Search Results (476)

With accelerating global urbanization and increasingly diverse demands for public spaces, promoting urban low-carbon transitions and enhancing residents’ quality of life have become central missions of modern urban development. As one of the city’s primary arteries, streets—through their green landscapes, slow-moving transportation systems, and public facilities—play an indispensable role in reducing carbon emissions, promoting healthy living, and improving residents’ well-being. In this study, the Yubei District of Chongqing was selected as the research area, and an automated evaluation framework was proposed for street visual quality, based on multi-source street view data and ensemble learning. PSP-Net semantic segmentation model was employed to extract eight key visual indicators from street view images, including green view index, Visual Entropy (Entropy), sky view factor (SVF), drivable space, sidewalk, safety facilities, buildings, and enclosure. Based on these features, a Stacking-based ensemble learning model was constructed, integrating multiple base models such as Random Forest, XGBoost, and LightGBM, with Linear Regression as the meta-learner, to predict street visual quality. The results demonstrate that the ensemble model significantly outperforms any single model, achieving a correlation coefficient (r) of 0.77 and effectively capturing the complex perceptual features of street environments. This study provides a reliable, intelligent, and quantitative method for large-scale evaluation of urban street visual quality, while supplying data support and decision-making references for street renewal and spatial optimization. Full article

In the fabrication process of pipelines for petrochemical and other industries, weld reinforcement is often excessive and adversely affects subsequent processes such as anticorrosion treatment and surface coating. Weld reinforcement must be removed through a grinding process. Welding deformation and fit-up errors often lead to highly irregular weld geometries, which makes robotic grinding difficult and causes the task to still heavily rely on manual operation. To address this issue, this study proposes an automatic weld recognition and grinding trajectory planning method based on 3D visualization and deep learning. A weld recognition network, termed WSR-Net, has been developed based on an improved PointNet++ architecture with a cross-attention mechanism, achieving a segmentation accuracy of 98.87% and a mean intersection over union of 90.71% on the test set. An intrinsic shape signature (ISS) key point selection algorithm with orthogonal slicing-based pruning optimization is developed to robustly extract key weld ridge points that characterize the weld trend on rugged weld surfaces. According to the height differences between the weld and the adjacent base metal surfaces, the grinding reference surface is fitted using the weld contour through the moving least-squares method. The ridge line points are projected onto the grinding reference surface along the local normal to generate the expected grinding trajectory points. The grinding trajectory that meets the process constraints is generated through reverse layer slicing. Grinding experiments demonstrate that the proposed WSR-Net achieves robust segmentation performance for both planar and curved surface welds. With the reverse layered trajectory planning method, the proposed method enables high-precision automatic grinding of complex spatially curved surface welds. The results show that the final grinding mean error is 0.316 mm, which satisfies the preprocessing requirements for subsequent processes. The proposed method provides a feasible technical method for the intelligent grinding of spatially curved surface welds. Full article

Net cleaning robots have been playing an increasingly important role in offshore aquaculture due to their efficiency and labor-saving capabilities. However, in practice, these robots are still entirely teleoperated and require constant, skilled human operation. The mesh intersection points, which serve as a structural feature of the nets, provide valuable visual cues for robot self-localization and net damage identification. Therefore, the detection and tracking of these points are crucial for developing autonomous net cleaning robots. To achieve intersection point detection, we propose NPUNet-lite, a lightweight model based on U-Net. This model significantly minimizes computational resources and model size while preserving high detection accuracy. For reliable point tracking, we develop the NlPTrack algorithm, which incorporates an iterative closest point-based association strategy to meet spatial constraints between points within a frame, and a cascaded association strategy to satisfy homographic and epipolar constraints across adjacent frames. We build a dataset from videos collected during a robotic cleaning task to train and evaluate our methods. The experimental results indicate that our segmentation network achieves comparable accuracy to advanced networks, yet with a substantial reduction in computational cost. Meanwhile, the tracking method successfully tracks the majority of intersection points across scenarios where the robot moves in different directions. Full article

