Search Results (3,968)

This study introduces a novel deep learning architecture for vessel trajectory prediction based on Automatic Identification System (AIS) data. The motivation stems from the increasing importance of maritime transport and the need for intelligent solutions to enhance safety and efficiency in congested waterways—particularly with respect to collision avoidance and real-time traffic management. Special emphasis is placed on river navigation scenarios that limit maneuverability with the demand of higher forecasting precision than open-sea navigation. To address these challenges, we propose a Principal Component Analysis (PCA)-driven layered attention mechanism integrated within an encoder–decoder model to reduce redundancy and enhance the representation of spatiotemporal features, allowing the layered attention modules to focus more effectively on salient positional and movement patterns across multiple time steps. This dual-level integration offers a deeper contextual understanding of vessel dynamics. A carefully designed evaluation framework with statistical hypothesis testing demonstrates the superiority of the proposed approach. The model achieved a mean positional error of 0.0171 nautical miles (SD: 0.0035), with a minimum error of 0.0006 nautical miles, outperforming existing benchmarks. These results confirm that our PCA-enhanced attention mechanism significantly reduces prediction errors, offering a promising pathway toward safer and smarter maritime navigation, particularly in traffic-critical riverine systems. While the current evaluation focuses on short-term horizons in a single river section, the methodology can be extended to complex environments such as congested ports or multi-ship interactions and to medium-term or long-term forecasting to further enhance operational applicability and generalizability. Full article

With the rapid development of technologies such as cloud computing, big data, and the Internet of Things (IoT), Software-Defined Networking (SDN) is emerging as a new network architecture for the modern Internet. SDN separates the control plane from the data plane, allowing a central controller, the SDN controller, to quickly direct the routing devices within the topology to forward data packets, thus providing flexible traffic management for communication between information sources. However, traditional Distributed Denial of Service (DDoS) attacks still significantly impact SDN systems. This paper proposes a novel dual-layer strategy capable of detecting and mitigating DDoS attacks in an SDN network environment. The first layer of the strategy enhances security by using blockchain technology to replace the SDN flow table storage container in the northbound interface of the SDN controller. Smart contracts are then used to process the stored flow table information. We employ the time window algorithm and the token bucket algorithm to construct the first layer strategy to defend against obvious DDoS attacks. To detect and mitigate less obvious DDoS attacks, we design a second-layer strategy that uses a composite data feature correlation coefficient calculation method and the Isolation Forest algorithm from unsupervised learning techniques to perform binary classification, thereby identifying abnormal traffic. We conduct experimental validation using the publicly available DDoS dataset CIC-DDoS2019. The results show that using this strategy in the SDN network reduces the average deviation of round-trip time (RTT) by approximately 38.86% compared with the original SDN network without this strategy. Furthermore, the accuracy of DDoS attack detection reaches 97.66% and an F1 score of 92.2%. Compared with other similar methods, under comparable detection accuracy, the deployment of our strategy in small-scale SDN network topologies provides faster detection speeds for DDoS attacks and exhibits less fluctuation in detection time. This indicates that implementing this strategy can effectively identify DDoS attacks without affecting the stability of data transmission in the SDN network environment. Full article

This study investigates global innovation trends in machine learning (ML) and deep learning (DL) technologies within the automotive sector through a patent analysis of 5314 applications filed between 2005 and 2022 across the five major patent offices (IP5). Using Cooperative Patent Classification (CPC) codes and keyword analysis, we identify seven sub-technology domains and examine both geographical and corporate patenting strategies. Our findings show that the United States dominates in overall filings, while Japan demonstrates a notably high share of triadic patents, which reflects a strong global-reach strategy. Patent activity is heavily concentrated in vehicle control and infrastructure traffic control, with emerging growth observed in battery management and occupant analytics. In contrast, security-related technologies remain underrepresented, indicating a potential blind spot in current innovation efforts. Corporate strategies diverge markedly; for example, some firms, such as Toyota and Bosch, pursue balanced tri-regional protection, whereas others, including Ford and GM, focus on dual-market coverage in the United States and China. These patterns illustrate how market priorities, regulatory environments, and technological objectives influence patenting behavior. By mapping the technological and strategic landscape of ML/DL innovation in the automotive industry, this study provides actionable insights for industry practitioners seeking to optimize intellectual property portfolios and for policymakers aiming to address gaps such as automotive cybersecurity in future R&D agendas. Full article

