Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (14,670)

Search Parameters:
Keywords = model group analysis

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
27 pages, 2297 KB  
Article
Artificial Intelligence Adoption in Non-Chemical Agriculture: An Integrated Mechanism for Sustainable Practices
by Arokiaraj A. Amalan and I. Arul Aram
Sustainability 2025, 17(19), 8865; https://doi.org/10.3390/su17198865 (registering DOI) - 4 Oct 2025
Abstract
Artificial Intelligence (AI) holds significant potential to enhance sustainable non-chemical agricultural methods (NCAM) by optimising resource management, automating precision farming practices, and strengthening climate resilience. However, its widespread adoption among farmers’ remains limited due to socio-economic, infrastructural, and justice-related challenges. This study investigates [...] Read more.
Artificial Intelligence (AI) holds significant potential to enhance sustainable non-chemical agricultural methods (NCAM) by optimising resource management, automating precision farming practices, and strengthening climate resilience. However, its widespread adoption among farmers’ remains limited due to socio-economic, infrastructural, and justice-related challenges. This study investigates AI adoption among NCAM farmers using an Integrated Mechanism for Sustainable Practices (IMSP) conceptual framework which combines the Technology Acceptance Model (TAM) with a justice-centred approach. A mixed-methods design was employed, incorporating Fuzzy-Set Qualitative Comparative Analysis (fsQCA) of AI adoption pathways based on survey data, alongside critical discourse analysis of thematic farmers narrative through a justice-centred lens. The study was conducted in Tamil Nadu between 30 September and 25 October 2024. Using purposive sampling, 57 NCAM farmers were organised into three focus groups: marginal farmers, active NCAM practitioners, and farmers from 18 districts interested in agricultural technologies and AI. This enabled an in-depth exploration of practices, adoption, and perceptions. The findings indicates that while factors such as labour shortages, mobile technology use, and cost efficiencies are necessary for AI adoption, they are insufficient without supportive extension services and inclusive communication strategies. The study refines the TAM framework by embedding economic, cultural, and political justice considerations, thereby offering a more holistic understanding of technology acceptance in sustainable agriculture. By bridging discourse analysis and fsQCA, this research underscores the need for justice-centred AI solutions tailored to diverse farming contexts. The study contributes to advancing sustainable agriculture, digital inclusion, and resilience, thereby supporting the United Nations’ Sustainable Development Goals (SDGs). Full article
Show Figures

Figure 1

15 pages, 2523 KB  
Article
Impact of Chromium Picolinate on Breast Muscle Metabolomics and Glucose and Lipid Metabolism-Related Genes in Broilers Under Heat Stress
by Guangju Wang, Xiumei Li, Miao Yu, Zhenwu Huang, Jinghai Feng and Minhong Zhang
Animals 2025, 15(19), 2897; https://doi.org/10.3390/ani15192897 - 3 Oct 2025
Abstract
The aim of the present study is to evaluate the impact of chromium (Cr) supplementation on glucose and lipid metabolism in breast muscle in broilers under heat stress. A total of 220 day-old broiler chicks were reared in cages. At 29 days old, [...] Read more.
The aim of the present study is to evaluate the impact of chromium (Cr) supplementation on glucose and lipid metabolism in breast muscle in broilers under heat stress. A total of 220 day-old broiler chicks were reared in cages. At 29 days old, 180 birds were randomly assigned to three treatments (0, 400, and 800 µg Cr/kg, as chromium picolinate) and transferred to climate chambers (31 ± 1 °C, 60 ± 7% humidity) for 14 days. Growth performance, carcass traits, serum biochemical indices, fasting glucose and insulin, homeostasis model assessment of insulin resistance (HOMA-IR), as well as muscle metabolomic profiles and gene expression related to energy and lipid metabolism were analyzed. The results showed that, compared with the heat stress group, the groups supplemented with 400 and 800 µg Cr/kg showed higher dry matter intake and average daily gain, breast muscle ratio, and lower feed conversion ratio and abdominal fat ratio; chickens supplemented with 400 and 800 µg Cr/kg showed significantly lower serum corticosterone (CORT), free fatty acids, and cholesterol levels compared with the heat stress (HS) group (p < 0.05). Fasting blood glucose and HOMA-IR were also significantly reduced, while fasting insulin was significantly increased in the Cr-supplemented groups (p < 0.05). Metabolomic analysis revealed that Cr supplementation regulated lipid and amino acid metabolism by altering key metabolites such as citric acid, L-glutamine, and L-proline, and modulating pathways including alanine, aspartate, and glutamate metabolism, and glycerophospholipid metabolism. Furthermore, Cr supplementation significantly upregulated the expression of Peroxisome Proliferator-Activated Receptor Gamma Coactivator 1 α (PGC-1α), ATP Binding Cassette Subfamily A Member 1 (ABCA1), Peroxisome Proliferator-Activated Receptor α (PPARα), and ATP Binding Cassette Subfamily G Member 1 (ABCG1) in both the hepatic and muscle tissue. This paper suggested that chromium supplementation may enhance energy metabolism and lipid transport like the findings of our study suggested. Full article
Show Figures

