Search Results (168)

Human-Robot Collaboration (HRC) is pivotal for flexible, worker-centric manufacturing in Industry 5.0, yet dynamic task allocation remains difficult because operator states—fatigue and skill—fluctuate abruptly. I address this gap with a hybrid framework that couples real-time perception and double-estimating reinforcement learning. A Convolutional Neural Network (CNN) classifies nine fatigue–skill combinations from synthetic physiological cues (heart-rate, blink rate, posture, wrist acceleration); its outputs feed a Double Deep Q-Network (DDQN) whose state vector also includes task-queue and robot-status features. The DDQN optimises a multi-objective reward balancing throughput, workload and safety and executes at 10 Hz within a closed-loop pipeline implemented in MATLAB R2025a and RoboDK v5.9. Benchmarking on a 1000-episode HRC dataset (2500 allocations·episode⁻¹) shows the hybrid CNN+DDQN controller raises throughput to 60.48 ± 0.08 tasks·min⁻¹ (+21% vs. rule-based, +12% vs. SARSA, +8% vs. Dueling DQN, +5% vs. PPO), trims operator fatigue by 7% and sustains 99.9% collision-free operation (one-way ANOVA, p < 0.05; post-hoc power 1 − β = 0.87). Visual analyses confirm responsive task reallocation as fatigue rises or skill varies. The approach outperforms strong baselines (PPO, A3C, Dueling DQN) by mitigating Q-value over-estimation through double learning, providing robust policies under stochastic human states and offering a reproducible blueprint for multi-robot, Industry 5.0 factories. Future work will validate the controller on a physical Doosan H2017 cell and incorporate fairness constraints to avoid workload bias across multiple operators. Full article

House price prediction is crucial in real estate for informed decision-making. This paper presents an automated prediction system that combines genetic algorithms (GA) for feature optimization and Analysis of Variance (ANOVA) for statistical analysis. We apply and compare five ensemble machine learning (ML) models, namely Extreme Gradient Boosting Regression (XGBR), random forest regression (RFR), Categorical Boosting Regression (CBR), Adaptive Boosting Regression (ADBR), and Gradient Boosted Decision Trees Regression (GBDTR), on a comprehensive dataset. We used a dataset with 1000 samples with eight features and a secondary dataset for external validation with 3865 samples. Our integrated approach identifies Categorical Boosting with GA (CBRGA) as the best performer, achieving an R² of 0.9973 and outperforming existing state-of-the-art methods. ANOVA-based analysis further enhances model interpretability and performance by isolating key factors such as square footage and lot size. To ensure robustness and transparency, we conduct 10-fold cross-validation and employ explainable AI techniques such as Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), providing insights into model decision-making and feature importance. Full article

U.S. gasoline and diesel prices are often volatile, driven by geopolitical risks and disruptions in the fossil fuel market. Forest biomass fuels, particularly renewable diesel derived from logging residues, offer a low-carbon alternative with the potential to stabilize fuel prices. This study evaluates whether biomass can moderate fuel price volatility using ANOVA, Tukey post hoc tests, and quadratic regression based on monthly data for biomass production, inventories, and retail fuel prices. Findings reveal the existence of a significant nonlinear relationship between forest biomass inventory levels and fossil fuel prices. Average gasoline prices peaked in the medium-inventory group (M = 0.837) and dropped in the high-inventory group (M = 0.684). Diesel prices followed a similar pattern, with the highest values in the medium-inventory group (M = 0.963) and the lowest in the high-inventory group (M = 0.759). One-way ANOVA results were statistically significant for both gasoline (F(2, 99) = 7.39, p = 0.001) and diesel (F(2, 99) = 7.22, p = 0.0012). Tukey tests confirmed that diesel prices fell significantly from both medium to high and low to high-inventory levels. This result remains robust when using the biomass index level and the biomass production level. These results indicate a threshold effect: only at higher biomass inventories do fossil fuel prices decline, suggesting a potential for substitution. However, current policies inadequately support biomass integration, highlighting the need for targeted reforms. Full article

