Search Results (612)

Upper extremity (UE) pain and pathology are prevalent among manual wheelchair users (MWUs) due to repetitive loading demands, highlighting the need for tools to identify high-risk tasks and inform injury prevention. This study investigated the feasibility of classifying activity intensity for wheelchair-related tasks using wearable sensors and supervised machine learning. Twenty-four MWUs with chronic spinal cord injury completed a standardized mobility course and simulated activities of daily living while UE electromyography (EMG) and inertial measurement unit (IMU) data were collected. Signals segmented into 3, 5, and 10 s windows, and time- and frequency-domain features were extracted and labeled as low, moderate, or high intensity. Multiple classification algorithms were evaluated using subject-dependent and subject-independent cross-validation, and dimensionality reduction was explored to assess class separability. Subject-dependent analyses demonstrated performance above chance but below 75% accuracy, with decision tree models demonstrating superior performance, particularly when trained on data segmented into 5 s windows. IMU features outperformed EMG features, but combining signal types enhanced performance. Subject-independent analyses revealed similar overall accuracy across signal types, but decreased high-intensity classification for EMG data, indicating subject dependency. Findings support the potential of wearable sensor-based machine learning with population-specific findings for activity intensity classification in MWUs, while highlighting challenges related to inter-subject variability for injury risk prediction. Full article

Background/Objectives: Cognitive impairment affects multiple brain functions, and its early detection is essential to prevent progression to dementia; artificial intelligence has shown considerable potential in this field. This scoping review aims to map the impact of artificial intelligence–based tools for the early detection of cognitive impairment by identifying the main technologies used, examining their effectiveness, and exploring their ethical implications. Methods: A scoping review was conducted between April and May 2025 following the PRISMA-ScR methodological framework; the review protocol was previously registered on the Open Science Framework. PubMed, Scopus, and Cochrane databases were searched using natural language and controlled vocabulary terms via Medical Subject Headings. The search was limited to articles published between 2020 and 2025, in English or Spanish, with free full-text access. Methodological quality was assessed using CASPe, JBI, and MMAT. Results: A total of 14 studies were included after the selection and critical appraisal process. The findings show that artificial intelligence–based tools such as deep-learning models applied to neuroimaging, speech and gait analysis, electronic health record analysis, and mobile health applications demonstrate promising accuracy in detecting early cognitive changes. These technologies enable the identification of subtle patterns that may be difficult to detect using conventional clinical assessments. Conclusions: AI-based tools can provide substantial support for clinical decision-making by effectively identifying subtle changes that are imperceptible to human intelligence. However, their use also raises ethical issues related to patient privacy and data security. Full article

Soiling of solar panels has a considerable impact on the performance of photo voltaic (PV) systems, emphasizing the importance of developing reliable decision support tools for solar panel cleaning. Although recent convolutional neural network (CNN)-based models, including lightweight architectures such as SolPowNet, have demonstrated high classification accuracy, their performance can be sensitive to dataset variability and domain shifts encountered in real-world PV environments. Motivated by the lightweight design philosophy of SolPowNet, this paper proposes a hybrid and ensemble-based intelligent cleaning decision framework that integrates classical image processing, machine learning, and deep learning techniques. The proposed approach combines physically interpretable handcrafted texture and sharpness features classified using a Random Forest model with a pretrained MobileNetV3-Small CNN through a conservative OR-based ensemble fusion strategy. In addition, a probability-driven Soiling Index (SI) is introduced to translate classification confidence into actionable cleaning decisions, including no cleaning, light cleaning, and full cleaning. Experimental results on multiple PV image datasets demonstrate that, under domain-shift conditions where individual models may experience performance degradation, the proposed ensemble framework achieves an accuracy of up to 85.93% and attains a dusty-panel detection rate of 0.90 on the unseen dataset. On the in-distribution evaluation, the proposed OR-ensemble achieves an average accuracy of 0.9663 ± 0.0177 with dusty recall of 0.9896 ± 0.0104 over repeated stratified runs. Importantly, the conservative fusion strategy minimizes high-risk false negative cases while avoiding excessive misclassification of clean panels. Overall, the proposed framework offers a robust, scalable, and deployment-ready solution for intelligent PV cleaning decision support, advancing CNN-based soiling detection toward practical and risk-aware operation and maintenance systems. Full article