Figure 1

22 pages, 4631 KB  
Article
Crop Disease Spore Detection Method Based on Au@Ag NRS
by Yixue Zhang, Jili Guo, Fei Bian, Zhaowei Li, Chuandong Guo, Jialiang Zheng and Xiaodong Zhang
Agriculture 2025, 15(19), 2076; https://doi.org/10.3390/agriculture15192076 - 3 Oct 2025
Abstract
Crop diseases cause significant losses in agricultural production; early capture and identification of disease spores enable disease monitoring and prevention. This study experimentally optimized the preparation of Au@Ag NRS (Gold core@Silver shell Nanorods) sol as a Surface-Enhanced Raman Scattering (SERS) enhancement reagent via [...] Read more.
Crop diseases cause significant losses in agricultural production; early capture and identification of disease spores enable disease monitoring and prevention. This study experimentally optimized the preparation of Au@Ag NRS (Gold core@Silver shell Nanorods) sol as a Surface-Enhanced Raman Scattering (SERS) enhancement reagent via a modified seed-mediated growth method. Using an existing microfluidic chip developed by the research group, disease spores were separated and enriched, followed by combining Au@Ag NRS with Crop Disease Spores through electrostatic adsorption. Raman spectroscopy was employed to collect SERS fingerprint spectra of Crop Disease Spores. The spectra underwent baseline correction using Adaptive Least Squares (ALS) and standardization via Standard Normal Variate (SNV). Dimensionality reduction preprocessing was performed using Principal Component Analysis (PCA) and Successive Projections Algorithm combined with Competitive Adaptive Reweighted Sampling (SCARS). Classification was then executed using Support Vector Machine (SVM) and Multilayer Perceptron (MLP). The SCARS-MLP model achieved the highest accuracy at 97.92% on the test set, while SCARS-SVM, PCA-SVM, and SCARS-MLP models attained test set accuracy of 95.83%, 95.24%, and 96.55%, respectively. Thus, the proposed Au@Ag NRS-based SERS technology can be applied to detect airborne disease spores, establishing an early and precise method for Crop Disease detection. Full article
(This article belongs to the Special Issue Spectral Data Analytics for Crop Growth Information)
Show Figures

Figure 1

29 pages, 10807 KB  
Article
From Abstraction to Realization: A Diagrammatic BIM Framework for Conceptual Design in Architectural Education
by Nancy Alassaf
Sustainability 2025, 17(19), 8853; https://doi.org/10.3390/su17198853 - 3 Oct 2025
Abstract
The conceptual design phase in architecture establishes the foundation for subsequent design decisions and influences up to 80% of a building’s lifecycle environmental impact. While Building Information Modeling (BIM) demonstrates transformative potential for sustainable design, its application during conceptual design remains constrained by [...] Read more.
The conceptual design phase in architecture establishes the foundation for subsequent design decisions and influences up to 80% of a building’s lifecycle environmental impact. While Building Information Modeling (BIM) demonstrates transformative potential for sustainable design, its application during conceptual design remains constrained by perceived technical complexity and limited support for abstract thinking. This research examines how BIM tools can facilitate conceptual design through diagrammatic reasoning, thereby bridging technical capabilities with creative exploration. A mixed-methods approach was employed to develop and validate a Diagrammatic BIM (D-BIM) framework. It integrates diagrammatic reasoning, parametric modeling, and performance evaluation within BIM environments. The framework defines three core relationships—dissection, articulation, and actualization—which enable transitions from abstract concepts to detailed architectural forms in Revit’s modeling environments. Using Richard Meier’s architectural language as a structured test case, a 14-week quasi-experimental study with 19 third-year architecture students assessed the framework’s effectiveness through pre- and post-surveys, observations, and artifact analysis. Statistical analysis revealed significant improvements (p < 0.05) with moderate to large effect sizes across all measures, including systematic design thinking, diagram utilization, and academic self-efficacy. Students demonstrated enhanced design iteration, abstraction-to-realization transitions, and performance-informed decision-making through quantitative and qualitative assessments during early design stages. However, the study’s limitations include a small, single-institution sample, the absence of a control group, a focus on a single architectural language, and the exploratory integration of environmental analysis tools. Findings indicate that the framework repositions BIM as a cognitive design environment that supports creative ideation while integrating structured design logic and performance analysis. The study advances Education for Sustainable Development (ESD) by embedding critical, systems-based, and problem-solving competencies, demonstrating BIM’s role in sustainability-focused early design. This research provides preliminary evidence that conceptual design and BIM are compatible when supported with diagrammatic reasoning, offering a foundation for integrating competency-based digital pedagogy that bridges creative and technical dimensions of architectural design. Full article
(This article belongs to the Special Issue Advances in Engineering Education and Sustainable Development)
Show Figures

