Search Results (2,888)

Benchmarking embodied carbon in residential building stock accurately would involve a high volume of data sharing and would pose serious privacy and competitive issues among building construction stakeholders. This study introduces a new federated learning-based building stock modeling system (FedCarbon) that can allow embodied carbon to be evaluated collaboratively without data aggregation at a central place. The architecture proposed enables construction firms, cities, and providers of construction materials to collectively train predictive models at the same time as data sovereignty is achieved via a hierarchical federated aggregation mechanism with attention-based client weighting. A differentiated privacy scheme that is adaptively calibrated on noise guarantees the privacy of individual projects and allows for statistically significant benchmarking based on heterogeneous building portfolios. The framework also includes a gradient compression scheme based on momentum, which incurs an 82.6% reduction in communication overhead over traditional federated averaging-based methods and still maintains model convergence. The effectiveness of the approach is demonstrated with the help of comprehensive validation with the UCI Energy Efficiency Dataset, which includes 768 residential building configurations, and the Embodied Carbon in European Buildings Database, which includes 2340 residential units in 12 European jurisdictions. It has been experimentally shown that FedCarbon has a 94.2% prediction accuracy (R2) on embodied carbon intensity, with a mean absolute error of 21.4 kgCO₂e/m², and that (ε, δ) differential privacy can be guaranteed with ε = 1.0 and −δ = 10⁻⁵. This structure opens up building stock knowledge and hastens industry-wide implementation of low-carbon building strategies. Full article

In object detection, annotation cost and computational efficiency are important factors in iterative model improvement under standard benchmark settings. Active learning (AL) addresses this challenge by selecting informative samples for labeling; however, many detection-oriented AL methods incur substantial overhead due to repeated inference (e.g., augmentation-based consistency). This paper introduces Uncertainty3D, a lightweight uncertainty proxy designed for standard CNN-based object detectors. It leverages native pre-NMS predictions to estimate sample informativeness using a single forward pass. We propose a tri-dimensional formulation that captures inconsistencies in position, scale, and category across proposal-consistent predictions. Experiments on PASCAL VOC and MS COCO using representative CNN-based detectors (Faster R-CNN and RetinaNet) show competitive mAP versus representative baselines and about 3–$4\times$ faster uncertainty estimation than augmentation-based baselines. Full article

This integrative literature review synthesises five strands of recent scholarships on port city regions (PCRs): (1) their multidimensional transitions, (2) skills foresight and future competences, (3) challenges and reforms in vocational education and training (VET) systems, (4) social inclusion and equity in skills development, and (5) innovative VET methodologies in port-adjacent sectors. Drawing on the interdisciplinary academic and policy-oriented literature, this article adopts a qualitative, integrative review approach to examine how the twin green and digital transition is reshaping port city regions and their associated skills ecosystems. The review demonstrates that PCR transitions are not only technical but socio-institutional: while Onshore Power Supplies (OPSs), alternative fuels, and digital platforms are transforming operational landscapes, the success of these innovations depends critically on the adaptive capacity of workers, training systems, and governance arrangements. The article further examines emerging pedagogical approaches in port-adjacent VET, including work-based learning, micro-credentials, and immersive training methods. Taken together, the evidence converges on a central claim: the resilience and sustainability of port city regions depend on integrated skills systems that combine foresight, inclusivity, and pedagogical innovation. Without such systems, decarbonisation and digitalisation risk exacerbating social and spatial inequalities rather than fostering sustainable growth. The article concludes by outlining implications for research, policy, and practice, calling for integrative performance metrics, longitudinal evaluation, and quadruple helix collaboration to support inclusive, competitive, and sustainable port transitions. Full article

