Search Results (110)

High-precision semantic segmentation of remote sensing imagery is crucial in geospatial analysis. It plays an immeasurable role in fields such as urban governance, environmental monitoring, and natural resource management. However, when confronted with complex objects (such as winding roads and dispersed buildings), existing semantic segmentation methods still suffer from inadequate target recognition capabilities and multi-scale representation issues. This paper proposes a neural network model, LMVMamba (LoRA Multi-scale Vision Mamba), for semantic segmentation of remote sensing images. This model integrates the advantages of convolutional neural networks (CNNs), Transformers, and state-space models (Mamba) with a multi-scale feature fusion strategy. It simultaneously captures global contextual information and fine-grained local features. Specifically, in the encoder stage, the ResT Transformer serves as the backbone network, employing a LoRA fine-tuning strategy to effectively enhance model accuracy by training only the introduced low-rank matrix pairs. The extracted features are then passed to the decoder, where a U-shaped Mamba decoder is designed. In this stage, a Multi-Scale Post-processing Block (MPB) is introduced, consisting of depthwise separable convolutions and residual concatenation. This block effectively extracts multi-scale features and enhances local detail extraction after the VSS block. Additionally, a Local Enhancement and Fusion Attention Module (LAS) is added at the end of each decoder block. LAS integrates the SimAM attention mechanism, further enhancing the model’s multi-scale feature fusion capability and local detail segmentation capability. Through extensive comparative experiments, it was found that LMVMamba achieves superior performance on the OpenEarthMap dataset (mIoU 52.3%, OA 69.8%, mF1: 68.0%) and LoveDA (mIoU 67.9%, OA 80.3%, mF1: 80.5%) datasets. Ablation experiments validated the effectiveness of each module. The final results indicate that this model is highly suitable for high-precision land-cover classification tasks in remote sensing imagery. LMVMamba provides an effective solution for precise semantic segmentation of high-resolution remote sensing imagery. Full article

Road traffic crashes (RTCs) have emerged as a major global cause of fatalities, with the number of accident-related deaths rising rapidly each day. To mitigate this issue, it is essential to develop early prediction methods that help drivers and riders understand accident statistics relevant to their region. These methods should consider key factors such as speed limits, compliance with traffic signs and signals, pedestrian crossings, right-of-way rules, weather conditions, driver negligence, fatigue, and the impact of excessive speed on RTC occurrences. Raising awareness of these factors enables individuals to exercise greater caution, thereby contributing to accident prevention. A promising approach to improving road traffic accident severity classification is the stacking ensemble method, which leverages multiple machine learning models. This technique addresses challenges such as imbalanced datasets and high-dimensional features by combining predictions from various base models into a meta-model, ultimately enhancing classification accuracy. The ensemble approach exploits the diverse strengths of different models, capturing multiple aspects of the data to improve predictive performance. The effectiveness of stacking depends on the careful selection of base models with complementary strengths, ensuring robust and reliable predictions. Additionally, advanced feature engineering and selection techniques can further optimize the model’s performance. Within the field of artificial intelligence, various machine learning (ML) techniques have been explored to support decision making in tackling RTC-related issues. These methods aim to generate precise reports and insights. However, the stacking method has demonstrated significantly superior performance compared to existing approaches, making it a valuable tool for improving road safety. Full article

Fully weathered phyllite is widely encountered along railway corridors in China, yet its suitability as subgrade fill remains insufficiently documented. This study provides an integrated laboratory and field evaluation of both untreated and low-dosage cement-stabilized phyllite for sustainable transport constructions. Laboratory investigations covered mineralogy, classification, compaction, permeability, compressibility, shear strength, and bearing capacity, while large-scale field trials examined the influence of loose lift thickness, moisture content, and compaction sequence on subgrade quality. Performance indicators included the degree of compaction and the subgrade reaction modulus K₃₀, defined as the plate load modulus measured with a 30 cm diameter plate. A recommended cement dosage of 3.5% (by weight of dry soil) was established based on preliminary trials to balance strength development with construction reliability. The results show that untreated phyllite, when compacted under controlled conditions, can be used in lower subgrade layers, whereas cement stabilization significantly improves strength, stiffness, and constructability, enabling reliable application in the main load-bearing subgrade layers. Beyond mechanical performance, the study demonstrates a methodological innovation by linking laboratory mix design directly with field compaction strategies and embedding these within a life-cycle perspective. The sustainability analysis shows that using stabilized in-situ phyllite achieves lower costs and approximately 30% lower CO₂ emissions compared with importing crushed rock from 30 km away, while promoting resource reuse. Overall, the findings support circular economy and carbon-reduction objectives in railway and road earthworks, offering practical guidance for low-carbon, resource-efficient infrastructure. Full article