Background: Reliable and non-invasive methods for assessing welfare in poultry are essential for improving evidence-based welfare monitoring and advancing management practices in commercial production systems. The iris-to-pupil (IP) ratio, previously validated by our group in primates and cattle, reflects autonomic nervous system balance and may serve as a physiological indicator of stress in laying hens. This study evaluated the utility of the IP ratio under field conditions across diverse commercial layer housing systems. Materials and Methods: In total, 296 laying hens (Lohmann Brown, n = 269; White Leghorn, n = 27) were studied across four locations in Canada housed under different systems: Guelph (indoor; pen), Spring Island (outdoor and scratch; organic), Ottawa (outdoor, indoor and scratch; free-range), and Toronto (outdoor and hobby; free-range). High-resolution photographs of the eye were taken under ambient lighting. Light intensity was measured using the light meter app. The IP ratio was calculated using NIH ImageJ software (Version 1.54p). Statistical analysis included one-way ANOVA and linear regression using GraphPad Prism (Version 5). Results: Birds housed outdoors had the highest IP ratios, followed by those in scratch systems, while indoor and pen-housed birds had the lowest IP ratios (p < 0.001). Subgroup analyses of birds in Ottawa and Spring Island farms confirmed significantly higher IP ratios in outdoor environments compared to indoor and scratch systems (p < 0.001). The IP ratio correlated weakly with ambient light intensity (r² = 0.25) and age (r² = 0.05), indicating minimal influence of these variables. Although White Leghorn hens showed lower IP ratios than Lohmann Browns, this difference was confounded by housing type; all White Leghorns were housed in pens. Thus, housing system but not breed was the primary driver of IP variation. Conclusions: The IP ratio is a robust, non-invasive physiological marker of welfare assessment in laying hens, sensitive to housing environment but minimally influenced by light or age. Its potential for integration with digital imaging technologies supports its use in scalable welfare assessment protocols. Full article

This study presents a novel multi-material additive manufacturing (MMAM) strategy by combining virgin polylactic acid (vPLA) with recycled polylactic acid (rPLA) in a layered configuration to improve both performance and sustainability. Specimens were produced using fused deposition modelling (FDM) with various vPLA: rPLA ratios (33:67, 50:50, and 67:33) and two distinct layering approaches: one with vPLA forming the external layers and rPLA as the core, and a second using the reversed arrangement. Mechanical testing revealed that when vPLA is used as the exterior, printed components exhibit tensile strength and elongation improvements of 10–25% over conventional single-material prints, while the tensile modulus is largely influenced by the distribution of the two materials. Thermal analysis shows that both vPLA and rPLA begin to degrade at approximately 330 °C; however, rPLA demonstrates a higher end-of-degradation temperature (461.7 °C) and increased residue at elevated temperatures, suggesting improved thermal stability due to enhanced crystallinity. Full-field strain mapping, corroborated by digital microscopy (DM) and scanning electron microscopy (SEM), revealed that vPLA-rich regions display more uniform interlayer adhesion with minimal voids or microcracks, whereas rPLA-dominated areas exhibit greater porosity and a higher propensity for brittle failure. These findings highlight the role of optimal material placement in mitigating the inherent deficiencies of recycled polymers. The integrated approach of combining microstructural assessments with full-field strain mapping provides a comprehensive view of interlayer bonding and underlying failure mechanisms. Statistical analysis using analysis of variance (ANOVA) confirmed that both layer placement and material ratio have a significant influence on performance, with high effect sizes highlighting the sensitivity of mechanical properties to these parameters. In addition to demonstrating improvements in mechanical and thermal properties, this work addresses a significant gap in the literature by evaluating the combined effect of vPLA and rPLA in a multi-material configuration. The results emphasise that strategic material distribution can effectively counteract some of the limitations typically associated with recycled polymers, while also contributing to reduced dependence on virgin materials. These outcomes support broader sustainability objectives by enhancing energy efficiency and promoting a circular economy within additive manufacturing (AM). Overall, the study establishes a robust foundation for industrial-scale implementations, paving the way for future innovations in eco-efficient FDM processes. Full article