Figure 1

21 pages, 1538 KB  
Article
SarcoNet: A Pilot Study on Integrating Clinical and Kinematic Features for Sarcopenia Classification
by Muthamil Balakrishnan, Janardanan Kumar, Jaison Jacob Mathunny, Varshini Karthik and Ashok Kumar Devaraj
Diagnostics 2025, 15(19), 2513; https://doi.org/10.3390/diagnostics15192513 - 3 Oct 2025
Abstract
Background and Objectives: Sarcopenia is a progressive loss of skeletal muscle mass and function in elderly adults, posing a significant risk of frailty, falls, and morbidity. The current study designs and evaluates SarcoNet, a novel artificial neural network (ANN)-based classification framework developed in [...] Read more.
Background and Objectives: Sarcopenia is a progressive loss of skeletal muscle mass and function in elderly adults, posing a significant risk of frailty, falls, and morbidity. The current study designs and evaluates SarcoNet, a novel artificial neural network (ANN)-based classification framework developed in order to classify Sarcopenic from non-Sarcopenic subjects using a comprehensive real-time dataset. Methods: This pilot study involved 30 subjects, who were divided into Sarcopenic and non-Sarcopenic groups based on physician assessment. The collected dataset consists of thirty-one clinical parameters like skeletal muscle mass, which is collected using various equipment such as Body Composition Analyser, along with ten kinetic features which are derived from video-based gait analysis of joint angles obtained during walking on three terrain types such as slope, steps, and parallel path. The performance of the designed ANN-based SarcoNet was benchmarked against the traditional machine learning classifiers utilised including Support Vector Machine (SVM), k-Nearest Neighbours (k-NN), and Random Forest (RF), as well as hard and soft voting ensemble classifiers. Results: SarcoNet achieved the highest overall classification accuracy of about 94%, with a specificity and precision of about 100%, an F1-score of about 92.4%, and an AUC of 0.94, outperforming all other models. The incorporation of lower-limb joint kinetics such as knee flexion, extension, ankle plantarflexion and dorsiflexion significantly enhanced predictive capability of the model and thus reflecting the functional deterioration characteristic of muscles in Sarcopenia. Conclusions: SarcoNet provides a promising AI-driven solution in Sarcopenia diagnosis, especially in low-resource healthcare settings. Future work will focus on improving the dataset, validating the model across diverse populations, and incorporating explainable AI to improve clinical adoption. Full article
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
Show Figures

Figure 1

31 pages, 11924 KB  
Article
Enhanced 3D Turbulence Models Sensitivity Assessment Under Real Extreme Conditions: Case Study, Santa Catarina River, Mexico
by Mauricio De la Cruz-Ávila and Rosanna Bonasia
Hydrology 2025, 12(10), 260; https://doi.org/10.3390/hydrology12100260 - 2 Oct 2025
Abstract
This study compares enhanced turbulence models in a natural river channel 3D simulation under extreme hydrometeorological conditions. Using ANSYS Fluent 2024 R1 and the Volume of Fluid scheme, five RANS closures were evaluated: realizable k–ε, Renormalization-Group k–ε, Shear Stress Transport k–ω, Generalized k–ω, [...] Read more.
This study compares enhanced turbulence models in a natural river channel 3D simulation under extreme hydrometeorological conditions. Using ANSYS Fluent 2024 R1 and the Volume of Fluid scheme, five RANS closures were evaluated: realizable k–ε, Renormalization-Group k–ε, Shear Stress Transport k–ω, Generalized k–ω, and Baseline-Explicit Algebraic Reynolds Stress model. A segment of the Santa Catarina River in Monterrey, Mexico, defined the computational domain, which produced high-energy, non-repeatable real-world flow conditions where hydrometric data were not yet available. Empirical validation was conducted using surface velocity estimations obtained through high-resolution video analysis. Systematic bias was minimized through mesh-independent validation (<1% error) and a benchmarked reference closure, ensuring a fair basis for inter-model comparison. All models were realized on a validated polyhedral mesh with consistent boundary conditions, evaluating performance in terms of mean velocity, turbulent viscosity, strain rate, and vorticity. Mean velocity predictions matched the empirical value of 4.43 [m/s]. The Baseline model offered the highest overall fidelity in turbulent viscosity structure (up to 43 [kg/m·s]) and anisotropy representation. Simulation runtimes ranged from 10 to 16 h, reflecting a computational cost that increases with model complexity but justified by improved flow anisotropy representation. Results show that all models yielded similar mean flow predictions within a narrow error margin. However, they differed notably in resolving low-velocity zones, turbulence intensity, and anisotropy within a purely hydrodynamic framework that does not include sediment transport. Full article
Show Figures