Effective forest planning in Mediterranean environments requires tools capable of managing ecological complexity, socio-economic pressures, and fragmented governance. This study develops and applies a GIS- and GNSS-based methodological framework for regional forest planning, tested in the “Bosco della Ficuzza, Rocca Busambra, Bosco del Cappelliere, Gorgo del Drago” Regional Nature Reserve (western Sicily, Italy). The main objective is to create a multi-layered Territorial Information System (TIS) that integrates high-resolution cartographic data, a Digital Terrain Model (DTM), and GNSS-based field surveys to support adaptive, participatory, and replicable forest management. The methodology combines the following: (i) DTM generation using Kriging interpolation to model slope and aspect with ±1.2 m accuracy; (ii) road infrastructure mapping and classification, adapted from national and regional forestry survey protocols; (iii) spatial analysis of fire-risk zones and accessibility, based on slope, exposure, and road pavement conditions; (iv) the integration of demographic and land use data to assess human–forest interactions. The resulting TIS enables complex spatial queries, infrastructure prioritization, and dynamic scenario modeling. Results demonstrate that the framework overcomes the limitations of many existing GIS-based systems—fragmentation, static orientation, and limited interoperability—by ensuring continuous data integration and adaptability to evolving ecological and governance conditions. Applied to an 8500 ha Mediterranean biodiversity hotspot, the model enhances road maintenance planning, fire-risk mitigation, and stakeholder engagement, offering a scalable methodology for other protected forest areas. This research contributes an innovative approach to Mediterranean forest governance, bridging ecological monitoring with socio-economic dynamics. The framework aligns with the EU INSPIRE Directive and highlights how low-cost, interoperable geospatial tools can support climate-resilient forest management strategies across fragmented Mediterranean landscapes. Full article

Human perception of urban streetscapes plays a crucial role in shaping human-centered urban planning and policymaking. Traditional studies on safety perception often rely on labor-intensive field surveys with limited spatial coverage, hindering large-scale assessments. To address this gap, this study constructs a street safety perception dataset for Wuhan, classifying street scenes into three perception levels. A convolutional neural network model based on transfer learning is developed, achieving a classification accuracy of 78.3%. By integrating image-based prediction with spatial clustering and correlation analysis, this study demonstrates that safety perception displays a distinctly clustered and uneven spatial distribution, primarily concentrated along major arterial roads and rail transit corridors by high safety levels. Correlation analysis indicates that higher safety perception is moderately associated with greater road grade, increased road width, and lower functional level while showing a weak negative correlation with housing prices. By presenting a framework that integrates transfer learning and geospatial analysis to connect urban street imagery with human perception, this study advances the assessment of spatialized safety perception and offers practical insights for urban planners and policymakers striving to create safer, more inclusive, and sustainable urban environments. Full article

This study presents a smartphone-based dual-index framework for evaluating bicycle pavement conditions, aimed at supporting sustainable urban mobility and cyclist safety. Conventional assessment methods, such as the International Roughness Index (IRI), often overlook short-range discontinuities and are impractical for micromobility-scale infrastructure monitoring. To address these limitations, two perception-aligned indices were developed: the Bicycle Road Roughness Index (BRI), reflecting sustained surface discomfort, and the Faulting Impact Index (FII), quantifying acute vertical shocks. Both indices were calibrated through structured panel surveys involving 40 experienced cyclists and validated using high-frequency tri-axial acceleration data collected in both experimental and field settings. Regression analysis confirmed strong alignment between sensor signals and user perception (R² = 0.74 for BRI; R² = 0.76 for FII). A five-grade classification system was proposed, with critical FII thresholds at 87.3 m/s² for “risky” and 119.4 m/s² for “not rideable” conditions. Field validation across four diverse sites revealed over 380 hazard segments requiring attention, demonstrating the framework’s ability to identify localized risks that may be masked by traditional metrics. By leveraging off-the-shelf smartphones and open-source sensing tools, the proposed approach enables scalable, low-cost, and cyclist-centered diagnostics. The dual-index system not only enhances rideability evaluation but also supports targeted maintenance planning, real-time hazard detection, and broader efforts toward data-driven, sustainable micromobility management. Full article