In this study, we present a comparative analysis of gradient descent-based optimizers frequently used in Convolutional Neural Networks (CNNs), including SGD, mSGD, RMSprop, Adadelta, Nadam, Adamax, Adam, and the recent EVE optimizer. To explore the interaction between optimization strategies and activation functions, we systematically evaluate all combinations of these optimizers with four activation functions—ReLU, LeakyReLU, Tanh, and GELU—across three benchmark image classification datasets: CIFAR-10, Fashion-MNIST (F-MNIST), and Labeled Faces in the Wild (LFW). Each configuration was assessed using multiple evaluation metrics, including accuracy, precision, recall, F1-score, mean absolute error (MAE), and mean squared error (MSE). All experiments were performed using k-fold cross-validation to ensure statistical robustness. Additionally, two-way ANOVA was employed to validate the significance of differences across optimizer–activation combinations. This study aims to highlight the importance of jointly selecting optimizers and activation functions to enhance training dynamics and generalization in CNNs. We also consider the role of critical hyperparameters, such as learning rate and regularization methods, in influencing optimization stability. This work provides valuable insights into the optimizer–activation interplay and offers practical guidance for improving architectural and hyperparameter configurations in CNN-based deep learning models. Full article

Platinum wires, known for their excellent electrical conductivity and durability, are widely used in high-precision industries, such as aerospace and automotive. These wires are typically coated with polyamide for protection; however, specific manufacturing processes require the coating to be selectively removed. Although traditional chemical stripping methods are effective, they are associated with high costs, safety concerns, and long processing times. As a result, laser ablation has emerged as a more efficient, precise, and cleaner alternative, especially at the microscale. In this study, ultraviolet nanosecond laser ablation was applied to remove polyamide coatings from ultra-thin platinum wires in a water-assisted environment. The presence of water enhances the process by promoting thermal management and minimizing debris. Key processing parameters, including the scanning speed, overlap percentage, and line distance, were evaluated. The optimal result was achieved at a scanning speed of 1200 mm/s, line distance of 1 µm, and single loop in water-ambient, where coating removal was complete, surface roughness remained low, and wire tensile strength was preserved. This performance is attributed to the effective energy distribution across the wire surface and reduced thermal damage due to the heat dissipation role of water, along with controlled overlap that ensured full coverage without overexposure. A thin, well-maintained water layer confined above the apex of the wire played a crucial role in regulating the thermal flow during ablation. This setup helped shield the delicate platinum substrate from overheating, thereby maintaining its mechanical integrity and preventing substrate damage throughout the process. This study primarily focused on analyzing the main effects and two-factor interactions of these parameters using Analysis of Variance (ANOVA). Interactions such as Speed × Overlap and Speed × Line Distance were statistically examined to identify the influence of combined factors on tensile strength and surface roughness. In the second phase of experimentation, the parameter space was further expanded by increasing the line distance and number of loops to reduce the overlap in the X-direction. This allowed for a more comprehensive process evaluation. Again, conditions around 1200 mm/s and 1500 mm/s with 2 µm line distance and two loops offered favorable outcomes, although 1200 mm/s was selected as the optimal speed due to better consistency. These findings contribute to the development of a robust, high-precision laser processing method for ultra-thin wire applications. The statistical insights gained through ANOVA offer a data-driven framework for optimizing future laser ablation processes. Full article