Background/Objectives: Accurate detection of thyroid cancer using ultrasound remains a challenge, as malignant nodules can be microscopic and heterogeneous, easily confused with point clusters and borderline-featured tissues. Current studies in deep learning demonstrate good performance with convolutional neural networks (CNNs) and clustering; however, many approaches focus on local tissue and provide limited, non-quantitative interpretation, reducing clinical confidence. This study proposes an integrated framework combining enhanced convolutional feature encoders (DenseNet169 and VGG19) with an enhanced vision transformer (ViT-E) to integrate local feature and global relational context during learning, rather than delayed integration. Methods: The proposed framework integrates enhanced convolutional feature encoders (DenseNet169 and VGG19) with an enhanced vision transformer (ViT-E), enabling simultaneous learning of local feature representations and global relational context. This design allows feature fusion during the learning stage instead of delayed integration, aiming to improve diagnostic performance and interpretability in thyroid ultrasound image analysis. Results: The best-performing model, ViT-E–DenseNet169, achieved 98.5% accuracy, 98.9% sensitivity, 99.15% specificity, and 97.35% AUC, surpassing the robust basic hybrid model (CNN–XGBoost/ANN) and existing systems. A second contribution is improved interpretability, moving from mere illustration to validation. Gradient-weighted class activation mapping (Grad-CAM) maps demonstrated distinct and clinically understandable concentration patterns across various thyroid cancers: precise intralesional concentration for high-confidence malignancies (PTC = 0.968), edge/interface concentration for capsule risk patterns (PTC = 0.957), and broader-field activation consistent with infiltration concerns (PTC = 0.984), while benign scans showed low and diffuse activation (PTC = 0.002). Spatial audits reinforced this behavior (IoU/PAP: 0.72/91%, 0.65/78%, 0.58/62%). Conclusions: The integrated ViT-E–DenseNet169 framework provides highly accurate thyroid cancer detection while offering clinically meaningful interpretability through Grad-CAM-based spatial validation, supporting improved confidence in AI-assisted ultrasound diagnosis. Full article

The growing urgency of resource-efficient construction in water-stressed and rapidly urbanizing regions necessitates integrated decision support frameworks that move beyond isolated sustainability metrics. This study operationalizes the water-energy nexus within building design evaluation by developing a structured hybrid multi-criteria decision-making (MCDM) framework tailored to the Indian construction context. Unlike conventional sustainability assessments that treat water and energy independently, the proposed approach integrates life cycle-based water consumption, operational and embodied energy demand, environmental impacts, economic feasibility, and project constraints within a unified analytical hierarchy. A Delphi-validated criterion structure comprising five main criteria and twenty sub-criteria is weighted using the Analytic Hierarchy Process (AHP), and ranked using the VIKOR compromise solution method. To strengthen methodological robustness, ranking outcomes are validated across three independent MCDM logics including TOPSIS, PROMETHEE, and COPRAS. The framework evaluates four representative building strategies aligned with Indian regulatory and certification systems (NBC, ECBC, IGBC/GRIHA, and net-zero water-energy design). Using expert-informed weights derived from a Delphi–AHP involving a panel of experienced practitioners, the VIKOR compromise ranking consistently identifies the net-zero alternative as the most favorable option within the evaluated framework. The results are therefore interpreted as an expert-informed assessment demonstrating the applicability of the proposed decision support methodology rather than as statistically generalizable priorities for the entire Indian construction sector. The study contributes by (i) embedding nexus-based resource interdependence into building-level MCDM modeling, (ii) enhancing transparency through explicit benefit-cost classification and decision matrix disclosure, and (iii) demonstrating ranking stability across multiple validation techniques. The proposed framework provides a transferable methodological approach that can be adapted to different regional contexts through locally derived expert inputs. Full article

Background: Qualitative motion analysis revealed that the cervical spine moves according to a consistent pattern. Current data analysis methods are limited by the extensive time required to process the retrieved data. A previous study demonstrated the feasibility of using a deep-learning model to automate analysis methods. However, segmentation accuracy needed to be improved. This study aims to improve segmentation model performance to enable reliable motion analysis. Methods: Four nnU-Net configurations were tested: baseline (A), pre-trained (B), with histogram equalization (C), and pre-trained with histogram equalization (D). Segmentation performance was evaluated using Dice Similarity Coefficient (DSC), Intersection over Union (IoU) and 95th percentile Hausdorff Distance (HD95). Vertebral rotation was estimated using mean shapes. Reliability was assessed using the Intraclass Correlation Coefficient (ICC). Sensitivity analyses were conducted. Results: Across all models, mean DSC ranged from 0.67 to 0.92, mean IoU from 0.55 to 0.85, and mean HD95 from 2.35 to 19.67 mm. After sensitivity analysis for low segmental range of motion (sROM) and low-quality recordings, the mean ICC ranged from 0.617 to 0.837 for model A, from 0.609 to 0.780 for model B, from 0.409 to 0.689 for model C, and from 0.480 to 0.835 for model D. Conclusions: This study shows that Models A and B can accurately analyze cervical motion patterns. High image contrast and an adequate sROM are essential for robust model performance. It also marks an important step toward automated qualitative motion analysis, increasing the accessibility of motion pattern evaluation. Full article

