energy buildings (NZEBs), in situ assessment methods have proven reliable for evaluating the performance of building components, including glazing systems. However, these methods are often time-consuming, intrusive to occupants, and disruptive to building operations. This study investigates the potential of a machine learning approach—multiple linear regression (MLR)—to predict the dynamic performance of an office building’s glazing system by analyzing surface temperature variations and their impact on nearby thermal comfort. The models were trained using in situ data collected over just two weeks—one in September and one in December—but were applied to predict the glazing performance on multiple other dates with diverse weather conditions. Results show that MLR predictions closely matched nighttime measurements, while some discrepancies occurred during the daytime. Nevertheless, the machine learning model achieved a daytime prediction accuracy of approximately 1.5 °C in terms of root mean square error (RMSE), which is lower than the values reported in previous studies. For thermal comfort evaluation, the MLR model identified the periods with thermal discomfort with an overall accuracy of approximately 92%. However, during periods when the difference between predicted and measured operative temperatures exceeded 1 °C, the thermal comfort predictions showed greater deviation from actual measurements. The study concludes by acknowledging its limitations and recommending a future approach that integrates machine learning with laboratory-based techniques (e.g., hot-box setups and solar simulators) and in situ measurements, together with a broader variety of glazing samples, to more effectively evaluate and enhance prediction accuracy, robustness, and generalizability. Full article

This paper proposes a methodology for implementing a custom-developed explainability model for credit rating using behavioral data registered during the lifecycle of the borrowing that can replicate the score given by the regulatory model for the solidarity economy in Colombia. The methodology integrates continuous behavioral and financial variables from over 17,000 real credit histories into predictive models based on ridge regression, decision trees, random forests, XGBoost, and LightGBM. The models were trained and evaluated using cross-validation and RMSE metrics. LightGBM emerged as the most accurate model, effectively capturing nonlinear credit behavior patterns. To ensure interpretability, SHAP was used to identify the contribution of each feature to the model predictions. The presented model using LightGBM predicted the credit risk assessment in accordance with the regulatory model used by the Colombian Superintendence of the Solidarity Economy, with a root-mean-square error of 0.272 and an R² score of 0.99. We propose an alternative framework using explainable machine learning models aligned with the internal ratings-based approach under Basel II. Our model integrates variables collected throughout the borrowing lifecycle, offering a more comprehensive perspective than the regulatory model. While the regulatory framework adjusts itself generically to national regulations, our approach explicitly accounts for borrower-specific dynamics. Full article

The clinical electroretinogram (ERG) is a non-invasive diagnostic test used to assess the functional state of the retina by recording changes in the bioelectric potential following brief flashes of light. The recorded ERG waveform offers ways for diagnosing both retinal dystrophies and neurological disorders such as autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), and Parkinson’s disease. In this study, different time-series-based machine learning methods were used to classify ERG signals from ASD and typically developing individuals with the aim of interpreting the decisions made by the models to understand the classification process made by the models. Among the time-series classification (TSC) algorithms, the Random Convolutional Kernel Transform (ROCKET) algorithm showed the most accurate results with the fewest number of predictive errors. For the interpretation analysis of the model predictions, the SHapley Additive exPlanations (SHAP) algorithm was applied to each of the models’ predictions, with the ROCKET and KNeighborsTimeSeriesClassifier (TS-KNN) algorithms showing more suitability for ASD classification as they provided better-defined explanations by discarding the uninformative non-physiological part of the ERG waveform baseline signal and focused on the time regions incorporating the clinically significant a- and b-waves of the ERG. With the potential broadening scope of practice for visual electrophysiology within neurological disorders, TSC may support the identification of important regions in the ERG time series to support the classification of neurological disorders and potential retinal diseases. Full article

