Search Results (1,307)

Fall detection systems in ambient assisted living (AAL) and smart homes are essential for the comfort, safety, and autonomy of elderly people. The aim of this study was to investigate the performance of these systems considering categories of sensors and methods used. A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Seven open databases were screened without a date limit: PubMed/MedLine, Google Scholar, ScienceDirect, Science.gov, Academia, IEEE Xplore, and Mendeley. The article selection and data extraction were performed by two authors independently. Among the 473 unique records, 80 studies were selected. Five fall detection performance parameters (accuracy, precision, sensitivity, specificity, F1-score) and two computation speed parameters (training and testing time) were extracted and classified according to three sensor categories (wearable, non-wearable, and hybrid solutions), and four methods (deep learning, machine learning, threshold, and all others). The ANOVA results showed that wearable sensors performed the worst in fall detection. Deep learning methods produced the best results for the five parameters. Identifying the advantages of different solutions is a major challenge for researchers, practitioners, and policymakers in the design and implementation of more effective fall detection systems. Full article

Farmers rely on nematode analysis for critical crop management decisions, yet traditional detection and classification methods remain subjective, labor-intensive, and time-consuming. Advances in Machine Learning (ML) and Deep Learning (DL) offer scalable solutions for automating microscopy-based nematode analyses. This systematic literature review (SLR) analyzed 44 articles published between 2018 and 2024 on ML/DL-based nematode image analysis, selected from 1460 records screened across Web of Science, IEEE Xplore, Agricola, and supplemental Google scholar searches. The quality of reporting was examined by considering dataset documentation and code availability. The results were synthesized narratively, as diversity in datasets, tasks, and metrics precluded a meta-analysis. Performance was primarily reported using accuracy, precision, recall, F1-score, Dice coefficient, Intersection over Union (IoU), and average precision (AP). CNNs were the most commonly used architectures, with models such as YOLO providing the best detection performance. Transformer-based models excelled in dense segmentation and counting. Despite strong performance, challenges include limited training data, occlusion, and inconsistent metric reporting across tasks. Although ML/DL models hold promise for scalable nematode analysis, future research should prioritize real-world validation, diverse nematode datasets, and standardized benchmark datasets to enable fair and reproducible model comparison. Full article

Fossil fuels are crucial to the global energy supply, with pipelines being a vital transportation method. However, these vital assets are highly susceptible to pitting corrosion, an insidious form of degradation that can lead to catastrophic failures. Unlike uniform corrosion, which represents a symmetric form of material loss, pitting corrosion is a highly asymmetric and localized phenomenon. The inherent complexity and asymmetry of this process make its prediction a significant challenge. To address this, this study presents SSA-CNN-Attention, a deep learning model specifically designed to analyze the complex, nonlinear interactions among environmental factors. The model employs a Convolutional Neural Network (CNN) to extract local features, while a crucial attention mechanism allows it to asymmetrically weight the importance of these features, enhancing its ability to recognize intricate interactions. Additionally, the Sparrow Search Algorithm (SSA) optimizes the model’s hyperparameters for improved accuracy and stability. Furthermore, a post hoc interpretability analysis using the LIME framework validates that the model’s learned feature relationships are consistent with established corrosion science, revealing how the model accounts for the asymmetric influence of key variables. The experimental results demonstrate that the proposed model reduces mean squared error (MSE) by 61.3% and mean absolute error (MAE) by 26.6%, while improving the coefficient of determination (R²) by 28.2% compared to traditional CNNs. These findings highlight the model’s superior performance in predicting a fundamentally asymmetric process and provide valuable insights into the underlying corrosion mechanisms. Full article

