Search Results (417)

The global rise in electronic waste (e-waste), especially in semiconductor components such as circuit boards and microchips, underscores a critical need for improved recycling technology. Current industrial sorters often miss small, high-value components. This leads to the loss of precious metals and inefficient recycling processes. This paper introduces an automated detection framework for detecting semiconductor components in e-waste. It assesses ensemble learning methods that leverage the strengths of multiple YOLO (You Only Look Once) object detection models, including YOLOv5, YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLOv12. Three ensemble fusion strategies are systematically compared: standard Non-Maximum Suppression (NMS), voting-based strategies (Affirmative, Consensus, Unanimous), and Weighted Box Fusion (WBF) with both static and dynamic weight optimization. Our simulations demonstrate that using multiple models together is far more effective than a single model for the following reasons. 1. Higher Accuracy: The best configuration, Top-4 Consensus Voting ensemble strategy, achieved an mAP@0.5 of 59.63%, a 10.3% improvement over the best individual model (YOLOv8s, 54.04%); 2. Greater Reliability: It significantly reduced “false negatives” (missed detections), even in cluttered or crowded e-waste scenarios; 3. Enhanced Detection: While the individual YOLOv8 model is fast (taking only 62.6 ms), supporting real-time detection, the best ensemble configuration (Consensus Top-4) takes 384.9 ms, creating a trade-off between detection accuracy and speed; 4. Well-Balanced Performance: Some fusion strategies showed slight trade-offs in mAP for certain parts, but collectively achieved a 7% rise in F1-score, indicating a better balance between precision and recall. This research marks significant progress in smart recycling. Improved component identification allows for more efficient recovery of high-purity materials. This promotes a circular economy by ensuring that rare and strategic materials in electronics are reused instead of discarded. Full article

Winter thermal comfort in university classrooms in China’s Hot Summer and Cold Winter (HSCW) regions remains problematic due to mismatches between institutional heating setpoints and students’ actual thermal preferences. To investigate students’ thermal perceptions and behavioral responses, a post-occupancy evaluation (POE) survey was conducted, followed by field measurements in a typical classroom in Chengdu under three conditions: no-heating condition, heating conditions at 20 °C and 25 °C. Indoor environmental parameters were continuously monitored, and thermal comfort was assessed using the Predicted Mean Vote (PMV) and Predicted Percentage of Dissatisfied (PPD) model. The results show that no-heating conditions were unacceptable, highlighting the necessity of heating. While the 20 °C setpoint provided partial improvement, thermal comfort was not consistently achieved throughout the day. In contrast, the 25 °C setpoint maintained near-neutral conditions during most occupied periods. In addition, a pre-heating duration of approximately 30 min was found to be essential for reducing initial thermal discomfort. Overall, the findings indicate that fixed institutional heating standards may not adequately satisfy students’ thermal needs. Adaptive heating strategies that combine appropriate setpoints with sufficient pre-heating duration are therefore recommended to balance thermal comfort and energy efficiency in university classrooms in the HSCW regions. Full article

Older adults often need guidance when visiting new buildings for the first time. However, indoor navigation remains challenging due to the lack of Global Positioning System (GPS) availability, visually repetitive corridors, and frequent location failures. This article presents a multimodal indoor navigation assistant that combines graph-based route planning with visual landmark verification to provide step-by-step guidance. The environment is modelled as a directed graph whose nodes are annotated with semantic landmarks, and the graph is constructed primarily from a video of the building, reducing the need for 3D scanners, beacons, or other specialised instruments. Routes are calculated using Dijkstra’s shortest-path algorithm over the semantic graph. During navigation, camera frames are analysed using a restricted vision-language recognition strategy that only considers candidate landmarks from the current and next nodes, reducing false detections and improving interpretability. To increase robustness, a temporary voting mechanism was introduced to confirm node transitions, as well as a hierarchical redirection strategy with local and global recovery. The system is implemented in two modes: handheld mode with visual cues using augmented reality arrows, mini map and voice instructions, and hands-free mode with front camera using voice instructions and keywords. Evaluation involved preliminary technical testing in the United Kingdom followed by formal user validation in Spain. During these trials, participants reported high usability, strong confidence and safety, and increased perceived independence. Full article