Background/Objectives: Alzheimer’s disease (AD), the most prevalent form of dementia, is characterized by an overall decline in cognitive functioning and represents a major public health crisis. It remains critical to be able to accurately and quickly diagnose patients with AD; however, recent deep learning approaches using MRI data do not provide sample generalization, have high computational requirements, and offer little interpretability. Methods: In this study, we present a new framework called eXplorative ViT-CNN (X-ViTCNN) that combines a customized Vision Transformer model with two previously trained CNNs (DenseNet201 and MobileNetV2). With our proposed preprocessing approach using contrast-enhanced preprocessing to highlight neuroanatomical features as well as Bayesian Optimization to tune hyperparameters, we fuse local structural features originating from the CNNs with global representations from the transformer and feed the final result to fully connected dense layers for multi-stage classification. We also use Grad-CAM visualizations to provide insight into how our model arrived at its classification. Results: Experiments conducted on ADNI and OASIS datasets demonstrate the superiority of X-ViTCNN, achieving accuracies of 97.98% and 94.52%, respectively. The model outperformed individual baselines and other pre-trained architectures, showing balanced sensitivity and specificity across all AD stages. Conclusions: The proposed X-ViTCNN framework is a powerful, interpretable method for predicting the development of multi-stage Alzheimer’s disease using MRI scans. The combination of complementary feature learning, automatic hyperparameter optimization and interpretability through visualization make it an excellent potential tool for clinicians to support their decision making in the early diagnosis and ongoing monitoring of persons with Alzheimer’s disease. Full article

Objectives: This study aimed to develop and validate a hybrid deep learning model combining Convolutional Neural Networks (CNN) and Vision Transformers (ViT) to automatically classify maxillary sinus membrane morphologies on Cone-Beam Computed Tomography (CBCT) images, distinguishing between Normal, Flat, Polypoid, and Obstruction types. Methods: A dataset of 959 CBCT images was collected and categorized into four morphological classes: Normal, Flat, Polypoid and Obstruction. A custom hybrid model was developed, integrating a lightweight residual CNN for local feature extraction, learnable weighted feature fusion with a bidirectional feature pyramid network and a Transformer encoder for global context modeling. The performance of proposed model was compared against six different architectures, including ResNet50, MobileNetV3L and standard ViT models, using accuracy, precision, recall and F1-score metrics. Results: The proposed hybrid model achieved the highest overall accuracy of 98.44%, outperforming six strong CNN and ViT models including ResNet50 (97.92%) and ViT-B16 (86.46%) models. In class-wise analysis, the model demonstrated superior diagnostic capability, particularly for the “Obstruction” class, achieving 100% accuracy. High discrimination was also observed for “Flat” (98.21%) and “Polypoid” (98.04%) morphologies, confirming the model’s sensitivity to shape-based features. Conclusions: The proposed hybrid CNN-ViT model successfully classifies maxillary sinus membrane morphologies with high accuracy, effectively overcoming the limitations of standard ViT models on limited datasets. Detection of membrane morphology is vital for predicting surgical risks like membrane perforation and post-operative sinusitis. This model serves as a reliable clinical decision support tool, enabling clinicians to objectively assess specific risk factors before implant surgery and sinus floor elevation. Full article

Diabetes mellitus is a growing global health challenge, and digital health technologies offer new opportunities to support self-management. Mobile applications can benefit both patients and healthcare professionals; however, awareness and integration of these tools into community pharmacy practice remain limited. As accessible frontline providers, pharmacists are well positioned to promote digital health, yet their readiness and engagement require further investigation. A cross-sectional survey was conducted among community pharmacists in Serbia using a structured questionnaire. Developed through a consensus-based process, the instrument assessed pharmacists’ awareness, attitudes, and experiences with digital health technologies, focusing on mobile applications for diabetes self-management. Only 15.8% of pharmacists were aware of such applications, and 2.4% reported receiving relevant training. Higher digital health technology literacy was associated with greater awareness, confidence, and preference for digital learning. Most participants supported expanding pharmacists’ roles in advising patients on digital tools and expressed interest in structured education and official guidance. These findings indicate limited awareness and training in mobile health applications among community pharmacists. Enhancing digital competencies through targeted education and structured guidance may facilitate greater integration of digital tools into routine pharmacy practice and strengthen pharmacists’ roles in chronic disease management. Full article