Grading and providing early warning of traffic congestion density is crucial for the timely coordination and optimization of traffic management. However, current traffic density detection methods primarily rely on historical traffic flow data, resulting in ambiguous thresholds for congestion classification. To overcome these challenges, this paper proposes a traffic density grading algorithm for remote sensing images that integrates adaptive clustering and multi-scale fusion. A dynamic neighborhood radius adjustment mechanism guided by spatial distribution characteristics is introduced to ensure consistency between the density clustering parameter space and the decision domain for image cropping, thereby addressing the issues of large errors and low efficiency in existing cropping techniques. Furthermore, a hierarchical detection framework is developed by incorporating a dynamic background suppression strategy to fuse multi-scale spatiotemporal features, thereby enhancing the detection accuracy of small objects in remote sensing imagery. Additionally, we propose a novel method that combines density analysis with pixel-level gradient quantification to construct a traffic state evaluation model featuring a dual optimization strategy. This enables precise detection and grading of traffic congestion areas while maintaining low computational overhead. Experimental results demonstrate that the proposed approach achieves average precision (AP) scores of 32.6% on the VisDrone dataset and 16.2% on the UAVDT dataset. Full article

With the accelerated commercialization of autonomous vehicles, new accident types and complex risk factors have emerged beyond the scope of existing traffic safety management systems. This study aims to contribute to sustainable safety by establishing a quantitative basis for early recognition and response to high-risk situations in urban traffic environments where autonomous and conventional vehicles coexist. To this end, high-risk factors were identified through a combination of literature meta-analysis, accident history and image analysis, autonomous driving video review, and expert seminars. For analytical structuring, the six-layer scenario framework from the PEGASUS project was redefined. Using the analytic hierarchy process (AHP), 28 high-risk factors were identified. A risk prediction model framework was then developed, incorporating observational indicators derived from expert rankings. These indicators were structured as input variables for both road segments and autonomous vehicles, enabling spatial risk assessment through agent-based strategies. This space–object integration-based prediction model supports the early detection of high-risk situations, the designation of high-enforcement zones, and the development of preventive safety systems, infrastructure improvements, and policy measures. Ultimately, the findings offer a pathway toward achieving sustainable safety in mixed traffic environments during the initial deployment phase of autonomous vehicles. Full article

We introduce a novel optimization method, the Bud Lifecycle Algorithm (BLA), and present a mathematical model for optimizing urban transportation systems, demonstrated through a Baltimore case study. Our approach centers on the Proximity Topology Attribute Model, which integrates topological graph properties with K-means clustering to partition city nodes and identify key activity areas via betweenness centrality. A simulated bridge collapse reveals significant impacts on insurance companies and transport users. To balance traffic efficiency with construction costs in public transport projects, we propose a multi-objective optimization model prioritizing transit hubs while minimizing expenses in congested zones. We introduce the Bud Lifecycle Algorithm (BLA) to enhance traditional Genetic Algorithm performance, achieving improvements in system coverage, cost-efficiency, and user satisfaction. Our findings suggest that expanding public transport networks and optimizing rail projects could substantially boost employment and tourism in West Baltimore. We propose the Smart Traffic Management System (STMS) and Community Traffic Safety Program (CTSP) to enhance traffic safety, reduce congestion, and improve residents’ quality of life. Full article