Rapid urbanization has intensified microclimatic deterioration in temperate monsoon cities, directly affecting human thermal comfort. This study investigates the regulatory effects of common street tree species under varying street aspect ratios (H/W) and orientations in Shenyang, China, a representative temperate monsoon city characterized by cold winters. Field surveys and questionnaire data were combined with ENVI-met simulations to quantify thermal comfort responses using the Universal Thermal Climate Index (UTCI). Results demonstrate that street geometry strongly constrains microclimate regulation: streets with H/W = 1.2 and a SE–NW orientation achieved the most favorable balance between shading and ventilation, yielding the lowest UTCI values. Significant interspecies variability was observed: Golden Elm and Chinese Willow provided the greatest cooling benefits, whereas Ginkgo exhibited limited adaptability, particularly in enclosed or highly open canyons. A comparison with subjective thermal comfort votes confirmed strong model reliability, though discrepancies emerged in dense commercial areas due to non-meteorological factors. Based on these findings, a spatially driven, species-adaptive, and human-centered framework is proposed to optimize street greening strategies in a temperate monsoon city characterized by cold winters. This research provides quantitative evidence for urban greening design, highlights the necessity of integrating spatial form with tree-species selection, and offers practical guidance for resilient thermal comfort management in rapidly urbanizing cold-region cities. Full article

Indoor Environmental Quality (IEQ) plays a vital role in occupant health and productivity. However, current Building Management Systems (BMS) often struggle in sustaining optimal IEQ levels due to limitations in data management and lack of occupant-centric feedback loops. To address these gaps, this research synthesizes the state-of-the-art methods for IEQ monitoring, assessment, and control within Building Automation Systems (BAS), identifying both technological and methodological advancements, as well as highlighting the challenges and potential opportunities for future innovations. Employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, this multi-stage literature review analyzes 176 publications from 1997 to 2024, with a focus on the decade of rapid technological evolution from 2014 to 2024. The review focuses on high-impact journals indexed in Scopus to ensure quality while acknowledging the potential bias inherent in a single-database search. The synthesis reveals a methodological shift in monitoring from sparse, zone-level sensing towards dense, multi-modal systems that incorporate physiological data via wearables and behavioral recognition through computer vision. Assessment techniques are evolving from static models such as the Predicted Mean Vote (PMV) towards adaptive, personalized frameworks supported by Digital Twins and integrated simulations. Furthermore, control logic is transitioning toward Reinforcement Learning and Model Predictive Control to proactively manage occupancy surges and environmental variables. This evolution of monitoring approaches, assessment techniques, and control strategies is represented within the study’s Three-Tiered Developmental Trajectory, providing a novel Body of Knowledge (BOK) for mapping the transition of building systems from reactive tools to autonomous, occupant-centric agents. This study also introduces a Cross-Modal Interaction Matrix to systematically analyze the systemic trade-offs between IEQ domains. Furthermore, by establishing the “Implementation Frontier,” this work identifies the specific technical and ethical bottlenecks, such as “false vacancy” sensing errors, fragmented data silos, and the ethical complexities of high-resolution data collection that prevent academic innovations from becoming industry standards. To bridge these gaps, we conclude that the next generation of “cognitive buildings” must prioritize three pillars: resolving binary sensing limitations, harmonizing data via vendor-neutral APIs, and adopting privacy-preserving architectures to ensure scalable, interoperable, and occupant-centric optimization. Full article

Optimizing nitrogen (N) fertilization is essential for sustaining durum wheat yield and grain quality while reducing the environmental impacts associated with N over-application. Hyperspectral sensing provides a rapid and non-destructive approach for monitoring crop N status. However, high-dimensional data, phenology-dependent spectral responses, and spatial autocorrelation in field measurements limit robust nitrogen classification and interpretation. This study evaluated hyperspectral-based nitrogen status classification in durum wheat under Mediterranean field conditions and identified key spectral regions using explainable artificial intelligence. A field experiment was conducted in Southern Italy using ten N fertilization rates (0–180 kg N ha⁻¹). Canopy reflectance was acquired at the booting and heading stages from georeferenced sampling locations. Three nitrogen stratification strategies (binary Low–High, Extreme, and three-level) were evaluated using Random Forest, SVM-RBF, and XGBoost classifiers. Model performance was assessed using spatially independent Leave-One-Plot-Out cross-validation at both the sample and plot levels, with plot-level predictions derived through majority voting. Classification robustness was strongly influenced by the stratification strategy and phenological stage. The binary Low–High stratification achieved the highest sample-level accuracy, with a maximum of 0.78 at booting (SVM-RBF) and 0.75 at heading (SVM-RBF), whereas the Extreme stratification produced intermediate performance, with maximum accuracies of 0.73 at booting (SVM-RBF) and 0.63 at heading (XGBoost). Plot-level aggregation improved performance, reaching up to 0.90 at booting and 1.00 at heading. SHAP analysis highlighted red, red-edge, and near-infrared wavelengths as the dominant contributors, with increased reliance on longer wavelengths at the heading. Overall, explainable machine learning provides a robust framework for hyperspectral nitrogen monitoring in durum wheat. Full article