Objective: The aim of this study was to evaluate the accuracy of machine and deep learning approaches on radiomics features obtained by Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) and contrast enhanced mammography (CEM) in the characterization of breast cancer and in the prediction of the tumor molecular profile. Methods: A total of 153 patients with malignant and benign lesions were analyzed and underwent MRI examinations. Considering the histological findings as the ground truth, three different types of findings were used in the analysis: (1) benign versus malignant lesions; (2) G1 + G2 vs. G3 classification; (3) the presence of human epidermal growth factor receptor 2 (HER2+ vs. HER2−). Radiomic features (n = 851) were extracted from manually segmented regions of interest using the PyRadiomics platform, following IBSI-compliant protocols. Highly correlated features were excluded, and the remaining features were standardized using z-score normalization. A feature selection process based on Elastic Net regularization (α = 0.5) was used to reduce dimensionality. Synthetic balancing of the training data was applied using the ROSE method to address class imbalance. Model performance was evaluated using repeated 10-fold cross-validation and AUC-based metrics. Results: Among the 153 patients enrolled in the studies, 113 were malignant lesions. Among the 113 malignant lesions, 32 had high grading (G3) and 66 had the HER2+ receptor. Radiomic features derived from both CEM and DCE-MRI showed strong discriminative performance for malignancy detection, with several features achieving AUCs above 0.80. Gradient Boosting Machine (GBM) achieved the highest accuracy (0.911) and AUC (0.907) in differentiating benign from malignant lesions. For tumor grading, the neural network model attained the best accuracy (0.848), while LASSO yielded the highest sensitivity (0.667) for detecting high-grade tumors. In predicting HER2+ status, the neural network also performed best (AUC = 0.669), with a sensitivity of 0.842. Conclusions: Radiomics-based machine learning models applied to multiparametric CEM and DCE-MRI images offer promising, non-invasive tools for breast cancer characterization. The models effectively distinguished benign from malignant lesions and showed potential in predicting histological grade and HER2 status. These results demonstrate that radiomic features extracted from CEM and DCE-MRI, when analyzed through machine and deep learning models, can support accurate breast cancer characterization. Such models may assist clinicians in early diagnosis, histological grading, and biomarker assessment, potentially enhancing personalized treatment planning and non-invasive decision-making in routine practice. Full article

The quality control of fruit purée products such as mango and mangosteen is crucial for maintaining consumer satisfaction and meeting industry standards. Traditional destructive techniques for assessing key quality parameters like the soluble solid content (SSC) and titratable acidity (TA) are labor-intensive and time-consuming; prompting the need for rapid, nondestructive alternatives. This study investigated the use of deep learning (DL) models including Simple-CNN, AlexNet, EfficientNetB0, MobileNetV2, and ResNeXt for predicting SSC and TA in mango and mangosteen purée and compared their performance with the conventional chemometric method partial least squares regression (PLSR). Spectral data were preprocessed and evaluated using 10-fold cross-validation. For mango purée, the Simple-CNN model achieved the highest predictive accuracy for both SSC (coefficient of determination of cross-validation (${\mathrm{R}}_{\mathrm{CV}}^2$) = 0.914, root mean square error of cross-validation (RMSE_CV) = 0.688, the ratio of prediction to deviation of cross-validation (RPD_CV) = 3.367) and TA (${\mathrm{R}}_{\mathrm{CV}}^2$ = 0.762, RMSE_CV = 0.037, RPD_CV = 2.864), demonstrating a statistically significant improvement over PLSR. For the mangosteen purée, AlexNet exhibited the best SSC prediction performance (${\mathrm{R}}_{\mathrm{CV}}^2$ = 0.702, RMSE_CV = 0.471, RPD_CV = 1.666), though the RPD_CV values (<2.0) indicated limited applicability for precise quantification. TA prediction in mangosteen purée showed low variance in the reference values (standard deviation (SD) = 0.048), which may have restricted model performance. These results highlight the potential of DL for improving NIR-based quality evaluation of fruit purée, while also pointing to the need for further refinement to ensure interpretability, robustness, and practical deployment in industrial quality control. Full article