Traditional teaching methods are often far from aligning with professional practice demands. Team-Based Learning (TBL), a variant of Problem-Based Learning, may foster motivation, autonomy, and deeper knowledge acquisition, especially in those educative contexts linked to practical knowledge. The objective of the present research was to explore the impact of a TBL program with digital support on Sport Sciences students’ psychological and learning outcomes. A quasi-experimental design with pre- and post-tests was applied to 68 fourth-year students (mean age = 21.45 ± 1.57 years). The intervention spanned 12 weeks, where the students had to solve specific case studies linked to the theoretical content of the subject and its applicability. Variables measured included motivational climate, satisfaction of basic psychological needs, intrinsic motivation, transversal competences, and academic performance. Significant improvements were observed in task- and ego-oriented climate, autonomy, competence, relatedness, knowledge scores, and competence in scientific searches and academic dissemination (p < 0.05). No significant changes were found in intrinsic motivation or audiovisual material competence. Sex influenced several outcomes, while project marks and prior transversal skills did not. TBL combined with digital tools enhanced learning outcomes and key psychological needs, though intrinsic motivation remained unchanged. Findings highlight the value of active methodologies in higher education, while underscoring the need for long-term, broader studies. Full article

Background/Objectives: Gamification and game-based learning (GBL) have recently emerged as fresh and appealing ways of health education, and they have been shown to perform better in knowledge acquisition than traditional teaching approaches. Digital serious games are developing as innovative tools for cancer education and behaviour change, yet no review has systematically synthesized their use across key populations. This scoping review aimed to map evidence on serious games for cancer prevention, care, and survivorship among the public, patients, and healthcare professionals, framed through the Capability, Opportunity, Motivation-Behaviour (COM-B) model. Methods: Following Joanna Briggs Institute methodology, we searched Web of Science, MEDLINE, CINAHL, and PsycINFO. Eligible studies evaluated a serious game with a cancer focus and reported outcomes on knowledge, awareness, engagement, education, or behaviour. Data extraction and synthesis followed the PRISMA-ScR checklist. Results: Thirty-five studies met the inclusion criteria, covering diverse cancers, populations, and platforms. Most reported improvements in knowledge, engagement, self-efficacy, and communication. However, heterogeneity in study design and limited assessment of long-term behaviour change constrained comparability. Conclusions: Digital serious games show promise for enhancing cancer literacy and supporting behavioural outcomes across patients, professionals, and the public. By integrating multiple perspectives, this review highlights opportunities for theory-driven design, robust evaluation, and implementation strategies to maximize their impact in cancer education and awareness. Full article

Background: Older adults are highly vulnerable to infectious diseases due to immunosenescence, multimorbidity, and atypical presentations. Artificial intelligence (AI) offers promising opportunities to improve diagnosis, prognosis, treatment, and continuity of care in this population. This review summarizes current applications of AI in the management of infections in older adults across diagnostic, prognostic, therapeutic, and preventive domains. Methods: We conducted a narrative review of peer-reviewed studies retrieved from PubMed, Scopus, and Web of Science, focusing on AI-based tools for infection diagnosis, risk prediction, antimicrobial stewardship, prevention of healthcare-associated infections, and post-discharge care in individuals aged ≥65 years. Results: AI models, including machine learning, deep learning, and natural language processing techniques, have demonstrated high performance in detecting infections such as sepsis, pneumonia, and healthcare-associated infections (Area Under the Curve AUC up to 0.98). Prognostic algorithms integrating frailty and functional status enhance the prediction of mortality, complications, and readmission. AI-driven clinical decision support systems contribute to optimized antimicrobial therapy and timely interventions, while remote monitoring and telemedicine applications support safer hospital-to-home transitions and reduced 30-day readmissions. However, the implementation of these technologies is limited by the underrepresentation of frail older adults in training datasets, lack of real-world validation in geriatric settings, and the insufficient explainability of many models. Additional barriers include system interoperability issues and variable digital infrastructure, particularly in long-term care and community settings. Conclusions: AI has strong potential to support predictive and personalized infection management in older adults. Future research should focus on developing geriatric-specific, interpretable models, improving system integration, and fostering interdisciplinary collaboration to ensure safe and equitable implementation. Full article