The widespread deployment of electric vehicles (EVs) has introduced substantial challenges to electricity pricing, grid stability, and renewable energy integration. This paper proposes a real-time pricing optimization framework for large-scale EV charging networks incorporating renewable intermittency, demand elasticity, and infrastructure constraints within a high-dimensional optimization model. The core objective is to dynamically determine spatiotemporal electricity prices that simultaneously reduce system peak load, improve renewable energy utilization, and minimize user charging costs. A rigorous mathematical formulation is developed integrating over 40 system-level constraints, including power balance, transmission capacity, renewable curtailment, carbon targets, voltage regulation, demand-side flexibility, social participation, and cyber resilience. Real-time electricity prices are treated as dynamic decision variables influenced by charging station utilization, elasticity response curves, and the marginal cost of renewable and grid-supplied electricity. The problem is solved over 96 time intervals using a hybrid solution approach, with benchmark comparisons against mixed-integer programming (MILP) and deep reinforcement learning (DRL)-based baselines. A comprehensive case study is conducted on a 500-station EV charging network serving 10,000 vehicles integrated with a modified IEEE 118-bus grid model and 800 MW of variable renewable energy. Historical charging data with ±12% stochastic demand variation and real-world solar and wind profiles are used to simulate realistic operational conditions. Results demonstrate that the proposed framework achieves a 23.4% average peak load reduction per station, a 17.9% improvement in renewable energy utilization, and user cost savings of up to 30% compared to baseline flat-rate pricing. Utilization imbalances across the network are reduced, with congestion mitigation observed at over 90% of high-traffic stations. The real-time pricing model successfully aligns low-price windows with high-renewable periods and off-peak hours, achieving time-synchronized load shifting and system-wide flexibility. Visual analytics including high-resolution 3D surface plots and disaggregated bar charts reveal structured patterns in demand–price interactions, confirming the model’s ability to generate smooth, non-disruptive pricing trajectories. The results underscore the viability of advanced optimization-based pricing strategies for scalable, clean, and responsive EV charging infrastructure management in renewable-rich grid environments. Full article

Purpose: To evaluate the prevalence of undiagnosed ligamentous knee injuries in patients surgically treated for high-energy pelvic ring or acetabular fractures and propose a mechanism to diagnose these briefly post-hospital discharge. Methods: A retrospective case series (level of evidence IV) was conducted at Italy’s largest trauma center. Medical records from 2018 to 2023 were reviewed to identify patients who underwent surgical treatment for pelvic or acetabular fractures. Eligible patients were contacted for a structured telephone interview, which included a questionnaire on knee symptoms and the International Knee Documentation Committee (IKDC) score. Associations between demographic factors, trauma mechanism, and knee outcomes were statistically analyzed. Results: Fifty-nine patients (mean age 55 years, 72.9% male) were enrolled. Undiagnosed knee ligament injuries were present in 11.9%, with an additional 8.5% reporting persistent knee symptoms. The average time to diagnosis was 6.4 months post-discharge. Patients involved in road traffic accidents showed a significantly higher incidence of knee injuries (34.8%) compared to those who fell from a height (3.9%) (p = 0.049). Patients who had undergone ligament reconstruction had significantly lower IKDC scores (62.0 ± 8.2) than non-surgical cases (82.4 ± 12.1, p = 0.0002). No association was found with age or sex. Conclusions: Ligamentous knee injuries are frequently overlooked in the acute management of high-energy pelvic fractures, particularly in road traffic accidents. A systematic knee assessment before discharge or early outpatient imaging should be considered to improve detection and outcomes. Full article

Currently, the short-term accurate prediction of multi-region taxi pick-up demand often adopts methods that integrate graph neural networks with temporal modeling. However, most models focus solely on node features during the learning process, neglecting or simplifying edge features. This study adopts a hybrid prediction framework, Edge-GATv2-LSTM, which integrates an edge-aware attention-based graph neural network (Edge-GATv2) with a temporal modeling component (LSTM). The framework not only models spatial interactions among regions via GATv2 and temporal evolution via LSTM but also incorporates edge features into the attention computation structure, jointly representing them with node features. This enables the model to perceive both node attributes and the strength of inter-regional relationships during attention weight calculation. Experiments are conducted based on real-world taxi order data from Ningbo City, and the results demonstrate that the adopted Edge-GATv2-LSTM model exhibits favorable performance in terms of pick-up demand prediction accuracy. Specifically, the model achieves the lowest RMSE and MAE of 3.85 and 2.86, respectively, outperforming all baseline methods and confirming its effectiveness in capturing spatiotemporal demand patterns. This research can provide decision-making support for taxi drivers, platform operators, and traffic management departments—for example, by offering a reference basis for optimizing taxi pick-up route planning when vehicles are unoccupied. Full article

