Search Results (2,909)

Urban traffic congestion presents a complex challenge driven by intricate spatial dependencies and non-stationary temporal dynamics. While Multi-Agent Deep Reinforcement Learning has shown promise for Traffic Signal Control, existing approaches often struggle with partial observability and fail to coordinate effectively across large-scale, heterogeneous road networks. In this paper, we propose HydraLight (HYbrid Deep Reinforcement Learning Architecture for Traffic Lights), a novel spatio-temporal framework that integrates Graph Attention Networks and Temporal Transformers. To overcome the localized myopia of standard graph methods, HydraLight introduces a Global Pooling Context module that broadcasts macroscopic, citywide traffic summaries, enabling agents to proactively mitigate systemic gridlock. Furthermore, to facilitate robust multi-scenario training, we introduce a Unified Prioritized Experience Replay (Unified PER) module that normalizes Temporal-Difference errors, preventing task dominance across diverse topologies. Extensive experiments on the RESCO benchmark across five synthetic and real-world networks demonstrate that HydraLight consistently outperforms state-of-the-art baselines (including X-Light and CoSLight).Byreducing traffic congestion, travel delays, and idle waiting times, the proposed framework also contributes to more sustainable urban mobility through improved traffic flow efficiency, lower fuel consumption, and reduced vehicular carbon emissions. Notably, the proposed architecture excels in structurally irregular environments, achieving up to 13.07% reduction in average travel time on complex arterial networks and consistently improving queue stability and waiting-time minimization across both synthetic and real-world RESCO benchmarks compared to state-of-the-art baselines. Full article

Off-grid electric vehicle (EV) charging infrastructure powered by hybrid solar–wind systems address critical adoption barriers in developing countries, where grid unreliability and sparse charging networks constrain transportation electrification. Despite growing research interest, no comprehensive review has systematically synthesized the interplay between hybrid renewable architectures, intelligent energy management strategies, and techno-economic viability specifically for off-grid EV charging in resource-constrained settings. This systematic review applies the PRISMA methodology to analyze 94 peer-reviewed publications (2013–2026), examining system architectures, intelligent control strategies, power electronics, battery storage, and deployment frameworks for standalone hybrid solar–wind EV charging stations. Key findings indicate that hybrid solar–wind configurations achieve 30–50% reductions in battery storage requirements and 15–25% lower levelized cost of energy (LCOE) (USD 0.08–0.15/kWh) compared with single-source systems, driven by diurnal and seasonal resource complementarity. Among intelligent control methods, the two-stage distributionally robust optimization (TSDRO) framework emerges as the most promising for data-scarce environments, outperforming conventional deterministic and stochastic approaches by 10–20% in managing renewable intermittency without requiring precise probability distributions. Wide-bandgap power semiconductors (SiC, GaN) enable 96–98% conversion efficiency, while lithium iron phosphate batteries provide 3000–5000 cycle lifetimes suited to tropical operating conditions. Critical gaps remain with field validation still predominantly simulation based, long-term operational data exceeding 24 months on equipment degradation and climate resilience are scarce, and scalable financing models for developing country contexts require further development. Nigeria is presented as an exemplar deployment context, with transferable insights for sub-Saharan Africa, South Asia, and Southeast Asia. Full article