Background: Total Hip Replacement (THR) is a standard treatment for advanced hip osteoarthritis; yet, its effects on gait recovery remain understudied. This study examines gait pattern changes in women undergoing monitored rehabilitation after unilateral THR, using Statistical Parametric Mapping (SPM) to detect significant motion differences over time. Methods: This longitudinal study included 32 women who underwent primary cementless THR. Gait was assessed preoperatively and postoperatively at 6 weeks, 3 months, 6 months, and 12 months using a motion analysis system. Repeated measures ANOVA and post hoc SPM{t} analyses were conducted to evaluate significant gait changes across time points. Results: Significant improvements (p < 0.05) were observed in spatio-temporal parameters. Velocity increased from 0.42 ± 0.10 m/s (Ex1) to 0.72 ± 0.06 m/s (Ex5), stride length from 0.85 ± 0.12 m to 1.15 ± 0.07 m, and step length (involved leg) from 0.32 ± 0.08 m to 0.48 ± 0.05 m. Cycle time decreased from 1.50 ± 0.20 s to 1.22 ± 0.10 s, indicating improved gait efficiency. Post hoc SPM{t} analysis revealed significant kinematic changes in hip flexion-extension, knee flexion, and pelvic tilt, particularly between Ex2 and Ex3. Statistically significant improvements (p < 0.001) were observed in key spatio-temporal parameters. Conclusions: Gait parameters improved significantly within the first year post-THR, with the most pronounced changes occurring between the early and mid-term recovery phases. These findings support the need for targeted rehabilitation strategies in the first six months post-surgery. SPM analysis provides a robust method for detecting subtle gait adaptations, contributing to the refinement of post-THR rehabilitation strategies. Full article

Background/Objectives: Frailty is a multifactorial condition influenced by physical and psychosocial factors. Understanding longitudinal changes in these domains may guide prevention strategies. This study examines the relationship between frailty status, physical fitness, and psychosocial conditions in community-dwelling older adults using five-year longitudinal data. Methods: Participants were 52 out of 89 older adults who completed both baseline and five-year follow-up assessments (follow-up rate: 58.4%). Data were collected using 10 physical fitness indicators, the fitness age score (FAS), geriatric depression scale (GDS), Lubben social network scale short form (LSNS-6), and relevant items in the six Kihon Checklist (KCL) domains. Due to low prevalence of frailty, individuals with pre-frailty and frailty were combined into the frailty-risk group. Repeated measures ANOVA with sex as a covariate was conducted to compare groups. Logistic regression was used to identify baseline predictors of frailty status at five years. Statistical significance was set at p < 0.05. Results: GDS, LSNS-6, and KCL scores remained stable over five years. However, physical fitness significantly declined in several measures, including grip strength, vertical jump height, knee extension strength, functional reach, and FAS. A significant interaction for the timed up and go test showed that the robust group maintained function, while the frailty-risk group declined. Logistic regression identified KCL oral function as a significant predictor (OR = 5.331, 95% CI = 1.593–17.839, p = 0.007). Conclusions: Maintaining both oral function and physical fitness is vital for preventing frailty, even among health-conscious older adults. Proactive strategies may support healthy aging. Full article

To explore the prevalence of depression among emergency medicine (EM) interns before and during the COVID-19 pandemic. The Intern Health Study is a national longitudinal cohort study examining mental health among interns across various specialties. In this secondary analysis, we focused specifically on EM interns from 2008 to 2022. Participants completed a baseline survey before their intern year and quarterly surveys throughout their intern year. Depression severity was assessed using the Patient Health Questionnaire (PHQ9), with scores of 10 or higher indicating moderate-to-severe depression. In total, 1956 EM interns from 160 programs completed all PHQ9 surveys. PHQ9 scores at baseline (start of the intern year) were significantly lower prior to the COVID-19 pandemic compared to during it (p < 0.001). PHQ9 scores at month 9 were significantly higher during the COVID-19 pandemic (p < 0.05) compared to pre-COVID-19 pandemic interns at month 9. One-way ANOVA comparing pre-COVID-19 and during COVID-19 differences in PHQ9 from baseline to the end of intern year revealed a significant difference, with during COVID-19 differences being significantly less than pre-COVID-19. There was no significant difference in the proportion of interns with PHQ9 scores greater than 10 during the COVID-19 pandemic. The COVID-19 pandemic had a significant effect on the mental health of EM interns, with higher baseline depression scores observed during the pandemic. However, the smaller change in depression severity over the intern year during the pandemic suggests a complex interplay of factors that warrants further investigation. Our study is the first to examine depression among EM interns during the COVID-19 pandemic using a large, multi-year sample, providing a unique and comprehensive analysis of how the pandemic impacted mental health in this high-risk group. Unlike previous studies with smaller sample sizes, our research offers robust, generalizable insights into the trends and severity of depression in EM interns, highlighting the critical need for ongoing mental health support in medical training. Full article