Real-time performance remains a core requirement for safety-critical robotic applications. ROS 2 has become a de facto middleware standard, while Docker is increasingly adopted for modular and portable deployment. However, embedded hardware updates often constrain Linux distributions and real-time kernel versions, while existing software stacks depend on older ROS 2 releases and legacy libraries. This mismatch forces costly porting and revalidation, motivating heterogeneous deployments that mix ROS 2 versions across host and Docker container runtimes. Yet the overheads introduced by Docker and cross-version ROS 2 communication are not well quantified in terms of real-time guarantees. This paper presents a Docker-enabled real-time framework for evaluating robotic applications in heterogeneous ROS 2 deployments. The framework integrates an RT-PREEMPT–patched Linux kernel, Dockerized ROS 2 distributions, and configurable cross-version communication pathways to enable controlled, repeatable experiments without full-stack migration. We empirically quantify Docker-induced effects on real-time execution using task periodicity, jitter, and response time, and assess ROS 2 communication using end-to-end latency under host-only, container-only, and hybrid configurations. To demonstrate practical viability, we apply the framework to an operational mobile-robot use case that integrates legacy control code with new modules, including a reinforcement-learning decision layer, within a mixed host–container ROS 2 stack. The resulting analyses provide reusable tooling and actionable guidelines for deploying deterministic ROS 2 systems under containerized heterogeneous constraints. Full article

This study investigates how firms in high-emission sectors progress along the low-carbon transition by analysing the joint dynamics of Management Quality (MQ) and Carbon Performance (CP) using probabilistic modelling and explainable machine-learning methods. Digitalisation is conceptualised as the increasing use of data-driven and algorithmic tools in corporate governance, sustainability monitoring, and regulatory oversight, enabling a more granular assessment of corporate transition pathways across multiple time horizons. Using annual Transition Pathway Initiative data for 175 firms over the period 2018–2025, we apply discrete-time Markov chains to capture state persistence and directional mobility in MQ and CP, while Hidden Markov Models uncover latent performance regimes shaping firms’ transition trajectories across three decarbonisation horizons (2028, 2035, and 2050). To enhance interpretability and policy relevance, CatBoost-based feature importance analysis identifies governance, emissions-related, and sector-specific drivers of transitions between states. The results indicate a steady and highly persistent improvement in Management Quality, reflecting cumulative consolidation of governance structures, while Carbon Performance evolves more slowly and heterogeneously, with only moderate convergence emerging toward the 2050 horizon. Latent-regime estimates reveal a gradual shift from volatile, low-performance pathways toward more stable transition regimes over time. From a policy perspective, the findings suggest that governance improvements alone are insufficient to ensure timely emission reductions, highlighting the need for digitally enabled, sector-specific regulatory incentives and enforcement mechanisms targeting realised Carbon Performance. Full article

The proliferation of digital health education content (DHEC) offers a transformative opportunity for medical training worldwide. While students in high-income countries routinely integrate these tools, their use and impact in low-resource settings such as Mozambique remain poorly understood. Exploring this topic offers interesting possibilities at the intersection of global health equity, digital literacy, and pedagogical innovation. This study assessed how Mozambican medical students engage with online health videos, examining the types of content they search for, preferred platforms, perceived benefits, and attitudes toward integrating these materials into medical training. A quantitative cross-sectional survey was administered to 151 second-year medical students at the Catholic University of Mozambique and Alberto Chipande University. A structured online questionnaire, comprising multiple-choice, Likert-scale, and open-ended questions, was used. Data were analyzed using descriptive statistics, cross-tabulation, chi-square test, and Cramer’s V effect size. All students (100%) reported searching for online health videos. They primarily do so via YouTube (92.1%) and use mobile phones (98.7%). Students mainly searched topics related to basic biomedical sciences (60%). They reported that video enhances their learning (86.8%), academic work (11.3%), and other skills (1.9%). Mean scores for utility (4.06), self-reported knowledge gain (4.05), and interest in continuing use (4.30) reflected positive perceptions. Furthermore, an overwhelming majority (91.4%) supported the institutional production of educational videos, whereas 8.6% disagreed, citing videos as a tool that diverts students’ focus from reading and a preference for traditional classes. No statistically significant gender-based differences were observed in usefulness, learning levels, or core interest in continuing to search for online videos (p > 0.05). Online health videos are widely used and positively perceived by Mozambican medical students as a supplementary learning tool. The findings highlight the need for institutions to create curriculum-aligned video libraries and strengthen students’ digital literacy, an affordable strategy for enhancing medical education in low-resource contexts. Full article

The fungal pathogen Botrytis cinerea (B. cinerea) attacks over 1400 plant species and results in estimated annual losses of $10–100 billion worldwide. In precision agriculture, deep learning (DL) provides reliable tools for rapid and objective plant disease detection. This study presents a unified two-stage DL solution for the automated detection of visible B. cinerea across three major vegetable crops—tomato, pepper, and cucumber—using standard RGB imagery. In the first stage, a YOLOv11-based instance segmentation model accurately localizes leaf regions, achieving a localization accuracy of 87.3% as measured by mAP₅₀. In the second stage, an ensemble of 13 MobileViT variant models analyzes the segmented leaf regions and performs per-crop classification into healthy and infected leaves. The proposed system achieves an overall detection accuracy of 84.05%, with per-class detection of infected leaves at 88.61% for pepper, 82.68% for tomato, and 70.55% for cucumber, measured using the F1-score. These results demonstrate that the proposed approach can reliably detect B. cinerea symptoms across different crops using only RGB data, offering a practical path toward smartphone-based field deployment and integration into decision support systems for timely, symptom-based disease management. Full article