The palm swamp landscapes, particularly the Vereda wetlands and their associated swamp gallery forests (VED.SGF), comprise essential yet threatened ecosystems within the Brazilian Cerrado. In addition to supporting significant portions of biodiversity, they provide critical ecosystem services such as storing and filtering excess rainwater and serving as major carbon reservoirs in organic soils. These wetlands are directly linked to the drainage systems of the headwaters of the main Cerrado river basins, which together account for about two-thirds of Brazil’s hydrographic basins. Mapping and managing VED.SGF ecosystems through remote sensing present major challenges addressed in this first study. Their narrow, dendritic, and complex tabular spatial pattern, often elongated along watersheds on scales of hundreds of kilometers, suffering distortions due to human impact, and the limited amount of annotated data make segmentation particularly challenging. Existing deep learning (DL) methods, typically pre-trained on natural images, struggle to capture the spectral and spatial intricacies of these ecosystems. This study introduces a trained-from-scratch U-Net model supported by field-based experimental procedures to ensure high-quality wetland annotations. The resulting dataset covers approximately 7300 km² in western Bahia and provides domain-specific weights tailored to remote sensing applications. Using high-resolution (4.6 m) RGB mosaics, the model was trained, validated, and tested to establish a reproducible and scalable pipeline. The proposed method achieved robust results in an independent test area of 8040 km², with a mean IoU of 0.728, F1-score of 0.843, and Cohen’s Kappa of 0.837. These results demonstrate consistent performance and strong generalization to new areas, establishing a scientifically reliable baseline that situates the model competitively within the current state of the art. By releasing both the model weights and annotated dataset, this study provides valuable resources to advance future research on mapping and monitoring these unique and strategic wetland ecosystems. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder in which early detection remains a major clinical challenge due to heterogeneous motor and non-motor manifestations and the lack of reliable biomarkers. In recent years, machine learning (ML) and deep learning (DL) methods have been increasingly investigated as decision-support tools for PD screening using diverse clinical and behavioral data. This review synthesizes PD detection studies published between 2017 and 2025, systematically analyzing 32 representative works across multiple modalities, including MRI, PET, EEG, REM sleep biomarkers, voice recordings, gait signals, handwriting/drawing tasks, and finger-tapping measurements. Across the reviewed literature, high classification performance is frequently reported, with CNN-based and hybrid DL architectures achieving particularly strong results in imaging and time-series settings, while classical ML approaches such as SVM and ensemble models remain competitive for engineered feature-based datasets. However, the review also reveals major barriers to reliable translation, including small datasets, inconsistent evaluation protocols, limited external validation, and the risk of performance inflation caused by non-subject-independent data splitting. Overall, this review provides a structured and modality-oriented reference of algorithms, datasets, and performance trends, while highlighting key methodological gaps and practical priorities for developing robust and clinically deployable PD detection systems. Full article

As a critical step in industrial quality control, surface defect detection in aluminum materials remains challenging for minor defects despite advances in deep learning. To address this, this paper proposes an enhanced YOLOv8-based model, BFI-YOLO, that incorporates a Bidirectional Multi-scale Residual Network. Specifically, we design a Bidirectional Multi-scale Feature Pyramid Network (BM-FPN) based on BiFPN to strengthen cross-scale feature fusion. The parameter-free SimAM attention module is embedded to enhance subtle defect responses while suppressing background texture interference, without introducing additional computational overhead.Furthermore, we develop a Multi-scale Residual Convolution (MSRConv) module to capture defects of varying sizes on aluminum surfaces comprehensively. MSRConv utilizes multi-scale convolutional kernels to adapt to cross-scale defect features and retains shallow details via residual connections, thereby strengthening the model’s representation of fine defects. Extensive experiments on the public TAPSDD dataset show that BFI-YOLO achieves a precision of 91.3%, a recall of 89.8%, and mAP@0.5 of 92.1%, with only 1.8 M parameters. Compared to the baseline, BFI-YOLO reduces parameters by 40% while increasing mAP@0.5 by 4.2%, effectively balancing detection accuracy and lightweight performance. Optimized for resource-constrained industrial platforms such as embedded systems and mobile robots, BFI-YOLO meets real-time monitoring requirements while achieving competitive detection accuracy, providing an efficient and practical solution for metal surface defect detection. Full article