Accurate accounting of residual film recovery operation areas is essential for supporting targeted implementation of white pollution control policies in cotton fields and serves as a critical foundation for data-driven prevention and control of soil contamination. To address the reliance on manual screening during preprocessing in traditional residual film recovery area calculation methods, this study proposes a DBSCAN-MFI field-road trajectory segmentation method. This approach combines DBSCAN density clustering with multi-feature inference. Building on DBSCAN clustering, the method incorporates a convex hull completion strategy and multi-feature inference rules utilizing speed-direction feature filtering to automatically identify and segment field and road areas, enabling precise operation area calculation. Experimental results demonstrate that compared to DBSCAN, OPTICS, the Grid-Based Method, and the DBSCAN-FR algorithm, the proposed algorithm improves the F1-Score by 7.01%, 7.13%, 7.28%, and 4.27%, respectively. Regarding the impact on operation area calculation, segmentation accuracy increased by 23.61%, 25.14%, 20.71%, and 6.87%, respectively. This study provides an effective solution for accurate field-road segmentation during mechanical residual film recovery operations to facilitate subsequent calculation of the recovered area. Full article

Efficient detection of road surface defects is vital for timely maintenance and traffic safety. This study introduces a novel AI-powered web framework, TriRoad AI, that integrates multiple versions of the You Only Look Once (YOLO) object detection algorithms—specifically YOLOv8 and YOLOv11—for automated detection of potholes and cracks. A user-friendly browser interface was developed to enable real-time image analysis, confidence-based prediction filtering, and severity-based geolocation mapping using OpenStreetMap. Experimental evaluation was conducted using two datasets: one from online sources and another from field-collected images in Ankara, Turkey. YOLOv8 achieved a mean accuracy of 88.43% on internet-sourced images, while YOLOv11-B demonstrated higher robustness in challenging field environments with a detection accuracy of 46.15%, and YOLOv8 followed closely with 44.92% on mixed field images. The Gemini AI model, although highly effective in controlled environments (97.64% detection accuracy), exhibited a significant performance drop of up to 80% in complex field scenarios, with its accuracy falling to 18.50%. The proposed platform’s uniqueness lies in its fully integrated, browser-based design, requiring no device-specific installation, and its incorporation of severity classification with interactive geospatial visualization. These contributions address current gaps in generalization, accessibility, and practical deployment, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments. Full article

Urban ventilation corridors play a critical role in improving wind environments, mitigating the urban heat island (UHI) effect, and enhancing urban climate resilience. Traditional Computational Fluid Dynamics (CFD) methods offer high accuracy in simulating wind fields but are computationally intensive and inefficient for large-scale, multi-scenario urban planning tasks. To address this limitation, this study proposes a morphology-driven, machine learning-based framework for ventilation corridor identification. The method integrates Lattice Boltzmann Method (LBM) simulations, neighborhood-based feature normalization, and a random forest regression model to establish a predictive relationship between morphological indices and wind speed distributions under prevailing wind conditions. Input features include raw and log-transformed LBM values, neighborhood-normalized indicators within multiple radii (100–2000 m), and porosity statistics. The model is trained and validated using CFD-simulated wind speeds, with the dataset randomly divided into training (80%), validation (10%), and testing (10%) subsets. The results show that the proposed method can accurately predict spatial wind speed patterns and identify both primary and secondary ventilation corridors. Primary corridors are closely aligned with large rivers and lakes, while secondary corridors are shaped by arterial roads and localized open spaces. Compared with conventional approaches such as FAI classification, Least Cost Path (LCP), and circuit theory models, the proposed framework offers higher spatial resolution and better alignment with the CFD results while significantly reducing computational cost. This study demonstrates the feasibility of using morphological and data-driven approaches to support efficient and scalable urban ventilation analysis, providing valuable guidance for climate-responsive urban design. Full article

Distributed optical fiber sensing (DOFS) is an advanced tool for structural health monitoring (SHM), offering high precision, wide measurement range, and real-time as well as long-term monitoring capabilities. It enables real-time monitoring of both temperature and strain information along the entire optical fiber line, providing a novel approach for safety monitoring and structural health assessment in transportation engineering. This paper first introduces the fundamental principles and classifications of DOFS technology and then systematically reviews the current research progress on Brillouin scattering-based DOFS. By analyzing the monitoring requirements of various types of transportation infrastructure, this paper discusses the applications and challenges of this technology in SHM and damage detection for roads, bridges, tunnels, and other infrastructure, particularly in identifying and tracking cracks, deformations, and localized damage. This review highlights the significant potential and promising prospects of Brillouin scattering technology in transportation engineering. Nevertheless, further research is needed to optimize sensing system performance and promote its widespread application in this field. These findings provide valuable references for future research and technological development. Full article