In the V2X environment, intelligent connected vehicles can obtain multi-dimensional traffic flow data in real time through the vehicle–road collaborative cyber–physical fusion system. Based on this, this study proposes a multi-lane traffic flow lattice model integrating optimal traffic flow difference estimation information to effectively suppress traffic congestion. The linear stability criterion of the system is derived through linear stability analysis, proving that the optimal traffic flow difference estimation can significantly expand the stable region and suppress traffic fluctuations caused by small disturbances. Furthermore, the perturbation method is used to derive the mKdV equation near the critical stability point of the system, revealing the nonlinear characteristics of traffic congestion propagating in the form of kink solitary waves, and indicating that the new consideration effect can effectively slow down the congestion propagation speed by adjusting the parameters of solitary waves (such as wave speed and amplitude). The numerical simulation results show that compared to the traditional model, the improved model exhibits enhanced traffic flow stability and robustness. Meanwhile, it reveals the nonlinear relationship between the increase of the number of lanes and the alleviation of congestion, and there is an optimal lane configuration threshold. The research results not only provide theoretical support for the optimization of traffic flow efficiency in intelligent transportation systems, but also provide a decision-making basis for dynamic lane management strategies in the V2X environment. Full article

Background and Objectives: Interpersonal violence (IPV) has overtaken road traffic collisions as a leading cause of facial fractures, yet regional data from Southern Europe are limited. Materials and Methods: We retrospectively reviewed all adults (≥18 y) treated between 1 January 2011 and 31 December 2022 for radiologically confirmed IPV-related facial fractures. Recorded variables were demographics, AO-CMF (Arbeitsgemeinschaft für Osteosynthesefragen—Craniomaxillofacial) fracture site, Facial Injury Severity Score (FISS), presence of facial soft-tissue wounds, treatment modality, and length of stay; associations between variables were explored. Results: A total of 224 victims were identified; 94% were men (median age 26 y, IQR 22–34). The mandible was the most frequently involved bone (42%), followed by the orbit (25%); 14% sustained fractures at multiple sites. Facial soft-tissue wounds occurred in 9% of cases, three-quarters of which were associated with mandibular injury (p = 0.005). The median FISS was 2 and was higher in males, patients > 34 y, those with multiple fractures, and those with wounds (all p < 0.05). FISS showed a weak positive correlation with hospital stay (r = 0.23), which averaged 4.1 ± 1.6 days. Open reduction and internal fixation were required in 78% of patients, most often 24–72 h after admission. Annual IPV-related admissions remained stable throughout the 12-year period. Conclusions: IPV in this region consistently injures young men, with the mandible and orbit most at risk. FISS is a practical bedside indicator of resource use. The unchanging incidence—likely underestimated because isolated nasal fractures and minor injuries are often managed outside maxillofacial services or never reported—highlights the urgency of targeted prevention programs, routine screening, and streamlined multidisciplinary pathways. Full article

Sustainability has an ever-increasing importance in our lives, mainly due to climate changes, finite resources, and a growing population, where each of us is called to make a change. Although climate change is a global phenomenon, our individual choices can make the difference. The transportation sector is one of the largest contributors to global carbon emissions, making the transition toward sustainable mobility a critical priority. The adoption of electric vehicles is widely recognized as a key solution to reduce the environmental impact of transportation. However, their widespread acceptance depends on various technological, behavioral, and economical factors. Within this research we use as an artifact the CO₂ Emission Management Gauge (CEMG) devices to better understand how the manufacturers, with integrated features on vehicles, could significantly enhance sales and drive the movement towards electric vehicle adoption. This study proposes an innovative new theoretical model based on Task-Technology Fit, Technology Acceptance, and the Theory of Planned Behavior to understand the main drivers that may foster electric vehicle adoption, tested in a quantitative study with structural equation modelling (SEM), and conducted in a South European country. Our findings, not without some limitations, reveal that while technological innovations like CEMG provide consumers with valuable transparency regarding emissions, its influence on the intention of adoption is dependent on the attitude towards electric vehicles and subjective norm. Our results also support the influence of task-technology fit on perceived usefulness and perceived ease-of-use, the influence of perceived usefulness on consumer attitude towards electric vehicles, and the influence of perceived ease-of-use on perceived usefulness. A challenge is also presented within our work to expand CEMG usage in the future to more intrinsic urban contexts, combined with smart city algorithms, collecting and proving CO₂ emission information to citizens in locations such as traffic lights, illumination posts, streets, and public areas, allowing the needed information to better manage the city’s quality of air and traffic. Full article