Indoor 3D point cloud semantic segmentation is a fundamental task for fine-grained scene understanding and intelligent perception. Due to the prohibitive cost of dense point-wise annotations, weakly supervised learning has emerged as a promising alternative for indoor point cloud segmentation. However, existing weakly supervised methods commonly rely on fixed confidence thresholds for pseudo-label selection, which exhibit limited generalization caused by threshold sensitivity, underutilization of informative low-confidence regions, and progressive noise accumulation during self-training. To address these issues, we propose TGR-T, a weakly supervised framework for indoor 3D point cloud semantic segmentation that incorporates truncated-Gaussian-weighted reliability with adaptive dynamic thresholding. Specifically, a reliability-adaptive dynamic thresholding strategy is introduced to guide pseudo-label selection based on the evolving confidence statistics of unlabeled mini-batches, with exponential moving average smoothing employed to produce stable global estimates and robust separation of reliable and ambiguous regions. To further exploit uncertain regions, a learnable truncated Gaussian weighting function is designed to explicitly model prediction uncertainty within the ambiguous set, providing soft supervision by assigning adaptive weights to low-confidence predictions during optimization. Extensive experimental results demonstrate that the proposed framework significantly enhances the exploitation of unlabeled data under extremely limited supervision: extensive experiments conducted on standard indoor 3D scene benchmarks demonstrate that TGR-T achieves competitive or superior segmentation performance under extremely sparse supervision and can even outperform several fully supervised baselines trained with dense annotations while using only 1% labeled points, thereby substantially narrowing the performance gap between weakly supervised and fully supervised 3D semantic segmentation methods. Full article

To address the issues of sample imbalance, unstable generation quality, and insufficient feature extraction in spectrum anomaly signal detection under complex electromagnetic environments, this paper proposes a VAE-GANGP identification model that integrates a Variational Autoencoder (VAE) with a Gradient Penalty-based Generative Adversarial Network (GAN-GP). First, the VAE is employed to encode the original spectrum, generating structured latent features that follow a standard normal distribution. This replaces the random noise input in traditional GANs, significantly enhancing the semantic consistency of generated samples and training stability. Second, an adversarial training mechanism based on Wasserstein distance with gradient penalty (WGAN-GP) is introduced, effectively mitigating mode collapse and gradient vanishing, thereby improving the model’s capability to fit complex signal distributions. Furthermore, a multi-objective optimization function combining reconstruction error and adversarial loss is constructed, establishing an end-to-end integrated framework for feature learning, signal reconstruction, and anomaly discrimination. Experiments are conducted using a synthetic dataset comprising various modulation types and simulated environments with different signal-to-noise ratios for systematic validation. The results demonstrate that the spectrum data generated by VAE-GANGP closely matches the distribution of real signals. Under AWGN-dominated synthetic test conditions, the model achieves an anomaly detection accuracy of 98.1%. When evaluated under more realistic channel impairments (phase noise, multipath, impulsive interference), the model maintains competitive performance, outperforming existing methods and demonstrating promising potential for practical electromagnetic spectrum monitoring. Its performance significantly surpasses traditional detection methods and single deep learning models, providing a highly reliable and adaptive solution for spatial electromagnetic spectrum anomaly detection. Full article