Accurate traffic flow forecasting is essential for the stable operation and efficient scheduling of intelligent transportation systems. The key lies in identifying the complex spatio-temporal dependencies within the road network structure. In the real world, traffic data are often noisy and incomplete due to sensor failures, communication interruptions, and other unexpected disturbances. To overcome these challenges, this paper proposes an adaptive spatio-temporal self-supervised traffic flow forecasting method based on contrastive learning (ASTSS-CL). At the graph level, structural perturbations are generated by combining node centrality with nonlinear probabilities, while a learnable temporal-periodic parameter matrix and an attention-based fusion mechanism are introduced to adaptively optimize adjacency relationships. At the temporal level, complementary augmentations are designed in both the time and frequency domains. Dynamic interpolation captures continuous traffic variations, while wavelet decomposition and node-adaptive frequency masking balance low-frequency trends and high-frequency details; random masking further improves robustness to missing observations and disturbances. In addition, spatial heterogeneity learning and contrastive consistency learning are jointly employed to enhance representation quality. Experiments on the PeMS04 and PeMS08 datasets show that ASTSS-CL achieves MAE, RMSE, and MAPE values of 17.95, 28.86, and 12.07% on PeMS04, and 13.78, 22.05, and 9.46% on PeMS08, respectively, outperforming the best-performing baseline. These results validate the effectiveness of the proposed method and demonstrate its potential to support traffic management and the operation of intelligent transportation systems. Full article

Conventional truck emission accounting methods based on average activity levels and static emission factors are increasingly inadequate for dynamic regulation and policy comparison at high spatiotemporal resolution. This review synthesizes recent progress in dynamic truck emission estimation from four perspectives: multi-source data support, key feature extraction, physics-constrained emission modeling, and governance-oriented applications. The literature was collected from Web of Science Core Collection and ScienceDirect for the period 2014–2026, supplemented by backward reference checking, and was analyzed through a progressive framework linking data, features, models, and governance tasks. Unlike previous reviews that usually discuss emission inventories, conventional emission models, or data-driven prediction methods separately, this review highlights an integrated governance-oriented chain that connects multi-source data fusion, mechanism-related feature construction, physics-constrained modeling, and environmental management applications. Existing studies suggest that multi-source data, including GPS trajectories, on-board diagnostics (OBDs), on-board monitoring (OBM), portable emissions measurement system (PEMS) measurements, traffic flow monitoring, and road network attributes, provide an important basis for representing real-world operating processes. Meanwhile, key features have expanded from surface-level variables such as vehicle velocity to mechanism-related factors, including payload, road grade, engine operating conditions, vehicle-specific power, and roadway context. Truck emission modeling has also evolved from unconstrained or weakly constrained approaches toward frameworks that place greater emphasis on physical consistency, interpretability, and result credibility. In parallel, application scenarios have extended from emission quantification to high-emission vehicle identification, dynamic inventory development, hotspot detection, policy comparison, and transport optimization. These developments can support policymakers, transportation planners, and environmental agencies in moving from aggregate emission accounting toward targeted and process-based truck emission governance. Current research, however, still faces challenges related to data consistency, model generalizability, uncertainty propagation, and real-time application. Future work should focus on standardized datasets, hybrid AI–physics modeling frameworks, uncertainty-aware validation, real-time deployment in intelligent transportation systems, and improved links between dynamic estimation and practical environmental management. Full article

The Internet of Vehicles (IoV) is rapidly emerging as a core component of intelligent transportation systems, enabling real-time communication among vehicles, infrastructure, and cloud platforms. However, the increasing interconnectivity of vehicular systems and the advancement of quantum computing introduce significant security challenges to existing cryptographic mechanisms. Conventional schemes such as RSA and Elliptic Curve Cryptography (ECC) are vulnerable to quantum attacks and are computationally inefficient for resource-constrained vehicular environments. To address these limitations, this paper proposes a Double-Ring Hybrid Sparse NTRU (DRH-SNTRU) framework, a lightweight and quantum-resistant cryptographic scheme for secure IoV communication. The proposed framework introduces three key enhancements: (i) controlled-support sparse polynomial structures to reduce polynomial multiplication complexity while improving entropy distribution; (ii) a double-ring algebraic architecture that separates key operations from message processing to enhance structural security and minimize coefficient leakage; and (iii) hybrid ephemeral keys derived from contextual entropy to strengthen forward secrecy and adaptive security. An optional ciphertext evaluation mechanism is further incorporated to detect malformed and replayed ciphertexts prior to decryption. Security analysis demonstrates that the proposed framework achieves IND-CPA security under the hardness assumption of the NTRU lattice problem and can be extended to resist chosen-ciphertext attacks through the integrated validation mechanism. Experimental benchmarking across polynomial dimensions N = 512 to 8192 demonstrates that DRH-SNTRU achieves low setup overhead below 3 μs, efficient decryption latency of approximately 305.64 μs at N = 8192, and compact sparse private key representation of only 117 bytes at higher dimensions. Compared with Standard NTRUEncrypt, NTRU-HRSS, and Ring-LWE Encryption, the proposed framework demonstrates improved decryption efficiency, lightweight storage overhead, and enhanced ciphertext integrity protection while maintaining practical scalability for resource-constrained post-quantum IoV environments. Full article