Motor imagery (MI) EEG classification is a key component of noninvasive brain–computer interfaces (BCIs) and often must satisfy strict latency constraints in online or edge deployments. Although ensembling can reliably improve MI decoding accuracy, its inference cost grows linearly with the number of ensemble members, making it impractical for low-latency applications. To address these issues, we propose an entropy-based dual-teacher distillation framework that transfers ensemble teacher knowledge to a single deployable backbone. From an information theoretic perspective, two failure modes are common in small and noisy MI datasets: elevated predictive entropy (noisy decisions) and large fluctuation across late training epochs (unstable convergence and unreliable checkpoint selection). Thus, we introduce an exponential moving average (EMA) teacher with entropy-gated activation as a low-pass filter in parameter space to reduce the student’s prediction noise. In addition, a two-stage cosine annealing schedule is employed to suppress late-stage oscillations and improve the robustness of final checkpoint selection. Experiments on two public MI benchmarks (BCI Competition IV-2a and IV-2b) with three representative backbones (EEGNet, ShallowConvNet, and ATCNet) under the subject dependent protocol show consistent accuracy gains over the ensemble teacher and strong distillation baselines. On IV-2a, our method achieves an average accuracy of 0.7713 across the backbones, surpassing both the original models (0.7222) and the corresponding ensembles (0.7482); on IV-2b, it achieves 0.8583 versus 0.8432 (original) and 0.8529 (ensemble). Full article

Real-world traffic is highly dynamic, with pedestrians exhibiting unpredictable movements. Pedestrians’ poses are essential cues for predicting their actions, enabling vehicles to respond proactively and reduce accident risks. In autonomous driving, the distance between vehicles and pedestrians is critical, making 3D human pose estimation crucial. In this context, pedestrian pose estimation has been actively studied, and recently, light detection and ranging (LiDAR) sensors have attracted attention due to their accurate 3D depth information and privacy benefits. However, existing LiDAR-based 3D pose estimation methods mainly process 3D data directly, requiring high computational cost and memory. In this paper, we propose a lightweight LiDAR-based 3D human pose estimation method specifically designed for deployment in autonomous driving systems. Unlike conventional 3D direct processing methods, our approach strategically reduces computational complexity by projecting point clouds into 2D depth images and leveraging a lightweight MoveNet, followed by efficient 3D lifting. Furthermore, we introduce a self-occlusion correction algorithm to improve robustness under side-view and bending poses, where depth-based projections often suffer from distortion. Experimental results on benchmark datasets demonstrate that the proposed method achieves competitive pose estimation accuracy while substantially improving efficiency, highlighting its practicality and scalability for real-time autonomous vehicle applications. Full article

Demand for new solutions to emerging issues faced by the electricity generation, demand and supply industries continues to increase with the introduction of increasing proportions of variable renewable energy and changing system demands. Energy storage systems represent a key part of the solution as stakeholders attempt to move towards a ‘net zero’ system. Within research, studies into the techno-economic optimisation of varied energy storage technologies for different applications continue to play a significant role in this changing landscape. A key aspect of this research is the modelling and simulation of such systems, often with the goal of optimising their parameters for deploying in specific roles and services. This paper presents an extensive analysis of the current economic outlook for five major energy storage technologies, highlighting the significant variation in quoted costs within the literature. It presents a unique and novel perspective by considering economic and optimisation modelling from both a technology and application-centric approach. It explores the different approaches available for performing economic analysis on energy storage systems, providing a novel overview of the advantages of various approaches along with examples from the literature on how these studies are implemented. Finally, the paper explores optimisation studies, giving an in-depth explanation of different approaches used in the optimisation of energy storage systems and reviewing prominent uses within the literature. The paper concludes with a consideration of the main challenges that face the field of techno-economic energy storage studies and provides recommendations on areas that require further research. Full article