Background and Objectives: Diabetes mellitus represents one of the most prevalent chronic metabolic disorders worldwide, necessitating precise insulin dose management to prevent both acute and long-term complications. The optimization of insulin dosing remains a significant clinical challenge, as inappropriate dosing can lead to hypoglycemia or hyperglycemia, each carrying substantial morbidity risks. Machine learning approaches have emerged as promising tools for developing clinical decision support systems; however, their practical implementation requires both high predictive accuracy and model interpretability. This study aimed to develop and evaluate an explainable machine learning framework for predicting insulin dose adjustments in diabetic patients. We sought to compare multiple ensemble learning approaches and identify the optimal model configuration that balances predictive performance with clinical interpretability through comprehensive SHAP and LIME analyses. Materials and Methods: A comprehensive dataset comprising 10,000 patient records with 12 clinical and demographic features was utilized. We implemented and compared nine machine learning models, including gradient boosting variants (XGBoost, LightGBM, CatBoost, GradientBoosting), AdaBoost, and four ensemble strategies (Voting, Stacking, Blending, and Meta-Learning). Model interpretability was achieved through SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) analyses. Performance was evaluated using accuracy, weighted F1-score, area under the receiver operating characteristic curve (AUC-ROC), precision-recall AUC (PR-AUC), sensitivity, specificity, and cross-entropy loss. Results: The Meta-Learning Ensemble achieved superior performance across all evaluation metrics, attaining an accuracy of 81.35%, weighted F1-score of 0.8121, macro-averaged AUC-ROC of 0.9637, and PR-AUC of 0.9317. The model demonstrated exceptional sensitivity (86.61%) and specificity (91.79%), with particularly high performance in detecting dose reduction requirements (100% sensitivity for the ‘down’ class). SHAP analysis revealed insulin sensitivity, previous medications, sleep hours, weight, and body mass index as the most influential predictors across different insulin adjustment categories. The meta-model feature importance analysis indicated that LightGBM probability estimates contributed most significantly to the ensemble predictions. Conclusions: The proposed explainable Meta-Learning Ensemble framework demonstrates robust predictive capability for insulin dose adjustment recommendations while maintaining clinical interpretability. The integration of SHAP-based explanations facilitates clinician understanding of model predictions, supporting transparent and informed decision-making in diabetes management. This approach represents a significant advancement toward the clinical implementation of artificial intelligence in personalized insulin therapy. Full article

The government’s scientific disclosure of food safety inspection information can guide consumers toward rational substitution choices, thereby improving food safety while transforming individual decision-making into collective action, thereby achieving social co-governance. This process activates the “voting with their feet” market mechanism, which exerts pressure on supply chain enterprises to improve quality control. However, the current mismatch between disclosed information and consumer demand significantly weakens this effect. Drawing on evolutionary game theory, this study constructs an evolutionary game model involving producers, sellers, and consumers to explore how information alignment shapes stakeholder behavior. The findings indicate that improving information alignment effectively nudges consumers toward informed substitution choices, reinforcing the market-driven pressure on supply chain enterprises to strengthen quality control; reducing quality control costs is a more effective short-term incentive for sellers than increasing market returns; and when information alignment is low, prioritizing inspections of sellers more efficiently enhances co-governance performance, whereas under high alignment, stronger regulation of producers becomes more effective. Aligning the content, channels, and presentation of government-disclosed inspection information with consumer needs is critical to empowering effective social co-governance. These findings provide theoretical foundations and policy insights to optimize information disclosure strategies and regulatory resource allocation. Full article