Advanced technology systems and neuroelectronics for crash risk assessment and anticipation may be a promising field for advancing responsible automated driving on urban roads. In principle, there are prospects of an artificially intelligent (AI)-powered automated vehicle (AV) system that tracks the degree of perceived crash risk (as either low, mid, or high) and perceived safety. As a result, communicating (verbally or nonverbally) this information to the user based on human factor aspects should be reflected. As humans and vehicle automation systems are prone to error, we need to design advanced information and communication technologies that monitor risks and act as a mediator when necessary. One possible approach is towards designing a crash risk classification and management system. This would be through responsible AI that monitors the user’s mental states associated with risk-taking behaviour and communicates this information to the user, in conjunction with the driving environment and AV states. This concept is based on a literature review and industry experts’ perspectives on designing advanced technology systems that support users in preventing crash risk encounters due to long-term effects. Equally, learning strategies for responsible automated driving on urban roads were designed. In a sense, this paper offers the reader a meticulous discussion on conceptualising a safety-inspired ‘ergonomically responsible AI’ concept in the form of an intelligent risk assessment system (iRisk) and an AI-powered Risk information Human–Machine Interface (AI rHMI) as a useful concept for responsible automated driving and safe human–automation interaction. Full article

Inflammatory bowel diseases (IBDs), comprising Crohn’s disease (CD) and ulcerative colitis (UC), are chronic immune-mediated inflammatory diseases of the gastrointestinal (GI) tract with still-elusive etiopathogeneses and an increasing prevalence worldwide. Despite the growing availability of more advanced therapies in the last two decades, there are still a number of unmet needs. For example, the achievement of mucosal healing has been widely demonstrated as a prognostic marker for better outcomes and a reduced risk of dysplasia and cancer; however, the accuracy of endoscopy is crucial for both this aim and the precise and reproducible evaluation of endoscopic activity and the detection of dysplasia. Artificial intelligence (AI) has drastically altered the field of GI studies and is being extensively applied to medical imaging. The utilization of deep learning and pattern recognition can help the operator optimize image classification and lesion segmentation, detect early mucosal abnormalities, and eventually reveal and uncover novel biomarkers with biologic and prognostic value. The role of AI in endoscopy—and potentially also in histology and imaging in the context of IBD—is still at its initial stages but shows promising characteristics that could lead to a better understanding of the complexity and heterogeneity of IBDs, with potential improvements in patient care and outcomes. The initial experience with AI in IBDs has shown its potential value in the differentiation of UC and CD when there is no ileal involvement, reducing the significant amount of time it takes to review videos of capsule endoscopy and improving the inter- and intra-observer variability in endoscopy reports and scoring. In addition, these initial experiences revealed the ability to predict the histologic score index and the presence of dysplasia. Thus, the purpose of this review was to summarize recent advances regarding the application of AI in IBD endoscopy as there is, indeed, increasing evidence suggesting that the integration of AI-based clinical tools will play a crucial role in paving the road to precision medicine in IBDs. Full article