One major challenge faced by deep learning-based methods that detect target objects in the form of bounding boxes is object occlusion. High degrees of occlusion significantly diminish the accuracy of instance segmentation. Nonetheless, complex-valued Fourier descriptors can robustly represent object boundaries using minimal information. In this study, the impact of integrating Fourier descriptors—renowned for their strong representational capacity—with deep network models (UNet) that exhibit high generalization performance on instance segmentation accuracy was investigated. Within the scope of the research, nine network models were designed based on different strategies for utilizing frequency components. These variants fall into four strategy families: (i) UNet-style spectrum regression on fixed low-frequency windows (FUNet), (ii) magnitude-guided frequency selection/ROI construction (FUNet–Thr, FUNet–BBox), (iii) sequence models over tokenized FFT coefficients (BiLSTM Patch/Sorted), and (iv) encoder-only spectrum predictors with different depth/capacity (EncoderFFT1/2). To fairly evaluate the models’ performance in segmenting objects subjected to disruptive factors (e.g., occlusion, blurring, noise), a specialized synthetic dataset was prepared. The task is formulated as single-target (single-instance), single-class segmentation. This dataset, automatically generated according to initial parameter values, contains images of objects moving at various speeds within a single frame. Among these models, the one termed FUNet, which relies on partial matching of central frequency components, achieved the highest segmentation accuracy despite the disruptive effects. Under the challenging Dataset 8 setting, the proposed FUNet achieved the highest overlap-based performance (Dice = 0.9329, IoU = 0.8842) among Attention U-Net, U-Net, and FourierNet, with statistically significant gains confirmed by paired per-image tests. Full article

Understanding the net outcomes of ecological interactions by examining the costs and benefits of organism associations is central to ecology. The mutualistic relationship between ants and plants mediated by extrafloral nectaries (EFNs) has long been viewed as protective, with ants defending plants from herbivores in exchange for nectar. However, alternative hypotheses, like the ant-distraction and flower-distraction, highlight the multifunctionality of EFNs. The flower-distraction hypothesis proposes that EFNs evolved to divert ants from flowers, reducing ant impact on pollination. Recent studies reveal that EFN interactions with ants are highly context-dependent, shaped by factors such as EFN location and ant behavior. Although EFNs often occur on vegetative tissues, they are sometimes located near flowers, raising the possibility that they serve both protective and distracting roles. This duality challenges the notion that EFNs can be categorized exclusively by location or function. Instead, their ecological roles likely shift in space and time, depending on plant growth form, pollination system, and interacting species. We propose moving beyond a dichotomous framework toward a nuanced perspective that embraces a potential continuum of functionalities. Considering multiple ecological and evolutionary factors will enhance understanding of EFN evolution, plant–animal interactions, and ecosystem dynamics. Full article

Impaired glucose metabolism, a known precursor to type 2 diabetes, is associated with dysregulation of the autonomic nervous system. To assess such autonomic states, consumer wearable devices provide continuous, non-invasive physiological monitoring and may capture autonomic signatures related to metabolic status. This exploratory study examined whether dynamic features of heart rate (HR) and heart rate variability (HRV) during sleep—derived from a consumer wrist-worn device (Fitbit)—are associated with glucose metabolism status in free-living adults. We analyzed 189 nights from 18 participants (7 participants in the higher-glycemic-risk group, estimated glycated hemoglobin (HbA1c) ≥ 5.5%; 11 participants in the lower-glycemic-risk group, estimated HbA1c < 5.5%). From 28 candidate HR/HRV variables, Elastic Net regression ($\alpha =0.5$) was applied to identify features associated with nocturnal mean glucose. Fourteen features retained non-zero coefficients; notably, dynamic features capturing overnight trends and variability patterns showed stronger associations than conventional static mean values. The nocturnal trends of within-window standard deviation and variance of $ln\left(\mathrm{RMSSD}\right)$ (root mean square of successive differences between consecutive RR intervals, estimated here from PPG-derived inter-beat intervals; RMSSD) emerged as prominent candidates, alongside HR variability indices. Independent between-group comparisons further confirmed that two dynamic HRV features differed significantly between the lower- and higher-glycemic-risk groups (both $\mathit{p}<0.05$; Cohen’s $\left|d\right|>1.1$). Specifically, the lower-glycemic-risk group exhibited decreasing overnight trends in HRV variability, consistent with progressive autonomic stabilization during sleep. In contrast, the higher-glycemic-risk group showed increasing variability trends, suggestive of persistent autonomic instability. These directional patterns are consistent with prior evidence linking autonomic dysfunction to impaired glucose metabolism. We characterize these findings as hypothesis-generating. The identified dynamic HR/HRV features represent physiologically plausible candidate correlates of glycemic status and warrant confirmatory investigation in larger, independent cohorts with laboratory-measured HbA1c. More broadly, this work highlights the potential of widely available, consumer-grade wearable devices to move beyond activity tracking and support continuous, real-world assessment of cardiometabolic health, thereby expanding their utility in everyday health monitoring and preventive medicine. Full article