With the rapid electrification of urban transportation and increasing penetration of renewable energy, maintaining frequency stability in smart-city multi-microgrids (MMG) systems increasingly depends on coordinated vehicle-to-grid (V2G) flexibility. However, existing load frequency control strategies typically treat electric vehicles (EVs) as homogeneous resources and overlook the impacts of charging-infrastructure diversity, user mobility constraints, and extreme weather conditions on regulation availability. To address these challenges, this study proposes a weather-adaptive intelligent load frequency control strategy for smart-city MMG considering heterogeneous charging stations and energy requirements of EV users. Fast and slow charging infrastructures are modeled separately to reflect their distinct regulation characteristics, while time-varying charging and discharging margins are derived from travel demand, parking duration, and state-of-charge preferences and further adjusted under extreme weather scenarios. Based on these dynamic constraints, an enhanced multi-agent soft actor–critic (MA-SAC) controller coordinates micro gas turbines and charging stations for distributed frequency regulation. Simulations demonstrate MA-SAC outperforms PID, Fuzzy, and MA-DDPG methods, achieving a 98.51% frequency excellent rate normally and 91.47% during extreme weather. It reduces maximum deviations by up to 80% versus PID, while preserving user travel requirements. The proposed framework provides a practical pathway for integrating electrified mobility into resilient smart-city MMG frequency regulation. Full article

Crowd simulation is essential for applications in evacuation planning, transportation systems, urban analytics, virtual reality, and intelligent mobility. Despite substantial progress, research in this field remains fragmented across diverse modeling paradigms, behavioral abstractions, simulation settings, implementation tools, and evaluation practices. To provide a unified overview, this study conducts a Systematic Mapping Study (SMS) of 54 peer-reviewed primary studies published between 2021 and 2025. Guided by a structured set of 15 research questions, the SMS examines dominant modeling paradigms, associated modeling techniques, spatial representations, behavioral layers, learning methods, and agent capabilities. The study further analyses simulation characteristics—including behavior types, granularity levels, temporal modes, environment types, and application domains—alongside implementation aspects such as programming tools and simulation platforms. Additionally, the mapping covers evaluation practices by identifying reported performance metrics and methodological approaches. Based on the extracted evidence, we propose a comprehensive taxonomy. The results highlight prevailing trends, gaps, and fragmentation in crowd simulation research, including uneven reporting of metrics, limited integration of learning-based methods, and inconsistencies in behavioral modeling. The study also synthesizes key technical challenges and corresponding solutions proposed in recent literature, offering a structured foundation for future research. Full article