Figure 1

14 pages, 879 KB  
Article
Predicting Factors Associated with Extended Hospital Stay After Postoperative ICU Admission in Hip Fracture Patients Using Statistical and Machine Learning Methods: A Retrospective Single-Center Study
by Volkan Alparslan, Sibel Balcı, Ayetullah Gök, Can Aksu, Burak İnner, Sevim Cesur, Hadi Ufuk Yörükoğlu, Berkay Balcı, Pınar Kartal Köse, Veysel Emre Çelik, Serdar Demiröz and Alparslan Kuş
Healthcare 2025, 13(19), 2507; https://doi.org/10.3390/healthcare13192507 - 2 Oct 2025
Abstract
Background: Hip fractures are common in the elderly and often require ICU admission post-surgery due to high ASA scores and comorbidities. Length of hospital stay after ICU is a crucial indicator affecting patient recovery, complication rates, and healthcare costs. This study aimed to [...] Read more.
Background: Hip fractures are common in the elderly and often require ICU admission post-surgery due to high ASA scores and comorbidities. Length of hospital stay after ICU is a crucial indicator affecting patient recovery, complication rates, and healthcare costs. This study aimed to develop and validate a machine learning-based model to predict the factors associated with extended hospital stay (>7 days from surgery to discharge) in hip fracture patients requiring postoperative ICU care. The findings could help clinicians optimize ICU bed utilization and improve patient management strategies. Methods: In this retrospective single-centre cohort study conducted in a tertiary ICU in Turkey (2017–2024), 366 ICU-admitted hip fracture patients were analysed. Conventional statistical analyses were performed using SPSS 29, including Mann–Whitney U and chi-squared tests. To identify independent predictors associated with extended hospital stay, Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied for variable selection, followed by multivariate binary logistic regression analysis. In addition, machine learning models (binary logistic regression, random forest (RF), extreme gradient boosting (XGBoost) and decision tree (DT)) were trained to predict the likelihood of extended hospital stay, defined as the total number of days from the date of surgery until hospital discharge, including both ICU and subsequent ward stay. Model performance was evaluated using AUROC, F1 score, accuracy, precision, recall, and Brier score. SHAP (SHapley Additive exPlanations) values were used to interpret feature contributions in the XGBoost model. Results: The XGBoost model showed the best performance, except for precision. The XGBoost model gave an AUROC of 0.80, precision of 0.67, recall of 0.92, F1 score of 0.78, accuracy of 0.71 and Brier score of 0.18. According to SHAP analysis, time from fracture to surgery, hypoalbuminaemia and ASA score were the variables that most affected the length of stay of hospitalisation. Conclusions: The developed machine learning model successfully classified hip fracture patients into short and extended hospital stay groups following postoperative intensive care. This classification model has the potential to aid in patient flow management, resource allocation, and clinical decision support. External validation will further strengthen its applicability across different settings. Full article
Show Figures