This paper introduces AdamN, a nested-momentum adaptive optimizer that replaces the single Exponential Moving Average (EMA) numerator in Adam/AdamW with a compounded EMA of gradients plus an EMA of that EMA, paired with an exact double-EMA bias correction. This yields a smoother, curvature-aware search direction at essentially first-order cost, with longer, more faithful gradient-history memory and a stable, warmup-free start. Under comparable wall-clock time per epoch, AdamN matches AdamW’s final accuracy on ResNet-18/CIFAR-100, while reaching 80% and 90% training-accuracy milestones ~127 s and ~165 s earlier, respectively. On pre-benchmarking workloads (toy problems and CIFAR-10), AdamN shows the same pattern: faster early-phase convergence with similar or slightly better final accuracy. On language modeling with token-frequency imbalance—Wikitext-2-style data with training-only token corruption and a 10% low-resource variant—AdamN lowers rare-token perplexity versus AdamW without warmup while matching head and mid-frequency performance. In full fine-tuning of Llama 3.1–8B on a small dataset, AdamN reaches AdamW’s final perplexity in roughly half the steps (≈$2.25\times$ faster time-to-quality). Finally, on a ViT-Base/16 transferred to CIFAR-100 (batch size 256), AdamN achieves 88.8% test accuracy vs. 84.2% for AdamW and reaches 40–80% validation-accuracy milestones in the first epoch (AdamW reaches 80% by epoch 59), reducing epochs, energy use, and cost. Full article

Ultra-low latency communication is fundamentally required to reduce end-to-end (E2E) latency related to the transportation of time-critical or time-sensitive traffic in 5G networks. Time-sensitive networking has significant prospects in factory automation and Industrial Internet of Things (IIoT) as a key technology that can provide low-latency, highly reliable, and deterministic communications over Ethernet, whereas IETF deterministic networking (DetNet) seeks to provide a complementary network layer to support ultra-low latency communications. DetNet, as standardized in the IETF, provides time-sensitive characteristics that assure extremely low packet loss and latency for ultra-reliable low-latency communications. This study develops a novel framework to enable 3GPP support for DetNet functionalities. First, the proposed framework seeks to support IP-based DetNet traffic and urgent data transmission in the network overload conditions of 3GPP 5G systems. Additionally, the proposed design supports DetNet service connectivity between non-DetNet and DetNet service areas. Based on simulation results, the proposed framework can guarantee deterministic latency requirements and critical data transmission for DetNet compared with conventional approaches. The proposed scheme can achieve more effective performance for moving DetNet devices. Full article

The Venice lagoon is the largest in the Mediterranean Sea. The historic city of Venice, located on a cluster of islands in the centre of this lagoon, is an enchanting and iconic destination for national and international tourists. The historical centre of Venice and the other islands of the lagoon, such as Burano, Murano and Torcello, attract crowds of tourists every year. Transportation is provided by boats navigating the lagoon along a network of canals. The lagoon itself attracts visitors who enjoy various outdoor recreational activities in the open air, such as fishing and sunbathing. While statistics are available for the activities targeting the islands, no information is currently available on the spatio-temporal distribution of recreational activities across the lagoon waters. This study explores the feasibility of using Sentinel-2 satellite images to assess and map the spatio-temporal distribution of boats in the Venice Lagoon. Cloud-free Level-2A images have been selected to study seasonal (summer vs. winter) and weekly (weekends vs. weekdays) variabilities in 2023, 2024, and 2025. The RGB threshold filtering and the U-Net Semantic Segmentation were applied to the Sentinel-2 images to ensure reliable results. Two spatial indices were produced: (i) a Water Recreation Index (WRI), identifying standing boats in areas attractive for recreation; and (ii) a Water Transportation Index (WTI), mapping moving boats along the canals. Multi-temporal WRI maps allow areas with recurring recreational activities—that are significantly higher in the summer compared to winter, and on weekends compared to other weekdays—to be identified. The WTI identifies canal paths with higher traffic intensity with seasonal and weekly variations. The latter should be targeted by measures for traffic control to limit wave induced erosion, while the first could be subject to protection or development strategies. Full article