Despite the advances on data analysis methodologies in the last decades, most of the traditional regression methods cannot be directly applied to large-scale data. Although aggregation methods are especially designed to deal with large-scale data, their performance may be strongly reduced in ill-conditioned problems (due to collinearity issues). This work compares the performance of a recent approach based on normalized entropy, a concept from information theory and info-metrics, with bagging and magging, two well-established aggregation methods in the literature, providing valuable insights for applications in regression analysis with large-scale data. While the results reveal a similar performance between methods in terms of prediction accuracy, the approach based on normalized entropy largely outperforms the other methods in terms of precision accuracy, even considering a smaller number of groups and observations per group, which represents an important advantage in inference problems with large-scale data. This work also alerts for the risk of using the OLS estimator, particularly under collinearity scenarios, knowing that data scientists frequently use linear models as a simplified view of the reality in big data analysis, and the OLS estimator is routinely used in practice. Beyond the promising findings of the simulation study, our estimation and aggregation strategies show strong potential for real-world applications in fields such as econometrics, genomics, environmental sciences, and machine learning, where data challenges such as noise and ill-conditioning are persistent. Full article

Captive Asian elephants (Elephas maximus) frequently present to hospitals with complex, multisystemic diseases, yet veterinarians lack objective tools to predict and classify clinical outcomes. Decision-making often relies on experience or anecdote, and few studies have applied data-driven approaches in wildlife medicine. This study developed a machine learning–based classification model using routinely collected clinical data. A total of 467 medical records from hospitalized elephants at Thailand’s National Elephant Institute (2019–2024) were retrospectively analyzed. Four variables (age, sex, disease group, and length of stay [LOS]) were used to train four classification algorithms: Random Forest, eXtreme Gradient Boosting, Naïve Bayes, and multinomial logistic regression. The Random Forest model achieved the highest classification performance (accuracy = 86.3%; log-loss = 0.374), with disease group, LOS, and age as key predictors. Survival analysis revealed distinct hospitalization trajectories across disease groups: acute conditions like elephant endotheliotropic herpesvirus-hemorrhagic disease and toxicosis showed rapid early declines, whereas dental and renal cases followed more prolonged courses. Our findings demonstrate the preliminary feasibility of outcome classification in elephant care and highlight the potential of clinical data science to improve in-hospital prognostication, monitoring, and treatment planning in zoological and wildlife medicine. Full article

Developing climate-resilient and high-quality cotton cultivars remains an urgent challenge, as the key target traits yield, fibre properties, and stress tolerance are highly polygenic and strongly influenced by genotype–environment interactions. Recent advances in chromosome-scale genome assemblies, pan-genomics, and haplotype-resolved resequencing have greatly enhanced the capacity to identify causal variants and recover non-reference alleles linked to fibre development and environmental adaptation. Parallel progress in functional genomics and precision genome editing, particularly CRISPR/Cas, base editing, and prime editing, now enables rapid, heritable modification of candidate loci across the complex tetraploid cotton genome. When integrated with high-throughput phenotyping, genomic selection, and machine learning, these approaches support predictive ideotype design rather than empirical, trial-and-error breeding. Emerging digital agriculture tools, such as digital twins that combine genomic, phenomic, and environmental data layers, allow simulation of ideotype performance and optimisation of trait combinations in silico before field validation. Speed breeding and phenomic selection further shorten generation time and increase selection intensity, bridging the gap between laboratory discovery and field deployment. However, the large-scale implementation of these technologies faces several practical constraints, including high infrastructural costs, limited accessibility for resource-constrained breeding programmes in developing regions, and uneven regulatory acceptance of genome-edited crops. However, reliance on highly targeted genome editing may inadvertently narrow allelic diversity, underscoring the need to integrate these tools with broad germplasm resources and pangenomic insights to sustain long-term adaptability. To realise these opportunities at scale, standardised data frameworks, interoperable phenotyping systems, robust multi-omic integration, and globally harmonised, science-based regulatory pathways are essential. This review synthesises recent progress, highlights case studies in fibre, oil, and stress-resilience engineering, and outlines a roadmap for translating integrative genomics into climate-smart, high-yield cotton breeding programmes. Full article