To address the challenges in forecasting crude oil and hot-rolled coil futures prices, the aim is to transcend the constraints of conventional approaches. This involves effectively predicting short-term price fluctuations, developing quantitative trading strategies, and modeling time series data. The goal is to enhance prediction accuracy and stability, thereby supporting decision-making and risk management in financial markets. A novel approach, the multi-dimensional fusion feature-enhanced (MDFFE) prediction method has been devised. Additionally, a data augmentation framework leveraging multi-dimensional feature engineering has been established. The technical indicators, volatility indicators, time features, and cross-variety linkage features are integrated to build a prediction system, and the lag feature design is used to prevent data leakage. In addition, a deep fusion model is constructed, which combines the temporal feature extraction ability of the convolution neural network with the nonlinear mapping advantage of an extreme gradient boosting tree. With the help of a three-layer convolution neural network structure and adaptive weight fusion strategy, an end-to-end prediction framework is constructed. Experimental results demonstrate that the MDFFE model excels in various metrics, including mean absolute error, root mean square error, mean absolute percentage error, coefficient of determination, and sum of squared errors. The mean absolute error reaches as low as 0.0068, while the coefficient of determination can be as high as 0.9970. In addition, the significance and stability of the model performance were verified by statistical methods such as a paired t-test and ANOVA analysis of variance. This MDFFE algorithm offers a robust and practical approach for predicting commodity futures prices. It holds significant theoretical and practical value in financial market forecasting, enhancing prediction accuracy and mitigating forecast volatility. Full article

Accurate forecasting of COVID-19 case numbers is critical for timely and effective public health interventions. However, epidemiological data’s irregular and noisy nature often undermines the predictive performance. This study examines the influence of four smoothing techniques—the rolling mean, the exponentially weighted moving average, a Kalman filter, and seasonal–trend decomposition using Loess (STL)—on the forecasting accuracy of four models: LSTM, the Temporal Fusion Transformer (TFT), XGBoost, and LightGBM. Weekly case data from Ukraine, Bulgaria, Slovenia, and Greece were used to assess the models’ performance over short- (3-month) and medium-term (6-month) horizons. The results demonstrate that smoothing enhanced the models’ stability, particularly for neural architectures, and the model selection emerged as the primary driver of predictive accuracy. The LSTM and TFT models, when paired with STL or the rolling mean, outperformed the others in their short-term forecasts, while XGBoost exhibited greater robustness over longer horizons in selected countries. An ANOVA confirmed the statistically significant influence of the model type on the MAPE (p = 0.008), whereas the smoothing method alone showed no significant effect. These findings offer practical guidance for designing context-specific forecasting pipelines adapted to epidemic dynamics and variations in data quality. Full article