Connected and autonomous vehicles (CAVs) increasingly rely on vehicle-to-everything (V2X) communication and distributed sensing infrastructures to support cooperative driving and intelligent transportation services. While these capabilities improve traffic efficiency and safety, they also expand the attack surface of vehicular networks and expose in-vehicle communication systems such as the Controller Area Network (CAN) bus to a wide range of cyber threats. Machine learning-based anomaly detection has emerged as a promising approach for identifying malicious CAN traffic patterns; however, conventional centralized learning requires large-scale data aggregation from vehicles, which raises privacy and scalability concerns. Federated learning (FL) enables collaborative model training across distributed vehicles without requiring the exchange of raw in-vehicle data, making it attractive for privacy-preserving vehicular security applications. Nevertheless, FL systems remain vulnerable to adversarial participants that manipulate local training data or model updates to poison the global model during aggregation. In this work, we present a systematic robustness evaluation of federated anomaly detection in connected vehicular networks under adversarial conditions. The study compares six aggregation strategies, including Federated Averaging (FedAvg), coordinate-wise Median, Trimmed Mean, Krum, Multi-Krum, and Geometric Median (GeoMed), within a non-IID federated CAN bus anomaly detection setting. The evaluation covers label-flipping attacks, gradient-scaling attacks, and a feature-triggered backdoor attack. In addition, the analysis examines malicious client participation, attack-strength variation, learning-rate sensitivity, Trimmed Mean beta sensitivity, multi-seed reliability, and server-side aggregation time. The results show that FedAvg is vulnerable under strong adversarial manipulation, while Trimmed Mean is sensitive to the selected trimming fraction. Median and GeoMed provide strong robustness against gradient-scaling attacks, whereas Multi-Krum achieves the strongest resistance to label-flipping and backdoor attacks. These findings demonstrate that no single aggregation strategy is optimal across all threat models. Instead, robust aggregation for federated CAV anomaly detection should be selected according to the expected attack type, reliability requirement, and computational overhead. Full article

Extensive research has been conducted to develop technologies that enable paratransit systems to operate autonomously, including advanced sensing technologies and associated software. However, there remains a gap in research addressing adaptive operational algorithms for such systems under stochastic and dynamically evolving demand. To address this gap, this study develops an imitation-learning-assisted deep reinforcement learning (DRL) approach for autonomous shuttle routing. The proposed framework integrates generative adversarial imitation learning with proximal policy optimization to enable sequential pickup and drop-off decision-making under stochastic passenger demand without centralized re-optimization. The DRL agent was trained over approximately 1.5 million training steps and evaluated across 1000 episodes with stochastic passenger generation. Its performance was benchmarked against a deterministic dial-a-ride problem (DARP) solver implemented using Google’s OR-Tools, as well as online heuristic baselines. Results indicate that while heuristic methods achieve lower average time-based performance metrics, the proposed approach is capable of learning adaptive routing policies and demonstrates consistent behavior across diverse demand realizations. These findings highlight the feasibility of learning-based routing in controlled environments and provide a foundation for extending such approaches to more complex and realistic autonomous mobility systems. Full article

Ship–bridge collisions in cross-sea bridge waterways are rare but potentially catastrophic events, making conventional accident-based risk assessment difficult to implement effectively. Existing AIS-based indicators capture vessel behaviors but insufficiently quantify bridge-passage safety margins, especially dynamic aspects such as crossing posture and readiness prior to bridge transit. To address this limitation, this study proposes a data-driven framework for detecting unsafe ship–bridge passages using two bridge-passage-oriented surrogate safety measures (SSMs) and extreme value theory (EVT). The Bridge-passage Lateral Clearance Margin (BLCM) quantifies the effective lateral safety margin retained during the realized bridge-crossing stage, while the Bridge-passage Readiness Lead Time (BRLT) measures how early a vessel becomes stably prepared for bridge passage before crossing. The Peaks Over Threshold (POT) model is first used to characterize the marginal extremes of the two indicators, and a bivariate threshold exceedance model (BTE) is then established to examine their joint risk behavior. Case studies of the Jintang Bridge and Zhoudai Bridge waterways demonstrate that the proposed framework can effectively screen and identify trajectories with unsafe or margin-deficient bridge-passage characteristics. The results show that unsafe passages are typically associated with both reduced lateral clearance and insufficient preparation time, and that joint modeling of the two indicators improves risk identification performance. The findings suggest that ship–bridge risk is better interpreted from the perspective of passage quality deficiency rather than simple geometric proximity. The proposed framework provides an interpretable tool for retrospective unsafe passage screening, traffic monitoring support, and post-event safety analysis in complex bridge waterways. Full article