Figure 1

29 pages, 435 KB  
Article
Public Debt, Oil Rent, and Financial Development in MENA Countries: A Fractional Response Model Approach (FRM)
by Mashael Fahad Alkhurayji and Hamed Mohammed Alhoshan
Economies 2025, 13(10), 288; https://doi.org/10.3390/economies13100288 - 2 Oct 2025
Abstract
The rapid accumulation of public debt raises global concern over its implications for financial markets. This study examines the effect of domestic public debt on financial development in Middle East and North Africa (MENA) countries, a region marked by sharp heterogeneity in institutions, [...] Read more.
The rapid accumulation of public debt raises global concern over its implications for financial markets. This study examines the effect of domestic public debt on financial development in Middle East and North Africa (MENA) countries, a region marked by sharp heterogeneity in institutions, debt dynamics, and oil dependence, using annual panel data for 16 countries over the period (2000–2020). Our analysis employs a fractional response model (FRM), which accounts for the bounded nature of the dependent variable, corrects for heteroskedasticity, and incorporates country fixed effects. The findings reveal a significant negative effect of domestic public debt on financial development, consistent with the lazy banks and crowding-out hypotheses. This adverse relationship persists across different income groups and debt percentiles, with modest attenuation at higher debt levels. Oil rents are also found to exert a robust negative effect, highlighting the structural vulnerabilities associated with oil dependence. These results emphasize the importance of debt management, fiscal frameworks that account for commodity cycles, and policies to reduce the sovereign–bank nexus in fostering sustainable financial development in the region. Full article
(This article belongs to the Section Macroeconomics, Monetary Economics, and Financial Markets)
15 pages, 883 KB  
Article
An Enhanced RPN Model Incorporating Maintainability Complexity for Risk-Based Maintenance Planning in the Pharmaceutical Industry
by Shireen Al-Hourani and Ali Hassanlou
Processes 2025, 13(10), 3153; https://doi.org/10.3390/pr13103153 - 2 Oct 2025
Abstract
In pharmaceutical manufacturing, the reliability of machines and utility assets is critical to ensuring product quality, regulatory compliance, and uninterrupted operations. Traditional Risk-Based Maintenance (RBM) models quantify asset criticality using the Risk Priority Number (RPN), calculated from the probability and impact of failure [...] Read more.
In pharmaceutical manufacturing, the reliability of machines and utility assets is critical to ensuring product quality, regulatory compliance, and uninterrupted operations. Traditional Risk-Based Maintenance (RBM) models quantify asset criticality using the Risk Priority Number (RPN), calculated from the probability and impact of failure alongside detectability. However, these models often neglect the practical challenges involved in diagnosing and resolving equipment issues, particularly in GMP-regulated environments. This study proposes an enhanced RPN framework that replaces the conventional detectability component with Maintainability Complexity (MC), quantified through two practical indicators: Ease of Diagnosis (ED) and Ease of Resolution (ER). Thirteen Key Performance Indicators (KPIs) were developed to assess Probability, Impact, and MC across 185 pharmaceutical utility assets. To enable objective risk stratification, Jenks Natural Breaks Optimization was applied to group assets into Low, Medium, and High risk tiers. Both multiplicative and normalized averaging methods were tested for score aggregation, allowing comparative analysis of their impact on prioritization outcomes. The enhanced model produced stronger alignment with operational realities, enabling more accurate asset classification and maintenance scheduling. A 3D risk matrix was introduced to translate scores into proactive strategies, offering traceability and digital compatibility with Computerized Maintenance Management Systems (CMMS). This framework provides a practical, auditable, and scalable approach to maintenance planning, supporting Industry 4.0 readiness in pharmaceutical operations. Full article
(This article belongs to the Section Pharmaceutical Processes)
Show Figures

Figure 1

14 pages, 1366 KB  
Article
Describing Dietary Habits and Body Composition Among High-Intensity Functional Training Athletes: A Mixed Methods Approach
by Kworweinski Lafontant, Jack Livingston, Sofea Smith, Michelle A. Da Silva Barbera, Claudia Gonzalez, Susan Kampiyil, Ngoc Linh Nhi Nguyen, Blake Johnson, Jeffrey R. Stout and David H. Fukuda
Sports 2025, 13(10), 340; https://doi.org/10.3390/sports13100340 - 2 Oct 2025
Abstract
High-intensity functional training (HIFT) has grown in popularity in the past several decades, yet previous research has largely focused on the dietary habits and body composition of elite HIFT athletes and utilized only quantitative study designs, potentially limiting our understanding of typical HIFT [...] Read more.
High-intensity functional training (HIFT) has grown in popularity in the past several decades, yet previous research has largely focused on the dietary habits and body composition of elite HIFT athletes and utilized only quantitative study designs, potentially limiting our understanding of typical HIFT athletes. This study aimed to comprehensively describe the common dietary habits and body composition of HIFT athletes. Data were only analyzed descriptively. Among 62 HIFT athletes (age: 36 ± 11.7 years), we estimated body fat percentage (BF%) using a Siri 3-compartment model, and we assessed dietary habits, dietary supplement (DS) use, and open-response rationales for DS use/disuse via an online questionnaire. Qualitative data from open-response questions were coded and grouped via inductive thematic analysis. Body composition varied among both male (n = 36, BF% = 6.5–27.6%) and female participants (n = 26, BF% = 10.6–37.6%). Most participants reported regular consumption of lean meats and home-cooked meals, yet few participants (~20%) regularly consumed the recommended twice daily servings of dairy, fruits, vegetables, and whole grains. Most (77.4%) HIFT athletes reported DS use, with the average HIFT athlete using approximately six DS; dairy protein, creatine, caffeine, and electrolyte drinks were the most reported DS. Improving health, recovery, and nutrient intake were common reasons for using DS, whereas a lack of noticeable results was the most common reason for discontinuation. Some HIFT athletes may rely on DS to address nutrient gaps rather than whole foods. Full article
(This article belongs to the Collection Human Physiology in Exercise, Health and Sports Performance)
Show Figures