The incorporation of recycled concrete aggregates (RCAs) into self-compacting concrete (SCC) represents a critical sustainable construction strategy addressing both construction waste management and natural resource conservation. However, predicting the compressive strength of recycled aggregate self-compacting concrete (RASCC) remains challenging due to complex nonlinear interactions among mixture parameters. This study develops a robust predictive framework using ensemble machine learning algorithms to accurately estimate RASCC compressive strength across diverse mixture compositions. A comprehensive database comprising 301 experimental specimens with 18 input variables—including curing age, binder components, water-to-binder ratio, recycled aggregate properties, and supplementary cementitious materials—was systematically analyzed. Four advanced modeling approaches were evaluated: Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Stacked Generalization with Ridge regression meta-learner, and Voting ensemble with Non-Negative Least Squares optimization. The Stacking ensemble model demonstrated superior predictive performance on the independent test set, with R² = 0.963, RMSE = 3.321 MPa, and MAE = 2.506 MPa. Rigorous residual analysis confirmed model validity through satisfaction of normality, homoscedasticity, and independence assumptions. SHAP interpretability analysis identified specimen age as the dominant predictor, followed by recycled aggregate density and water-to-binder ratio, while elucidating the complex nonlinear contributions of supplementary cementitious materials including fly ash and ground granulated blast furnace slag. The developed framework demonstrates practical applicability for predicting RASCC compressive strength across conventional to high-performance grades, facilitating sustainable mix design optimization while maintaining structural performance requirements, and advancing circular economy principles through confident integration of recycled aggregates in SCC applications. Full article

As a privacy-preserving distributed machine learning paradigm, federated learning (FL) faces serious communication bottlenecks in practical deployment. In this paper, we propose FedLayerPrune, a communication-efficient federated learning method that integrates three synergistic components: (i) a layer-adaptive pruning strategy that dynamically allocates pruning rates based on layer sensitivity and network depth; (ii) a heterogeneity-aware aggregation mechanism that combines sample-size weighted averaging with mask consensus voting to enhance robustness under non-IID data distributions; and (iii) a dynamic pruning rate scheduler that progressively increases compression intensity across training rounds. Unlike existing approaches that apply uniform pruning or consider these techniques in isolation, FedLayerPrune achieves a principled coordination among layer-wise importance evaluation, temporal pruning scheduling, and heterogeneous model aggregation. Extensive experiments on CIFAR-10, MNIST, and Fashion-MNIST demonstrate that FedLayerPrune reduces communication costs by up to 68.3% compared with standard FedAvg, while maintaining model accuracy within a 2% margin. Moreover, our method exhibits stronger robustness and faster convergence under severe non-IID data distributions. These results suggest that FedLayerPrune provides a practical and effective solution for deploying federated learning in resource-constrained edge computing environments. Full article

Causal inference in text data has been a demanding objective in the field of natural language processing, mainly due to the intrinsic ambiguity and context sensitivity inherent in data, inducing uncertainty. Diminishing this uncertainty is essential in identifying reliable causal connections and advancing predictive consistency. In this research, we introduce an uncertainty-aware ensemble architecture that combines multiple text embedding schemes with both linear and nonlinear classifiers to boost causal text detection. Both sparse and neural-level embeddings were employed, and then combined it with an ensemble weighting approach based on two uncertainty estimation techniques, namely entropy-based and KL divergence-based. Unlike conventional ensemble methods with uniform or fixed voting strategies, our approach assigns weights inversely proportional to classifier uncertainty, ensuring that confident models exert greater influence on the final decisions. Our results show that TF-IDF, through its effective word frequency weighting scheme, consistently outperforms other embedding techniques, achieving better performance across both linear and nonlinear classifiers on both datasets (News Corpus and CausalLM–Adjective group). The experimental results show that our uncertainty-aware ensemble approach enhances both calibration and confidence predictions. Entropy-based weighting improves confidence in the case of linear classifiers with accuracy, F1-score, entropy and prediction confidence values of 94.3%, 94.0%, 0.382 and 0.774, respectively, while in the case of nonlinear classifiers the KL divergence-based weighting acquires a better performance with an accuracy of 97.6%, F1-score of 97.2%, KL Mean value of around 0.055 and LogLoss of 0.221. Full article

Prediction of the ultimate moment capacity (Mu) of BFRP-reinforced concrete beams is complicated by nonlinear parameter interactions and the linear-elastic response of BFRP, reducing the accuracy of conventional design models. This study develops an optimized machine learning (ML) framework incorporating random forest, extra trees, gradient boosting, adaboost, bagging, support vector regression, histogram-based gradient boosting, and ensemble voting and stacking strategies for reliable prediction of the Mu of BFRP-reinforced concrete beams. A comprehensive database of material, geometric, reinforcement, and BFRP mechanical parameters was analyzed, and model performance was evaluated using an 80/20 train–test split and 10-fold cross-validation based on R², RMSE, MAE, and MAPE. The stacking regressor demonstrated superior predictive performance, achieving an R² of 0.999 (RMSE = 0.590) in training and an R² of 0.988 (RMSE = 2.487) in testing, indicating excellent robustness and strong generalization capability in predicting Mu. Furthermore, interpretability analyses based on SHAP, PDP, ALE, and ICE demonstrate that span length (L) and beam depth (h) constitute the governing parameters in the prediction of Mu. Unlike prior studies focused mainly on predictive accuracy, this work proposes an optimized and interpretable stacking ensemble framework that integrates explainable AI with classical flexural mechanics for physically consistent and reliable prediction of the ultimate moment capacity of BFRP-reinforced concrete beams. Full article