Riverine environmental information includes important data to collect, and the data collection still requires personnel’s field surveys. These on-site tasks still face significant limitations (i.e., hard or danger to entry). In recent years, as one of the efficient approaches for data collection, air-vehicle-based Light Detection and Ranging technologies have already been applied in global environmental research, i.e., land cover classification (LCC) or environmental monitoring. For this study, the authors specifically focused on seven types of LCC (i.e., bamboo, tree, grass, bare ground, water, road, and clutter) that can be parameterized for flood simulation. A validated airborne LiDAR bathymetry system (ALB) and a UAV-borne green LiDAR System (GLS) were applied in this study for cross-platform analysis of LCC. Furthermore, LiDAR data were visualized using high-contrast color scales to improve the accuracy of land cover classification methods through image fusion techniques. If high-resolution aerial imagery is available, then it must be downscaled to match the resolution of low-resolution point clouds. Cross-platform data interchangeability was assessed by comparing the interchangeability, which measures the absolute difference in overall accuracy (OA) or macro-F1 by comparing the cross-platform interchangeability. It is noteworthy that relying solely on aerial photographs is inadequate for achieving precise labeling, particularly under limited sunlight conditions that can lead to misclassification. In such cases, LiDAR plays a crucial role in facilitating target recognition. All the approaches (i.e., low-resolution digital imagery, LiDAR-derived imagery and image fusion) present results of over 0.65 OA and of around 0.6 macro-F1. The authors found that the vegetation (bamboo, tree, grass) and road species have comparatively better performance compared with clutter and bare ground species. Given the stated conditions, differences in the species derived from different years (ALB from year 2017 and GLS from year 2020) are the main reason. Because the identification of clutter species includes all the items except for the relative species in this research, RGB-based features of the clutter species cannot be substituted easily because of the 3-year gap compared with other species. Derived from on-site reconstruction, the bare ground species also has a further color change between ALB and GLS that leads to decreased interchangeability. In the case of individual species, without considering seasons and platforms, image fusion can classify bamboo and trees with higher F1 scores compared to low-resolution digital imagery and LiDAR-derived imagery, which has especially proved the cross-platform interchangeability in the high vegetation types. In recent years, high-resolution photography (UAV), high-precision LiDAR measurement (ALB, GLS), and satellite imagery have been used. LiDAR measurement equipment is expensive, and measurement opportunities are limited. Based on this, it would be desirable if ALB and GLS could be continuously classified by Artificial Intelligence, and in this study, the authors investigated such data interchangeability. A unique and crucial aspect of this study is exploring the interchangeability of land cover classification models across different LiDAR platforms. Full article

(1) Background: In the context of global population aging, how to enhance the health of older people has become a focus of attention in various fields. Although it is widely recognized that the effects of urban green space built environments on physical activity can substantially improve the health of older people, few studies have been conducted to understand the relationship between green spaces, physical activity, and the health of older people at the community level. This research gap has become a key issue hindering the sustainable development of health among the elderly. (2) Methods: This study used survey data from 1989 elderly individuals in Qingshan District, Wuhan, and applied multiple linear regression models to explore the relationship between community green space built environments and the overall intensity of physical activity, as well as the relationship with low, moderate, and high-intensity physical activity levels. (3) Results: The results show that education level, income level, health status, companionship, green view index, road cleanliness, and fitness facilities are positively correlated with the overall intensity of physical activity, while gender, age, self-assessed psychological stress, and road intersection density are negatively correlated with it. Companionship, green view index, road cleanliness, and recreational facilities are positively correlated with low-intensity physical activity levels among the elderly, while gender, income level, and fitness facilities are negatively correlated with them. Companionship, green view index, and road cleanliness are positively correlated with moderate-intensity physical activity among the elderly, while gender is negatively correlated with it. For high-intensity activities, education level and fitness facilities are positively correlated, while gender, self-assessed psychological stress, and road intersection density are negatively correlated. (4) Conclusions: Future research could expand the sample size while incorporating more longitudinal designs, expand the types of influencing factors, conduct more detailed classifications, and carry out broader data collection procedures to comprehensively analyze the effects of the community green space built environment on physical activity among older people, providing a stronger scientific basis for the formulation of healthy city policies. Full article

In the field of autonomous driving, it is important to protect vulnerable road users (VRUs) and ensure the safety of autonomous driving effectively by improving the detection accuracy of VRUs in the driver’s field of vision. However, due to the strong temporal similarity between pedestrians and cyclists, the insensitivity of the traditional least squares method to their differences results in its suboptimal classification performance. In response to this issue, this paper proposes an algorithm for classifying pedestrian and cyclist targets based on the micro-Doppler effect. Firstly, distinct from conventional time-frequency fusion methods, a preprocessing module was developed to solely perform frequency-domain fitting on radar echo data of pedestrians and cyclists in forward motion, with the purpose of generating fitting coefficients for the classification task. Herein, wavelet threshold processing, short-time Fourier transform, and periodogram methods are employed to process radar echo data. Then, for the heightened sensitivity to inter-class differences, a fractional polynomial is introduced into the extraction of micro-Doppler characteristics of VRU targets to enhance extraction precision. Subsequently, the support vector machine technique is embedded for precise feature classification. Finally, subjective comparisons, objective explanations, and ablation experiments demonstrate the superior performance of our algorithm in the field of VRU target classification. Full article