Rapid urbanization has significantly exacerbated the Urban Heat Island (UHI) effect in high-density megacities, driven by the intensifying competition between built-up morphology and natural cooling infrastructure. Current research, however, often fails to accurately predict land surface temperatures (LST) because traditional models frequently overlook the complex spatial dependencies and neighborhood spillover effects inherent in urban environments. Existing studies often ignore the spatial dependence of heat transfer. This study proposes an explainable machine learning framework incorporating spatial lag variables to capture the thermal spillover from adjacent neighborhood context—such as green space cooling diffusion or built-up heat accumulation—which is frequently treated as noise in traditional models. Taking Shenzhen as a case study, we integrated multi-source data (Landsat 8, building vectors, DEM) and developed an XGBoost regression model (R² = 0.806) augmented with SHAP (Shapley Additive exPlanations) to quantify the contributions of local and contextual features. The results revealed that: (1) Non-linear Thresholds: Vegetation cooling exhibits a saturation effect, with the highest marginal benefit observed in the NDVI range of 0.2–0.4, while building warming effects converge at extremely high densities due to mutual shading; (2) Neighborhood Spillovers: Spatial interaction analysis confirms significant cool island synergy (where clustered green spaces provide amplified cooling) and heat island agglomeration effects—e.g., green spaces surrounded by high ecological backgrounds provide amplified cooling benefits; (3) Spatial Antagonism: A novel Interaction Balance Index (IBI) based on game-theoretic SHAP contributions was constructed to map the source-sink competition patterns, identifying distinct heat-dominated (West) and cool-dominated (East) zones. Unlike traditional area-weighted source-sink landscape metrics, IBI enables a pixel-level additive decomposition of warming and cooling factors, quantifying the net thermal outcome of local morphology and neighborhood spillover. By explicitly encoding spatial context into non-linear modeling, this study provides a more mechanistically robust understanding of urban thermal environments. The identified thresholds and dominant driver maps offer precise, spatially differentiated guidance for urban climate-adaptive planning and ecological restoration. Full article

In recirculating aquaculture systems, fish detection is an essential component for maintaining effective farming operations. The availability of high-quality fish datasets is limited because of the richness of fish species, and the annotation of large-scale data, which is used to train models, is often labor-intensive and time-consuming. The presence of different fish species across batches introduces further challenges for consistent detection performance. This work introduces a few-shot learning approach for fish detection, utilizing a customized dataset as novel classes and the Fish4Knowledge dataset for base classes, thereby establishing a framework that enhances adaptability in data-scarce scenarios. Within the model architecture, multi-scale feature extraction is enhanced through an attention mechanism, which is integrated as a dedicated module to strengthen representation learning, thus enhancing the model’s capability to differentiate visually similar fish species. Two distinct customized fish datasets are employed to evaluate the robustness of the proposed method. Experimental results show that the proposed model performs competitively against TFA, Meta-RCNN, and VFA. In the base-training phase, it achieves a mAP of 0.775, slightly surpassing VFA, while in the 1-shot, 5-shot, and 10-shot fine-tuning settings, it obtains mAP values of 0.152, 0.247, and 0.265, respectively. A similar trend is observed on a subset of black fish, with mAP scores of 0.169, 0.253, and 0.286 in the corresponding few-shot settings. These results indicate that the proposed approach can maintain relatively stable detection accuracy and adaptability across different fish batches, offering a practical solution for fish detection tasks in aquaculture when annotated data is scarce. To further demonstrate the efficacy and practical utility of the proposed methodology, a case study in fish farming confirms that the enhanced model achieves consistent and precise detection across diverse fish species, even when trained with limited annotated data. Full article

Fifth generation (5G) networks have significantly enhanced connectivity, speed, and reliability, transforming industries with faster and more efficient communication. The Internet of Things (IoT) has introduced unprecedented convenience and automation, revolutionizing sectors such as healthcare, finance, and smart infrastructure. However, both 5G networks and IoT environments are experiencing a high frequency of attacks. Intrusion detection systems (IDSs) built on federated learning (FL) are being proposed to boost data privacy and security. However, these IDSs are related with the inherent drawbacks of FL, namely the existence of non-independently and identically (non-IID) distributed features and the machine learning model complexity. To address these limitations, we present a study that integrates a Mixture of Experts (MoE) into an FL setting in the task of intrusion detection. Specifically, to mitigate the issues of model complexity within the FL setting, we use a sparsely gated MoE layer consisting of a router/gating network and a set of experts. Only a subset of experts is selected via applying noisy top-k gating. To alleviate the issue of non-IID data, we adopt the Label-based Dirichlet Partition method, utilizing Dirichlet sampling with a hyperparameter $\alpha$ to simulate a label-based non-IID data distribution. Four FL strategies are employed. We perform our experiments on the 5G-NIDD and BoT-IoT datasets. Findings show that the proposed approach achieves competitive performance across both datasets under heterogeneous federated settings. Full article