Thermal comfort in office buildings is a key factor in occupant well-being and productivity, yet it poses a challenge due to the diversity of individual thermal characteristics and preferences. This study aims to investigate the relationships among thermal discomfort of occupants in office buildings, the ventilation mode, and individual occupant characteristics under actual-use conditions. Three buildings with a hybrid ventilation mode (natural ventilation and air-conditioning) and one building with central air-conditioning were evaluated. Data on thermal discomfort and occupant characteristics were collected via electronic questionnaires. A total of 7564 records were collected, of which 945 corresponded to clearly defined thermal discomfort (488 for heat discomfort and 457 for cold discomfort). The results showed that heat discomfort was more frequent among men and cold discomfort among women, with gender emerging as the most consistent individual factor associated with discomfort. The 30–50 age group, occupants with normal body mass index, lower clothing insulation, and lower metabolic rate accounted for a higher absolute number of discomfort reports; however, proportional analyses indicated relatively similar discomfort rates across these categories, reinforcing that thermal perception results from the combined influence of building operation and individual sensitivity rather than from isolated individual characteristics. A higher incidence of thermal discomfort, mainly due to cold, was also observed in air-conditioned environments. Among women, 68.8% of cold discomfort votes were associated with air-conditioning, while among men, it was 83.2%. In summary, the results highlight the need for strategies to personalise thermal comfort, with individual control and adaptive temperature adjustments in office buildings. Full article

Background/Objectives: This study proposes a comprehensive classification framework for the automatic detection of Alzheimer’s disease using handwriting data. An enriched feature space is constructed by combining 18 baseline features extracted from raw handwriting signals with 30 additional features derived from established handwriting analysis studies, resulting in a total of 48 features. To enhance clinical practicality, a task reduction analysis is conducted by comparing the full dataset containing 25 handwriting tasks with a reduced dataset comprising 14 selected tasks. Methods: The proposed framework employs a two-stage evaluation strategy involving four feature selection methods (Random Forest Feature Importance, Extreme Gradient Boosting Feature Importance, L1 Regularization and Recursive Feature Elimination), three normalization techniques (Unnormalized, Min–Max and Z-Score), and five baseline machine learning classifiers (Random Forest, Logistic Regression, Multilayer Perceptron, XGBoost and Support Vector Machines). In the second stage, a dynamic ensemble learning strategy is introduced, where the most effective classifiers are adaptively selected for each cross-validation fold and integrated using soft and hard voting schemes. Results: The experimental results demonstrate that reducing the number of tasks leads to an improvement in average classification accuracy from 79.47% to 81.03%, while simultaneously decreasing training time and memory consumption by approximately 40% and 35%, respectively. The highest classification performance, achieving an accuracy of 94.20%, is obtained using the Hard Ensemble combined with L1-based feature selection. Conclusions: These findings highlight that the joint use of enriched feature representations, task reduction, and dynamic ensemble learning provides an effective and computationally efficient solution for handwriting-based Alzheimer’s disease detection. Full article

In contemporary 5G network environments, intrusion detection systems must balance detection accuracy with operational efficiency, as improvements in one dimension are often achieved at the expense of the other. This study addresses this trade-off by proposing a lightweight two-stage intrusion detection architecture that augments a standard decision-tree classifier with a conditional counter-inspection mechanism. At inference time, a global decision tree produces an initial classification for each traffic record, which is selectively validated by a small set of class-biased expert trees trained under controlled minority exposure. Only experts associated with the opposite class of the initial prediction are activated, and decision revision is governed by a unanimous-dissent rule, ensuring conservative and deterministic correction while avoiding over-correction. Experiments conducted on the 5G-NIDD dataset in a binary benign/malicious setting show that the proposed architecture consistently improves upon the standalone decision tree, reducing false negatives from 51 to 27 (−47.1%) and false positives from 48 to 30 (−37.5%), and achieving an F1-score of 0.99981 on a held-out test set. Ablation and paired statistical tests confirm that these gains arise from selective validation and the unanimous-dissent mechanism rather than from uniform ensembling. The complete pipeline operates in the microsecond inference regime per record, evaluates fewer models on average than flat voting strategies, and preserves full interpretability through deterministic decision paths, making it suitable for practical and resource-constrained 5G intrusion detection deployments. Full article