Figure 1

21 pages, 3036 KB  
Article
Infrared Thermography and Deep Learning Prototype for Early Arthritis and Arthrosis Diagnosis: Design, Clinical Validation, and Comparative Analysis
by Francisco-Jacob Avila-Camacho, Leonardo-Miguel Moreno-Villalba, José-Luis Cortes-Altamirano, Alfonso Alfaro-Rodríguez, Hugo-Nathanael Lara-Figueroa, María-Elizabeth Herrera-López and Pablo Romero-Morelos
Technologies 2025, 13(10), 447; https://doi.org/10.3390/technologies13100447 - 2 Oct 2025
Abstract
Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work [...] Read more.
Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work presents the design and clinical evaluation of a prototype device for non-invasive early diagnosis of arthritis (inflammatory joint disease) and arthrosis (osteoarthritis) using infrared thermography and deep neural networks. The portable prototype integrates a Raspberry Pi 4 microcomputer, an infrared thermal camera, and a touchscreen interface, all housed in a 3D-printed PLA enclosure. A custom Flask-based application enables two operational modes: (1) thermal image acquisition for training data collection, and (2) automated diagnosis using a pre-trained ResNet50 deep learning model. A clinical study was conducted at a university clinic in a temperature-controlled environment with 100 subjects (70% with arthritic conditions and 30% healthy). Thermal images of both hands (four images per hand) were captured for each participant, and all patients provided informed consent. The ResNet50 model was trained to classify three classes (healthy, arthritis, and arthrosis) from these images. Results show that the system can effectively distinguish healthy individuals from those with joint pathologies, achieving an overall test accuracy of approximately 64%. The model identified healthy hands with high confidence (100% sensitivity for the healthy class), but it struggled to differentiate between arthritis and arthrosis, often misclassifying one as the other. The prototype’s multiclass ROC (Receiver Operating Characteristic) analysis further showed excellent discrimination between healthy vs. diseased groups (AUC, Area Under the Curve ~1.00), but lower performance between arthrosis and arthritis classes (AUC ~0.60–0.68). Despite these challenges, the device demonstrates the feasibility of AI-assisted thermographic screening: it is completely non-invasive, radiation-free, and low-cost, providing results in real-time. In the discussion, we compare this thermography-based approach with conventional diagnostic modalities and highlight its advantages, such as early detection of physiological changes, portability, and patient comfort. While not intended to replace established methods, this technology can serve as an early warning and triage tool in clinical settings. In conclusion, the proposed prototype represents an innovative application of infrared thermography and deep learning for joint disease screening. With further improvements in classification accuracy and broader validation, such systems could significantly augment current clinical practice by enabling rapid and non-invasive early diagnosis of arthritis and arthrosis. Full article
(This article belongs to the Section Assistive Technologies)
Show Figures