Artificial intelligence is increasingly embedded in cyber–physical systems that coordinate sensing, computation, communication, and control across critical and semi-critical physical environments. Within the European Union, however, its adoption is shaped not only by technological maturity and economic value, but also by an increasingly dense regulatory landscape governing data processing, cybersecurity, product security, accountability, traceability, interoperability, and safety-relevant deployment. A PRISMA ScR-informed scoping review is used to examine how European Union regulation influences artificial intelligence adoption across four representative domains: energy and smart grids, smart buildings, mobility and transport systems, and industrial and manufacturing environments. The analysis draws on primary legal sources, the peer-reviewed literature, and policy and standards-related materials, and is structured around three dimensions: regulatory barriers, technological and architectural challenges, and cross-sector implications for governance, innovation, and competitiveness. The results show that regulation functions simultaneously as a constraint and an enabling condition. It increases compliance burden, raises integration complexity, and slows deployment in higher risk settings, while promoting trustworthy artificial intelligence, stronger cybersecurity, lifecycle governance, clearer accountability, and more interoperable digital infrastructures. The central finding is that regulation is not external to artificial intelligence adoption in cyber–physical systems, but actively shapes the design space within which such systems can be developed, integrated, validated, and scaled. Future progress therefore depends on regulation-aware systems engineering, stronger implementation guidance, and cross-sector reference architectures capable of aligning legal compliance with technical architecture and operational value creation. Full article

Accurately capturing spatiotemporal dependencies and enabling effective decision support are core challenges in Intelligent Transportation Systems (ITS). Existing research often treats traffic prediction and path planning as isolated tasks. Moreover, mainstream prediction models struggle with long-term periodic patterns, while Reinforcement Learning (RL)-based planning often suffers from inefficient exploration in sparse topologies. To address these issues, this paper proposes a unified framework combining a spectral-temporal Graph Neural Network (GNN) and bi-directional decoding RL. Specifically, a time-frequency dual-stream adaptive learning module is introduced for prediction. Fast Fourier Transform (FFT) and Gated Recurrent Unit (GRU) are employed to capture global frequency periodicities and local temporal dynamics, respectively. Their adaptive fusion effectively mitigates the long-sequence information forgetting problem. For path planning, the task is formulated as sequence generation. A graph-aware attention encoder with adjacency masking is designed, and heuristic feature embeddings are incorporated to guide efficient exploration. Furthermore, a bi-directional autoregressive decoding strategy enhances robustness against topological bottlenecks. On PEMSD4 and PEMSD8, the proposed predictor achieves MAE/RMSE/MAPE values of 18.211/30.433/12.006 and 13.587/23.566/8.955, respectively. Path-planning simulations on the PEMSD4-derived sparse topology further demonstrate stable bi-directional RL optimization, faster convergence with heuristic guidance, and a sparsity-aware encoder that reduces redundant attention interactions in sparse road networks. These results validate the effectiveness of the proposed “predict-then-plan” paradigm. Full article

Traffic accidents remain a major challenge for intelligent transportation systems, requiring reliable and real-time detection under complex visual conditions. This study aims to investigate how backbone-level architectural modifications affect traffic accident detection performance in video-based scenarios. A dataset of 250 accident videos was curated from a public traffic surveillance source. This resulted in approximately 3000 manually annotated frames covering diverse accident conditions such as motion blur, occlusion, and illumination variation. To improve detection performance, we introduce Cross Stage Partial (CSP)-based feature partitioning and extend Efficient Layer Aggregation Network (ELAN) structures within the YOLOv9 backbone. Experimental evaluation demonstrates that the CSP-enhanced YOLOv9-t model achieves the best performance among all tested variants, improving mAP50 from 0.35 to 0.50 (approximately 42.8% relative improvement) compared to the baseline YOLOv9-t model, while maintaining real-time inference speed. The results further reveal that CSP improves localization precision, whereas ELAN enhances recall, highlighting complementary behaviors of backbone-level modifications in traffic accident detection tasks. These findings provide insights into how targeted architectural refinements can improve detection robustness in challenging real-world traffic scenarios. Full article