Rolling bearing failures in rotating machinery essential to energy systems (e.g., motors, generators, or turbines) can cause downtime, energy inefficiency, and safety hazards—especially under variable speed conditions common in traction drives. Traditional diagnosis methods struggle with nonstationary signals from speed variations. In response, there is a growing trend toward unsupervised and adaptive signal processing techniques, which offer better generalization in complex operating scenarios. This paper proposes an intelligent fault diagnosis framework combining Adaptive Chirp Mode Decomposition (ACMD)-based order tracking with a novel Shortest Paths Density Peak Search (SP-DPS) clustering algorithm. ACMD is chosen for its proven ability to extract instantaneous speed profiles from nonstationary signals, enabling angular domain resampling and quasi-stationary signal representation. SP-DPS enhances clustering robustness by incorporating global structure awareness into the analysis of statistical features in both the time and frequency domains. The method is validated using both a public bearing dataset and a custom-built metro traction motor test bench, representative of electric traction systems. The results show over 96% diagnostic accuracy under significant speed fluctuations, outperforming several state-of-the-art clustering approaches. This study presents a scalable and accurate unsupervised solution for bearing fault diagnosis, with strong potential to improve reliability, reduce maintenance costs, and prevent energy losses in critical energy conversion machinery. Full article

Vertiports, as dedicated facilities for electric vertical takeoff and landing (eVTOL) aircraft, are essential to ensure the efficiency and sustainability of Urban Air Mobility (UAM). However, UAM infrastructure site selection has become increasingly complex due to limited land availability, complex spatial conditions, and the need to balance multiple objectives. Focusing on passenger-carrying UAM operations, this study proposes a systematic framework for vertiport site selection. First, key factors are classified into high, medium, and low levels across the safety, economic, and social dimensions, forming a modular evaluation system. A GIS-based spatial screening process is developed to identify potential vertiport locations. Subsequently, a variable representing the level of demand satisfaction is incorporated into a progressive coverage model specifically designed for vertiport site optimization. A hybrid algorithm is designed to solve the model. Using Shenzhen as a case study, the proposed approach is validated through real-world data. The results show that vertiport size and spatial requirements significantly influence the selection of suitable land types. High economic constraints may cause facility over-concentration, while setting standards aligned with regional functions better supports equitable access. Locating vertiports in high-demand areas enhances demand satisfaction levels, and both service capacity and range strongly influence overall system performance. These findings provide practical insights for future vertiport planning, promoting the efficient use of urban resources and supporting the successful implementation and sustainability of UAM. Full article

Urban multimodal travel trajectory prediction is a core challenge in Intelligent Transportation Systems (ITSs). It requires modeling both spatiotemporal dependencies and dynamic interactions among different travel modes such as taxi, bike-sharing, and buses. To address the limitations of existing methods in capturing these diverse trajectory characteristics, we propose a spatiotemporal multi-model ensemble framework, which is an ensemble model called GLEN (GCN and LSTM Ensemble Network). Firstly, the trajectory feature adaptive driven model selection mechanism classifies trajectories into dynamic travel and fixed-route scenarios. Secondly, we use a Graph Convolutional Network (GCN) to capture dynamic travel patterns and Long Short-Term Memory (LSTM) network to model fixed-route patterns. Subsequently the outputs of these models are dynamically weighted, integrated, and fused over a spatiotemporal grid to produce accurate forecasts of urban total traffic flow at multiple future time steps. Finally, experimental validation using Beijing’s Chaoyang district datasets demonstrates that our framework effectively captures spatiotemporal and interactive characteristics between multimodal travel trajectories and outperforms mainstream baselines, thereby offering robust support for urban traffic management and planning. Full article