Graphical abstract

34 pages, 1369 KB  
Article
Intergenerational Differences in Impulse Purchasing in Live E-Commerce: A Multi-Dimensional Mechanism of the ASEAN Cross-Border Market
by Yanli Pei, Jie Zhu and Junwei Cao
J. Theor. Appl. Electron. Commer. Res. 2025, 20(4), 268; https://doi.org/10.3390/jtaer20040268 - 2 Oct 2025
Abstract
Existing research on live-streaming e-commerce consumption behavior is mostly limited by a single disciplinary framework, unable to systematically parse the mechanism of macro-policies and cultural values on intergenerational consumer psychology. This study takes ASEAN cross-border live-streaming e-commerce as a scenario, integrates theories of [...] Read more.
Existing research on live-streaming e-commerce consumption behavior is mostly limited by a single disciplinary framework, unable to systematically parse the mechanism of macro-policies and cultural values on intergenerational consumer psychology. This study takes ASEAN cross-border live-streaming e-commerce as a scenario, integrates theories of economics, political science, and sociology, and constructs an innovative three-layer analysis model of “macroeconomic system–meso-market–micro-behavior” based on multi-source data from 2020 to 2024. It empirically explores the formation mechanism of intergenerational differences in impulse buying. The results show that the behavior differences of different groups are significantly driven by income gradient, cross-border policies (tariff adjustment and consumer protection regulations), and collectivism/individualism cultural orientations. The innovative contribution of this study is reflected in three aspects: Firstly, it breaks through the limitation of a single discipline, and for the first time, it incorporates structural variables such as policy synergy effect and family structure change into the theoretical framework of impulse buying, quantifying and revealing the differentiated impact of institutional heterogeneity in ASEAN markets on intergenerational behavior. Secondly, it reconstructs the transmission path of “cultural values–family structure–intergenerational behavior” and finds that the inhibitory effect of collectivism on impulse buying tends to weaken with age. Thirdly, it proposes a “policy instrument–generational response” matching model and verifies the heterogeneous impact of the same policy (such as tariff reduction) on different generations. This study fills the gaps in related research and can provide empirical support for ASEAN enterprises to formulate stratified marketing strategies and for policymakers to optimize cross-border e-commerce regulation. which is of great significance to promote the sustainable development of the regional live-broadcast e-commerce ecology. Full article
Show Figures

Figure 1

12 pages, 453 KB  
Article
A Comparison Between Two Bearing Surfaces for Total Hip Arthroplasty—Ceramic-on-Ceramic and Metal–Polycarbonate–Urethane—A Pseudo-Randomized Study
by Daniel Donaire Hoyas, Eladio Jiménez Mejías, Jesús Moreta Suárez, Manuel Sumillera García, Alberto Albert Ullibarri and Jorge Albareda Albareda
J. Funct. Biomater. 2025, 16(10), 371; https://doi.org/10.3390/jfb16100371 - 1 Oct 2025
Abstract
Background: Polycarbonate–urethane (PCU) is a recently developed bearing surface used in prosthetic hip surgery. It offers several theoretical advantages, including an elasticity modulus similar to that of natural cartilage, good lubrication properties, low wear, and the possibility of using large heads. However, comparative [...] Read more.
Background: Polycarbonate–urethane (PCU) is a recently developed bearing surface used in prosthetic hip surgery. It offers several theoretical advantages, including an elasticity modulus similar to that of natural cartilage, good lubrication properties, low wear, and the possibility of using large heads. However, comparative clinical experience is limited. The purpose of this study was to analyze the results of the PCU bearing surface and compare them with those of ceramic-on-ceramic (CoC) bearings using the same femoral stem model. (2) Methods: Following a propensity score matching analysis of a prospectively collected database, patients with a primary total hip arthroplasty aged between 18 and 60 years were included. Subjects were divided into two groups (PCU and CoC). Demographic, patient satisfaction, and implant survival data were recorded. Clinical results were evaluated using the Harris Hip Score (HHS) and the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). (3) Results: A total of 105 patients were included in each group. All patients exhibited a positive evolution on both the HHS and the WOMAC subscales between pre-op and one year post-op, no statistically significant differences being found between the groups with respect to improvement on the HHS (p = 0.172) or the pain (p = 0.523), stiffness (p = 0.448), and physical function (p = 0.255) subscales of the WOMAC. Head sizes in the PCU group were found to be larger, but this was not seen to have any effect on the patients’ clinical status or the prostheses’ dislocation rate. Although the complication rate was similar across the groups (p = 0.828), the incidence of squeaking was higher in the PCU group (p = 0.010). No differences were observed when comparing the implant survival rate (p = 0.427). nor in mean patient satisfaction (p = 0.138). (4) Conclusions: No differences were found in terms of clinical results, complications, implant survival, or patient satisfaction between the bearing surfaces under analysis, indicating that all of them are valid alternatives in total hip replacement, although the higher proportion of squeaking observed makes it advisable to exercise some caution. Full article
(This article belongs to the Section Bone Biomaterials)
14 pages, 1037 KB  
Article
MMSE-Based Dementia Prediction: Deep vs. Traditional Models
by Yuyeon Jung, Yeji Park, Jaehyun Jo and Jinhyoung Jeong
Life 2025, 15(10), 1544; https://doi.org/10.3390/life15101544 - 1 Oct 2025
Abstract
Early and accurate diagnosis of dementia is essential to improving patient outcomes and reducing societal burden. The Mini-Mental State Examination (MMSE) is widely used to assess cognitive function, yet traditional statistical and machine learning approaches often face limitations in capturing nonlinear interactions and [...] Read more.
Early and accurate diagnosis of dementia is essential to improving patient outcomes and reducing societal burden. The Mini-Mental State Examination (MMSE) is widely used to assess cognitive function, yet traditional statistical and machine learning approaches often face limitations in capturing nonlinear interactions and subtle decline patterns. This study developed a novel deep learning-based dementia prediction model using MMSE data collected from domestic clinical settings and compared its performance with traditional machine learning models. A notable strength of this work lies in its use of item-level MMSE features combined with explainable AI (SHAP analysis), enabling both high predictive accuracy and clinical interpretability—an advancement over prior approaches that primarily relied on total scores or linear modeling. Data from 164 participants, classified into cognitively normal, mild cognitive impairment (MCI), and dementia groups, were analyzed. Individual MMSE items and total scores were used as input features, and the dataset was divided into training and validation sets (8:2 split). A fully connected neural network with regularization techniques was constructed and evaluated alongside Random Forest and support vector machine (SVM) classifiers. Model performance was assessed using accuracy, F1-score, confusion matrices, and receiver operating characteristic (ROC) curves. The deep learning model achieved the highest performance (accuracy 0.90, F1-score 0.90), surpassing Random Forest (0.86) and SVM (0.82). SHAP analysis identified Q11 (immediate memory), Q12 (calculation), and Q17 (drawing shapes) as the most influential variables, aligning with clinical diagnostic practices. These findings suggest that deep learning not only enhances predictive accuracy but also offers interpretable insights aligned with clinical reasoning, underscoring its potential utility as a reliable tool for early dementia diagnosis. However, the study is limited by the use of data from a single clinical site with a relatively small sample size, which may restrict generalizability. Future research should validate the model using larger, multi-institutional, and multimodal datasets to strengthen clinical applicability and robustness. Full article
(This article belongs to the Section Biochemistry, Biophysics and Computational Biology)
Show Figures