With the rapid evolution of technology and the continuous deepening of digital transformation in education, personalized and adaptive learning have emerged as inevitable trends in the educational landscape. This study focuses on a Computerized Adaptive Learning System Based on Cognitive Diagnosis (CAL-CDS)—an integrated platform that incorporates multiple technologies for assessment and learning. The study is organized around two dimensions: (1) constructing a foundational cognitive diagnostic assessment framework, and (2) investigating the operational mechanisms of the cognitive diagnosis-based computerized adaptive system. It comprehensively incorporates core components including cognitive modeling, Q-matrix generation, and diagnostic test development. On this basis, this study dissects the system’s operational logic from four aspects: the adaptive testing system, diagnostic system, recommendation system, and empirical case studies. This study effectively addresses two core questions: how to construct a cognitive diagnostic assessment framework that alignes with China’s mathematics knowledge structure, and how to facilitate personalized student learning via cognitive diagnosis. Overall, this study offers a systematic solution for developing mathematics-specific cognitive diagnosis-driven adaptive learning systems. Full article

Heat-related morbidity and mortality are increasing due to climate change, emphasizing the need to identify vulnerable areas and people exposed to extreme temperatures. To improve heat stress impact assessment, we developed a replicable machine learning model that integrates remote sensing, ground station, and geospatial data to estimate daily air temperature at a spatial resolution of 100 m × 100 m across the region of Tuscany, Italy. Using a two-stage approach, we first imputed missing land surface temperature data from MODIS using gradient-boosted trees and spatio-temporal predictors. Then, we modeled daily maximum and minimum air temperatures by incorporating monitoring station observations, satellite-derived data (MODIS, Landsat 8), topography, land cover, meteorological variables (ERA5-land), and vegetation indices (NDVI). The model achieved high predictive accuracy, with R² values of 0.95 for Tmax and 0.92 for Tmin, and root mean square errors (RMSE) of 1.95 °C and 1.96 °C, respectively. It effectively captured both temporal (R²: 0.95; 0.94) and spatial (R²: 0.92; 0.72) temperature variations, allowing for the creation of high-resolution maps. These results highlight the potential of integrating Earth Observation and machine learning to generate high-resolution temperature maps, offering valuable insights for urban planning, climate adaptation, and epidemiological studies on heat-related health effects. Full article

Land use/land cover (LULC) data serve as a critical information source for understanding the complex interactions between human activities and global environmental change. The subtropical karst region, characterized by fragmented terrain, spectral confusion, topographic shadowing, and frequent cloud cover, represents one of the most challenging natural scenes for remote sensing classification. This study reviews the evolution of multi-source data acquisition (optical, SAR, LiDAR, UAV) and preprocessing strategies tailored for subtropical regions. It evaluates the applicability and limitations of various methodological frameworks, ranging from traditional approaches and GEOBIA to machine learning and deep learning. The importance of uncertainty modeling and robust accuracy assessment systems is emphasized. The study identifies four major bottlenecks: scarcity of high-quality samples, lack of scale awareness, poor model generalization, and insufficient integration of geoscientific knowledge. It suggests that future breakthroughs lie in developing remote sensing intelligent models that are driven by few samples, integrate multi-modal data, and possess strong geoscientific interpretability. The findings provide a theoretical reference for LULC information extraction and ecological monitoring in heterogeneous geomorphic regions. Full article

Emotion recognition capabilities in multimodal AI systems are crucial for developing culturally responsive educational technologies yet remain underexplored for Arabic language contexts, where culturally appropriate learning tools are critically needed. This study evaluated the emotion recognition performance of two advanced multimodal large language models, GPT-4o and Gemini 1.5 Pro, when processing Arabic children’s storybook illustrations. We assessed both models across three prompting strategies (zero-shot, few-shot, and chain-of-thought) using 75 images from seven Arabic storybooks, comparing model predictions with human annotations based on Plutchik’s emotional framework. GPT-4o consistently outperformed Gemini across all conditions, achieving the highest macro F1-score of 59% with chain-of-thought prompting compared to Gemini’s best performance of 43%. Error analysis revealed systematic misclassification patterns, with valence inversions accounting for 60.7% of errors, while both models struggled with culturally nuanced emotions and ambiguous narrative contexts. These findings highlight fundamental limitations in current models’ cultural understanding and emphasize the need for culturally sensitive training approaches to develop effective emotion-aware educational technologies for Arabic-speaking learners. Full article