This paper presents a Digital Twin (DT)-based framework for the control, monitoring, and intelligent optimization of an Assembly/Disassembly/Repair Mechatronic Production Line (A/D/R MPL), developed as a laboratory platform aligned with Industry/Education 4.0/5.0 paradigms. The A/D/R MPL is assisted by two complementary cyber–physical robotic systems: an Assembly/Disassembly/Replacement Cyber–Physical Robotic System (A/D/R CPRS), and a Mobile Cyber–Physical Robotic System (MCPRS), enabling both fixed and mobile intelligent operations. The CPRS is equipped with an industrial robotic manipulator (IRM) responsible for A/D/R tasks, while the A/D Mechatronic Line (A/D ML) consists of seven interconnected workstations (WS1–WS7) dedicated to storage, transport, quality control, and final product handling. MCPRS includes a wheeled mobile robot (WMR), carrying a robotic manipulator (RM) and Mobile Visual Servoing System (MVSS). Each workstation is connected to a local slave programmable logic controller (PLC), which communicates via PROFIBUS with a master PLC located at the CPRS level. Additional communication infrastructures include LAN PROFINET and LAN Ethernet for local integration, and WAN Ethernet connectivity enabled through open platform Communication-Unified Architecture (OPC-UA), ensuring interoperability, scalability, and remote accessibility. Also, MODBUS TCP as serial industrial communication is used between the master PLC and the MCPRS. Virtual environment supports task planning through Augmented Reality (AR) and real-time monitoring through Virtual Reality (VR). The system behaviour is modelled with synchronized hybrid Petri Nets (SHPNs) which describe the discrete and hybrid dynamics of A/D/R processes. Artificial intelligence (AI) techniques are integrated into the DT framework for optimal task scheduling and adaptive decision-making. As a laboratory-scale implementation, the proposed system provides a comprehensive platform for experimentation, validation, and education. It supports Education 4.0/5.0 objectives by facilitating hands-on learning, human–machine interaction, and the integration of emerging technologies such as AI, Digital Twins, AR/VR, and cyber–physical systems. At the same time, it embodies Industry 4.0/5.0 principles, including interoperability, decentralization, sustainability, robustness, and human-centric design. Full article

This study proposes a Behavior-Calibrated Endogenous Choice 2SFCA (BCEC-2SFCA) framework for assessing spatial accessibility to tertiary hospitals. Using large-scale taxi trajectory data from Ningbo, China, we empirically calibrate the Huff model parameters ($\alpha =1.1758, \beta =2.9608$) based on observed hospital choices and construct travel time and distance matrices from observed trips. Unlike existing Huff-based FCA approaches that assume parameter values, BCEC-2SFCA jointly estimates the attractiveness elasticity and distance-decay coefficient directly from local healthcare travel behavior and integrates these calibrated probabilities into a 2SFCA structure where hospital catchments are endogenously generated rather than exogenously imposed. Compared with conventional Gaussian 2SFCA, the BCEC-2SFCA model produces a continuously varying and behaviorally plausible accessibility surface and better replicates the relative order of hospital attractiveness ($\rho =0.527, p<0.05$), although its RMSE is slightly higher (0.02700 vs. 0.02211) while MAPE is clearly lower (32.17% vs. 42.12%). Robustness checks using all 22 hospitals confirm stable estimates, and subgroup analyses show consistent advantages across hospital scales. The framework is specifically designed for high-order medical services with strong inter-facility competition—such as tertiary hospitals—and its applicability to proximity-based services is limited. Full article