This study develops an interpretable machine learning framework for type 1 motor insurance renewal classification using 70,290 real-world Thai policies, providing essential insights for pricing, customer retention, and operational decision making. The dataset was partitioned into a 70% training set, utilizing 5-fold cross-validation for hyperparameter tuning and model selection, and a 30% hold-out testing set to evaluate final model performance. Five machine learning models including Binary Logistic Regression, K-Nearest Neighbors, Support Vector Machines, Random Forests, and XGB are systematically evaluated across multiple curated feature sets generated through statistical filtering, stepwise selection, and permutation-based importance. Non-parametric tests are employed to compare model performance across scenarios. Experimental results show that a reduced four-feature Random Forest model (car age, net premium, sum insured, and car group) achieves the highest predictive performance (AUC = 99.62%; F1 = 98.15%), outperforming full-feature models while maintaining superior computational efficiency. Consequently, H2OAutoML serves as an external validation tool to verify that this manually curated, interpretable pipeline remains highly competitive with fully automated systems. Integrating a SHAP-based explainability layer quantifies predictor influence, ensuring transparency and regulatory alignment. Prioritizing feature parsimony, this study provides integrable insights for dynamic pricing and risk-adjusted retention, enhancing decision support within evolving motor insurance markets through transparent systems. Full article

For few-shot image classification tasks, the recognition accuracy of existing models remains limited due to the inherent complexity of the few-shot learning setting. To address this challenge, this paper proposes a few-shot image classification approach, termed GDFSIC, which integrates a Global–Local Channel Attention Module (GLCAM) with a graph-propagation-based Distance–Direction Similarity Earth Mover’s Distance (DDS-EMD). The GLCAM module is incorporated into the feature extractor to enhance focus on discriminative regions and increase model attention to critical feature areas. Furthermore, a Distance–Direction Similarity (DDS) metric is introduced as a more effective distance criterion for capturing subtle differences in latent spatial representations. The proposed method is evaluated on four widely used few-shot image classification benchmarks: CIFAR-FS, CUB-200-2011, mini-ImageNet, and Tiered-ImageNet. Experimental results demonstrate that our approach achieves a clear competitive advantage in classification accuracy across these datasets. Ablation studies and further analyses confirm the effectiveness of each component of the proposed framework. Full article

Rumour propagation in online social networks poses significant risks to public trust, economic stability, and crisis management. Existing models often struggle with heterogeneous feature spaces, adversarial dynamics between rumours and debunking information, and data sparsity in early outbreak stages. This study introduces a cross-domain framework for group behaviour prediction that integrates unified representation learning, game-theoretic adversarial modelling, and transfer adaptation. A hybrid BERT–Node2Vec encoder captures both semantic richness and structural influence, while evolutionary game theory quantifies competitive interactions between rumour-spreaders and refuters. To alleviate data scarcity, Joint Distribution Adaptation (JDA) aligns heterogeneous feature spaces across domains, enabling robust transfer learning. Evaluated on simulated and real-world social media datasets, the proposed model demonstrates improved accuracy and interpretability in predicting rumour diffusion trends under adversarial conditions. These findings highlight the value of integrating semantic, structural, and behavioural signals into a scalable architecture, offering a practical solution for safeguarding digital ecosystems against misinformation. Full article

Tennis match analysis is a critical component of sports science, offering data on player performance, workload management, and competitive stress. We developed a data-driven framework to classify tennis matches as high-stress or low-stress using the Association of Tennis Professionals’ match statistics. High-stress matches are characterized by extended duration or frequent break points, both representing elevated physical and psychological demands. We implement TabNet and compare its performance with recurrent deep learning models, including long short-term memory (LSTM), bidirectional LSTM, attention-enhanced LSTM, and convolutional LSTM. Experimental results show that TabNet achieves the best accuracy (98%), while the recurrent models maintain accuracies above 93%, demonstrating consistent predictive capability. To enhance interpretability, SHAP analysis identifies break points faced, break points saved, and match duration as the most influential determinants of match stress, with serving and returning features providing secondary contributions. These findings confirm the effectiveness of interpretable deep learning in sports analytics and highlight its potential for guiding training and match preparation. Full article