Figure 1

25 pages, 1159 KB  
Article
Optimizing Agricultural Management Practices for Maize Crops: Integrating Clusterwise Linear Regression with an Adaptation of the Grey Wolf Optimizer
by Germán-Homero Morán-Figueroa, Carlos-Alberto Cobos-Lozada and Oscar-Fernando Bedoya-Leyva
Agriculture 2025, 15(19), 2068; https://doi.org/10.3390/agriculture15192068 - 1 Oct 2025
Abstract
Effectively managing agricultural practices is crucial for maximizing yield, reducing investment costs, preserving soil health, ensuring sustainability, and mitigating environmental impact. This study proposes an adaptation of the Grey Wolf Optimizer (GWO) metaheuristic to operate under specific constraints, with the goal of identifying [...] Read more.
Effectively managing agricultural practices is crucial for maximizing yield, reducing investment costs, preserving soil health, ensuring sustainability, and mitigating environmental impact. This study proposes an adaptation of the Grey Wolf Optimizer (GWO) metaheuristic to operate under specific constraints, with the goal of identifying optimal agricultural practices that boost maize crop yields and enhance economic profitability for each farm. To achieve this objective, we employ a probabilistic algorithm that constructs a model based on Clusterwise Linear Regression (CLR) as the primary method for predicting crop yield. This model considers several factors, including climate, soil conditions, and agricultural practices, which can vary depending on the specific location of the crop. We compare the performance of the Grey Wolf Optimizer (GWO) algorithm with other optimization techniques, including Hill Climbing (HC) and Simulated Annealing (SA). This analysis utilizes a dataset of maize crops from the Department of Córdoba in Colombia, where agricultural practices were optimized. The results indicate that the probabilistic algorithm defines a two-group CLR model as the best approach for predicting maize yield, achieving a 5% higher fit compared to other machine learning algorithms. Furthermore, the Grey Wolf Optimizer (GWO) metaheuristic achieved the best optimization performance, recommending agricultural practices that increased farm yield and profitability by 50% relative to the original practices. Overall, these findings demonstrate that the proposed algorithm can recommend optimal practices that are both technically feasible and economically viable for implementation and replication. Full article
(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
Back to TopTop