Intelligent transportation systems increasingly rely on artificial intelligence and predictive analytics to achieve sustainability. This study presents Adaptive Weighting, Chaos Theory, and Gaussian Mutation-based RIME algorithm-tuned Extreme Gradient Boosting (ACGRIME-XGBoost), an advanced Artificial Intelligence (AI)-driven framework specifically designed for carbon emission prediction in air transport to contribute to the development of sustainable smart infrastructure. The proposed hybrid model integrates XGBoost with ACGRIME, a novel metaheuristic optimization algorithm enhanced with chaos theory, adaptive weighting, and Gaussian mutation mechanisms to overcome limitations in traditional hyperparameter tuning approaches. The framework demonstrates exceptional performance on Congress on Evolutionary Computation (CEC) 2020 benchmark functions, outperforming conventional optimization algorithms in accuracy and robustness. When applied to real-world flight data within a smart transportation monitoring, ACGRIME-XGBoost achieves a 94% R² score for CO₂ emission prediction, significantly surpassing other optimized machine learning models. This research bridges the gap between advanced AI optimization techniques and sustainable transportation infrastructure, offering a scalable decision-support system that can be integrated with IoT sensor networks and mobility platforms in the future. The results demonstrate how metaheuristic-assisted machine learning can enhance environmental monitoring capabilities in smart transportation ecosystems, supporting data-driven policy-making for climate-resilient infrastructure and sustainable aviation management within the broader context. Also, the research contributes to sustainable aviation by enabling high-fidelity CO₂ prediction models that can inform policy-making and be integrated into digital monitoring tools for future smart transport infrastructures. Full article

The widespread application of glyphosate—the world’s most used herbicide—presents a significant environmental challenge due to its persistence and mobility within interconnected land–soil–water systems. This study addresses the limitations of traditional, discrete water monitoring by developing a predictive framework for glyphosate and its primary metabolite, aminomethylphosphonic acid (AMPA), in the agricultural context of Apulia, Southern Italy. The methodology integrates high-sensitivity analytical chemistry with advanced spatial intelligence. Water samples were analyzed using an optimized UHPLC–MS/MS framework with pre-column derivatization (FMOC-Cl), achieving an ultra-trace Limit of Quantification (LOQ) of 0.025 μg/L. To transition from point data to continuous spatial profiles, a hybrid Machine Learning (ML) architecture was implemented. The model utilized a suite of geospatial predictors, including land use (Corine Land Cover), Digital Elevation Models (DEMs), and slope characteristics extracted from river offset lines. A dual-modeling strategy was employed: Global Models (Random Forest, Gradient Boosting, and KNN) for regional trends and Individual Models for river segments exhibiting sufficient internal variability. Analytical findings (2018–2024) revealed that AMPA consistently exhibited higher mean concentrations than glyphosate, reaching peaks of 9.27 μg/L. This trend is primarily attributed to its superior environmental persistence and a half-life of up to 240 days, compared to the parent compound. Spatiotemporal analysis identified critical peaks in the second quarter for glyphosate and extreme surges in the fourth quarter for AMPA, particularly in the Cervaro basin. The Random Forest Regressor emerged as the most robust predictive tool, achieving a coefficient of determination (R²) of approximately 0.68 at the global scale and up to 0.75 for localized models where data density was sufficient. The integration of ML frameworks allows for the identification of contamination “micro-hotspots” and the mapping of probabilistic pollutant distribution along entire river reaches without additional sampling costs. This high-fidelity diagnostic tool provides a cost-effective strategy for environmental agencies to implement targeted mitigation and proactive water resource protection in Mediterranean agroecosystems. Full article