This paper presents a comprehensive analysis of artificial intelligence-powered automated grading systems (AI AGSs) in STEM education, systematically examining their algorithmic foundations, mathematical modeling approaches, and quantitative evaluation methodologies. AI AGSs enhance grading efficiency by providing large-scale, instant feedback and reducing educators’ workloads. Compared to traditional manual grading, these systems improve consistency and scalability, supporting a wide range of assessment types, from programming assignments to open-ended responses. This paper provides a structured taxonomy of AI techniques including logistic regression, decision trees, support vector machines, convolutional neural networks, transformers, and generative models, analyzing their mathematical formulations and performance characteristics. It further examines critical challenges, such as user trust issues, potential biases, and students’ over-reliance on automated feedback, alongside quantitative evaluation using precision, recall, F1-score, and Cohen’s Kappa metrics. The analysis includes feature engineering strategies for diverse educational data types and prompt engineering methodologies for large language models. Lastly, we highlight emerging trends, including explainable AI and multimodal assessment systems, offering educators and researchers a mathematical foundation for understanding and implementing AI AGSs into educational practices. Full article

The mobile tunnel scanning system (MTSS) enables efficient tunnel inspection; however, motion blur (MB) generated at high travel speeds remains a major factor undermining the reliability of deep-learning-based crack detection. This study focuses on investigating how horizontally oriented MB in MTSS imagery affects the crack-detection performance of convolutional neural networks (CNNs) and proposes a data-centric quality-assurance framework that leverages no-reference image quality assessment (NR-IQA) to optimize model performance. By intentionally applying MB to both public and real-world MTSS datasets, we analyzed performance changes in ResNet-, VGG-, and AlexNet-based models and established the correlations between four NR-IQA metrics (BRISQUE, NIQE, PIQE, and CPBD) and performance (F1 score). As the MB intensity increased, the F1 score of ResNet34 dropped from 89.43% to 4.45%, confirming the decisive influence of image quality. PIQE and CPBD exhibited strong correlations with F1 (−0.87 and +0.82, respectively), emerging as the most suitable indicators for horizontal MB. Using thresholds of PIQE ≤ 20 and CPBD ≥ 0.8 to filter low-quality images improved the AlexNet F1 score by 1.46%, validating the effectiveness of the proposed methodology. The proposed framework objectively assesses MTSS data quality and optimizes deep learning performance, enhancing the reliability of intelligent infrastructure maintenance systems. Full article

Background. Severe left ventricular hypertrophy (SLVH) is a high-risk structural cardiac abnormality associated with increased risk of heart failure. It is typically assessed using echocardiography or cardiac magnetic resonance imaging, but these modalities are limited by cost, accessibility, and workflow burden. We introduce a deep learning framework that classifies SLVH directly from chest radiographs, without intermediate anatomical estimation models or demographic inputs. A key contribution of this work lies in interpretability. We quantify how clinically relevant attributes are encoded within internal representations, enabling transparent model evaluation and integration into AI-assisted workflows. Methods. We construct class-balanced subsets from the CheXchoNet dataset with equal numbers of SLVH-positive and negative cases while preserving the original train, validation, and test proportions. ResNet-18 is fine-tuned from ImageNet weights, and a Vision Transformer (ViT) encoder is pretrained via masked autoencoding with a trainable classification head. No anatomical or demographic inputs are used during training. We apply Mutual Information Neural Estimation (MINE) to quantify dependence between learned features and five attributes: age, sex, interventricular septal diameter (IVSDd), posterior wall diameter (LVPWDd), and internal diameter (LVIDd). Results. ViT achieves an AUROC of 0.82 [95% CI: 0.78–0.85] and an AUPRC of 0.80 [95% CI: 0.76–0.85], indicating strong performance in SLVH detection from chest radiographs. MINE reveals clinically coherent attribute encoding in learned features: age > sex > IVSDd > LVPWDd > LVIDd. Conclusions. This study shows that SLVH can be accurately classified from chest radiographs alone. The framework combines diagnostic performance with quantitative interpretability, supporting reliable deployment in triage and decision support. Full article