STEM (Science, Technology, Engineering, and Mathematics) education faces the challenge of incorporating advanced technologies that foster motivation, collaboration, and hands-on learning. This study proposes a portable system capable of transforming ordinary surfaces into interactive learning spaces through gamification and spatial perception. A prototype based on multi-agent architecture was developed on the PANGEA (Platform for automatic coNstruction of orGanizations of intElligent agents) platform, integrating LIDAR (Light Detection and Ranging) sensors for gesture detection, an ultra-short-throw projector for visual interaction and a web platform to manage educational content, organize activities and evaluate student performance. The data from the sensors is processed in real time using ROS (Robot Operating System), generating precise virtual interactions on the projected surface, while the web allows you to configure physical and pedagogical parameters. Preliminary tests show that the system accurately detects gestures, translates them into digital interactions, and maintains low latency in different classroom environments, demonstrating robustness, modularity, and portability. The results suggest that the combination of multi-agent architectures, LIDAR sensors, and gamified platforms offers an effective approach to promote active learning in STEM, facilitate the adoption of advanced technologies in diverse educational settings, and improve student engagement and experience. Full article

This dataset contains detailed information on student trajectories and dropout factors at a Spanish technological university offering Science, Technology, Engineering, Arts, and Mathematics programs. The data comprise demographic, socioeconomic, and academic variables for all enrolled students, including those in bachelor’s, master’s, doctoral, and lifelong learning programs, across three complete academic years, excluding periods affected by the SARS-CoV-2 pandemic. The data were collected and standardized from disjointed internal data sources, and fully anonymized. The dataset contains information about 39,364 students, 4989 courses in 163 degrees, and 77 variables related to admission pathways, academic performance indicators, socio-demographic background, digital activity in the Learning Management System, and Wi-Fi access records. Each of the 464,739 records corresponds to a course enrolment per student per year, enabling longitudinal analyses of academic progression and dropout. This data has the potential to be reused to support research on factors influencing student retention, allow for the development of predictive models to identify students at risk of leaving their studies, and offer a resource for comparative studies in higher education. Full article

Background: Artificial Intelligence (AI) is increasingly applied in endurance sports to optimize performance, enhance recovery, and personalize nutrition and supplementation. This review synthesizes current knowledge on AI applications in endurance sports, emphasizing implications for metabolic health, nutritional strategies, and recovery optimization, while also addressing ethical considerations and future directions. Methods: A narrative review was conducted using targeted searches of PubMed, Scopus, and Web of Science with cross-referencing. Extracted items included sport/context, data sources, AI methods including machine learning (ML), validation type (internal vs. external/field), performance metrics, comparators, and key limitations to support a structured synthesis; no formal risk-of-bias assessment or meta-analysis was undertaken due to heterogeneity. Results: AI systems effectively integrate multimodal physiological, environmental, and behavioral data to enhance metabolic health monitoring, predict recovery states, and personalize nutrition. Continuous glucose monitoring combined with AI algorithms allows precise carbohydrate management during prolonged events, improving performance outcomes. AI-driven supplementation strategies, informed by genetic polymorphisms and individual metabolic responses, have demonstrated enhanced ergogenic effectiveness. However, significant challenges persist, including measurement validity and reliability of sensor-derived signals and overall dataset quality (e.g., noise, missingness, labeling error), model performance and generalizability, algorithmic transparency, and equitable access. Furthermore, limited generalizability due to homogenous training datasets restricts widespread applicability across diverse athletic populations. Conclusions: The integration of AI in endurance sports offers substantial promise for improving performance, recovery, and nutritional strategies through personalized approaches. Realizing this potential requires addressing existing limitations in model performance and generalizability, ethical transparency, and equitable accessibility. Future research should prioritize diverse, representative, multi-site data collection across sex/gender, age, and race/ethnicity. Coverage should include performance level (elite to recreational), sport discipline, environmental conditions (e.g., heat, altitude), and device platforms (multi-vendor/multi-sensor). Equally important are rigorous external and field validation, transparent and explainable deployment with appropriate governance, and equitable access to ensure scientifically robust, ethically sound, and practically relevant AI solutions. Full article