Malaria remains a major global health burden, requiring rapid and reliable diagnostic tools to complement or replace labor-intensive manual microscopy. Although deep learning methods have demonstrated strong potential for automated malaria diagnosis, many existing approaches depend on computationally expensive transfer learning architectures or exhibit sensitivity to suboptimal hyperparameter configurations. This study proposes a lightweight automated framework for binary classification of malaria cell images using a custom Convolutional Neural Network (CNN) optimized by a novel Adaptive Marine Predators Algorithm (AMPA). The proposed AMPA integrates a state-aware adaptive control factor that dynamically adjusts step size based on population loss, thereby improving search efficiency and reducing susceptibility to local optima. The framework was evaluated on the NIH Malaria Cell Image Dataset containing 27,558 single-cell images. Experimental results show that the AMPA-optimized CNN achieves a testing accuracy of 95.00% and an Area Under the Curve of 0.986. Comparative experiments indicate that the proposed model outperforms several reported lightweight architectures, including MobileNetV2 (92.00%) and YOLO-based detectors (94.07%), while achieving performance comparable to deeper networks such as VGG-16 (94.88%), with substantially lower computational complexity. The model further attains high sensitivity (0.94) and precision (0.96), supporting its suitability as a robust and resource-efficient approach for automated malaria screening research. Full article

Malignant lymphoma and other cancer types remain major global health concerns due to their rapid progression and potential for fatal outcomes. Conventional diagnostic approaches are often invasive and time-consuming, contributing to delays in early detection and treatment. These limitations highlight the urgent need for more accurate, efficient, and non-invasive diagnostic solutions that support timely clinical decision-making. In this study, we introduce CancerNet-W, a deep learning (DL) model built upon EfficientNet-B3 for automated classification of breast and cervical cancers using histopathological images (HIs). The model incorporates an Intelligent Learning Rate Controller (ILRC) that adaptively optimizes the LR during training, enhancing stability and performance. The preprocessing pipeline includes data augmentation, resizing, and normalization for the two datasets to improve feature extraction. The Breast cancer HIs Classification (BreakHis) dataset contains 10,000 HIs and the Cervical cancer (SipaKMed) dataset consists of 25,000 images. Importantly, the model leverages morphological cues such as cellular symmetry, which plays a key role in differentiating normal tissue, typically exhibiting more symmetric cellular organization—from malignant tissue, where cancer progression disrupts structural symmetry and leads to notable nuclear and architectural asymmetry, a hallmark of breast and cervical malignancies. This observation aligns with established findings on symmetry breaking in tumorigenesis and nuclear pleomorphism in cancer pathology. CancerNet-W achieved remarkable performance as a general model, yielding 100% accuracy for cervical cancer and 99.89% for breast cancer, outperforming state-of-the-art models including EfficientNet-B4, EfficientNet-B5, DenseNet-201, and MobileNet-V2. To promote strong learning and reduce overfitting, stratified five-fold cross-validation was utilized for the training-validation dataset. Model selection and optimization were based solely on validation performance. An independent test set, kept separate from both training and validation, was employed for final evaluation. The results, accuracy at 98.11% for breast cancer and 99.60% for cervical cancer, reflect the average test performance from the model trained across the five folds. Therefore, the proposed framework provides consistent and dependable diagnostic predictions while significantly reducing the time and cost associated with cancer detection, demonstrating its potential as a valuable tool for clinical applications. Full article

Background: Fungal infections are considered a global health concern, resulting in high morbidity and mortality rates, especially in immunocompromised individuals. Traditional diagnostic techniques, such as microscopy, culture, and polymerase chain reaction (PCR), suffer from low sensitivity, long processing time, and accessibility challenges, especially in resource-limited settings. Artificial intelligence (AI) and machine learning (ML) tools have demonstrated potential to enhance diagnostic accuracy and efficiency. This systematic study assesses the progress, precision, and efficacy of AI-driven diagnostic tools for fungal infections within various clinical contexts in comparison to traditional procedures. Methods: A systematic review was conducted according to PRISMA principles. Literature searches were conducted in PubMed, ScienceDirect, Web of Science, and Ovid, focusing on research employing AI models to diagnose fungal infections. The inclusion criteria were research that compared AI-based tools with conventional diagnostic methods in terms of sensitivity, specificity, and accuracy. Data extraction and quality evaluation were performed utilizing validated instruments, such as the Methodological Index for Non-Randomized Studies (MINORS). Results: Eleven research studies met the inclusion criteria: six retrospective and five prospective investigations. AI models, such as convolutional neural networks (CNNs), Faster R-CNN, VGG19, and MobileNet, have improved diagnostic accuracy, sensitivity, and specificity compared to traditional methods. However, differences in dataset quality, model validation, and real-world applicability remain as limitations. Conclusions: AI-driven diagnostic technologies provide significant benefits in identifying fungal infections, improving the speed and accuracy of diagnoses. However, additional extensive investigations and clinical validation are required to improve model generalizability and facilitate smooth incorporation into healthcare systems. Full article