This study aimed to detect weeds in vineyards throughout the crop cycle using pixel-based classification of RGB imagery captured by unmanned aerial vehicles (UAVs). Five vegetation indices (NGRDI, NDVI, GLI, NDRE, and GNDVI) and three supervised classifiers (SVM, RT, and KNN) were evaluated during four flight campaigns. Classification performance was assessed using precision, recall, and F1-Score, supported by descriptive statistics (mean, standard deviation, and 95% confidence interval), inferential tests (Shapiro–Wilk, ANOVA, and Kruskal–Wallis), and visual map inspection. Statistical analyses, both descriptive and inferential, did not indicate significant differences between classification methods. NGRDI consistently showed strong performance, especially for vine and soil classes, and effectively detected weeds, with F1-Scores above 0.78 in some campaigns, occasionally outperforming the supervised classifiers. GLI displayed variable results and a higher sensitivity to noise, whereas NDVI showed limitations when applied to RGB data, particularly in sparsely vegetated areas. Among the classifiers, the SVM achieved the highest F1-Score for vine (0.9330) and soil (0.9231), whereas KNN produced balanced results and visually coherent maps. RT showed lower accuracy and greater variability, particularly in the weed class. Despite the lack of statistically significant differences, visual analysis favored NGRDI and SVM for generating cleaner classification outputs. Study limitations include lighting variability, reduced spatial coverage owing to low flight altitude, and a lack of spatial context in pixel-based methods. Future research should explore object-based approaches and advanced classifiers (e.g., Random Forest and Convolutional Neural Networks) to enhance robustness and generalization. Overall, RGB-based indices, particularly NGRDI, are cost-effective and reliable tools for weed detection, thereby supporting scalable precision in viticulture. Full article

With the global emphasis on sustainable growth and development, the depletion of natural energy reserves due to reliance on fossil fuels and non-renewable sources remains a critical concern. Despite strides in transitioning to electrical mobility, rural and agricultural communities depend heavily on liquefied petroleum gas and firewood for cooking, lacking viable, sustainable alternatives. This study focuses on community-led efforts to advance biogas adoption, providing an eco-friendly and reliable energy alternative for rural and farming households. By designing and developing balloon-type anaerobic biodigesters, this initiative provides a robust, cost-effective, and scalable method to convert farm waste into biogas for household cooking. This approach reduces reliance on traditional fuels, mitigating deforestation and improving air quality, and generates organic biofertilizer as a byproduct, enhancing agricultural productivity through organic farming. The study focuses on optimizing critical parameters, including the input feed rate, gas production patterns, holding time, biodigester health, gas quality, and liquid manure yield. Statistical tools, such as descriptive analysis, regression analysis, and ANOVA, were employed to validate and predict biogas output data based on experimental and industrial-scale data. Artificial neural networks (ANNs) were also utilized to model and predict outputs, inspired by the information processing mechanisms of biological neural systems. A comprehensive database was developed from experimental and literary data to enhance model accuracy. The results demonstrate significant improvements in cooking practices, health outcomes, economic stability, and solid waste management among beneficiaries. The integration of statistical analysis and ANN modeling validated the biodigester system’s effectiveness and scalability. This research highlights the potential to harness renewable energy to address socio-economic challenges in rural areas, paving the way for a sustainable, equitable future by fostering environmentally conscious practices, clean energy access, and enhanced agricultural productivity. Full article

Feature selection plays a crucial role in the effectiveness of distributed denial of service (DDoS) attack detection methods, particularly as network traffic data becomes increasingly complex. This study conducts a categorical investigation of feature selection methods in clustering-based DDoS attack detection, comparing wrapper and hybrid approaches. Through two experiments using one-way ANOVA analyses, the research evaluated the effectiveness of different clustering approaches and supervised learning algorithms. The findings reveal that clustering-based wrapper methods performed more effectively than supervised learning approaches in feature selection for clustering-based DDoS attack detection methods. The results show strong statistical significance for clustering-based methods, with p-values of less than 0.05 and η² values indicating robust relationships between methods. Our clustering-based wrapper approach achieved a 57.7% reduction in false positive rates compared to supervised learning methods (mean FPR of 0.17 versus 0.40) on the CICIDS2017 dataset, with certain configurations reaching a false positive rate of 0.000. A similar pattern was observed with the NSL-KD dataset, where clustering-based methods reduced false positive rates by 63.1% compared to supervised approaches (0.048 versus 0.128). This study provides empirical evidence for effective combinations in which organizations and agencies can implement DDoS attack detection methods that have high performance. Full article