Large language models (LLMs) are playing an increasingly important role in data science applications. In this study, the performance of LLMs in generating code and designing solutions for data science tasks is systematically evaluated based on different real-world tasks from the Kaggle platform. Models from different LLM families were tested under both default settings and configurations with hyperparameter tuning (HPT) applied. In addition, the effects of few-shot prompting (FSP) and Tree of Thought (ToT) strategies on code generation were compared. Alongside technical metrics such as accuracy, F1 score, Root Mean Squared Error (RMSE), execution time, and peak memory consumption, LLM outputs were also evaluated against Kaggle user-submitted solutions, leaderboard scores, and two established AutoML frameworks (auto-sklearn and AutoGluon). The findings suggest that, with effective prompting strategies and HPT, models can deliver competitive results on certain tasks. The ability of some LLMS to suggest appropriate algorithms reveals that LLMs can be seen not only as code generators, but also as systems capable of designing machine learning (ML) solutions. This study presents a comprehensive analysis of how strategic decisions such as prompting methods, tuning approaches, and algorithm selection, affect the design of LLM-based data science systems, offering insights for future hybrid human–LLM systems. Full article

Star scientists are highly influential researchers who have made significant contributions to their field, gained widespread recognition, and often attracted substantial research funding. They are critical for the advancement of science and innovation and significantly influence the transfer of knowledge and technology to industry. Identifying potential star scientists before their performance becomes outstanding is important for recruitment, collaboration, networking, and research funding decisions. This study utilizes machine learning techniques and builds four different classifiers, i.e., random forest, support vector machines, naïve bayes, and logistic regression, to predict star scientists in the field of artificial intelligence while highlighting features related to their success. The analysis is based on publication data collected from Scopus from 2000 to 2019, incorporating a diverse set of features such as gender, ethnic diversity, and collaboration network structural properties. The random forest model achieved the best performance with an AUC of 0.75. Our results confirm that star scientists follow different patterns compared to their non-star counterparts in almost all the early-career features. We found that certain features, such as gender and ethnic diversity, play important roles in scientific collaboration and can significantly impact an author’s career development and success. The most important features in predicting star scientists in the field of artificial intelligence were the number of articles, betweenness centrality, research impact indicators, and weighted degree centrality. Our approach offers valuable insights for researchers, practitioners, and funding agencies interested in identifying and supporting talented researchers. Full article

Understanding the intricate relationship between composition, processing conditions, and material properties is essential for optimizing Cu-based alloys. Machine learning offers a powerful tool for decoding these complex interactions, enabling more efficient alloy design. This work introduces a comprehensive machine learning framework aimed at accurately predicting key properties such as hardness and electrical conductivity of low-alloyed Cu-based alloys. By integrating various input parameters, including chemical composition and thermo-mechanical processing parameters, the study develops and validates multiple machine learning models, including Multi-Layer Perceptron with Production-Aware Deep Architecture (MLP-PADA), Deep Feedforward Network with Multi-Regularization Framework (DFF-MRF), Feedforward Network with Self-Adaptive Optimization (FFN-SAO), and Feedforward Network with Materials Mapping (FFN-TMM). On a held-out test set, DFF-MRF achieved the best generalization (R²_test = 0.9066; RMSE_test = 5.3644), followed by MLP-PADA (R²_test = 0.8953; RMSE_test = 5.7080) and FFN-TMM (R²_test = 0.8914; RMSE_test = 5.8126), with FFN-SAO slightly lower (R²_test = 0.8709). Additionally, a computational performance analysis was conducted to evaluate inference time, memory usage, energy consumption, and batch scalability across all models. Feature importance analysis was conducted, revealing that aging temperature, Cr, and aging duration were the most influential factors for hardness. In contrast, aging duration, aging temperature, solution treatment temperature, and Cu played key roles in electrical conductivity. The results demonstrate the effectiveness of these advanced machine learning models in predicting critical material properties, offering insightful advancements for materials science research. This study introduces the first controlled, statistically validated, multi-model benchmark that integrates composition and thermo-mechanical processing with deployment-grade profiling for property prediction of low-alloyed Cu alloys. Full article