Search Results (1,734)

Reliable ship-to-shore backhaul is essential for maritime Internet of Things (IoT) data delivery, yet cellular and satellite connectivity varies by route, operating phase, and qualification criterion. This study analyses 606,625 georeferenced monitoring records collected during a nine-month, 12-voyage campaign aboard a container ship operating between Korea and Southeast Asia, with the cellular–geostationary Earth orbit (GEO) satellite analysis limited to the period of active very small aperture terminal (VSAT) service. During sailing, cellular attachment was reported for 70.3% of valid cellular state records, but only 28.0% satisfied the adopted technology-specific received power criteria, with leg-level qualified fractions ranging from 77.1% (Incheon–Busan) to 17.3% (Shanghai–Ho Chi Minh). Within the joint-analysis window, either the cellular criterion was satisfied or a valid GEO probe response was observed in 99.4% of records, although the residual gap reached 3.1% on Laem Chabang–Ho Chi Minh. Under retrospective cellular-first allocation, raising the candidate VSAT signal-to-noise ratio (SNR) threshold from 6 to 7 dB increased the store-and-forward share from 6.7% to 25.7% without reducing the median round-trip time (RTT) of the retained GEO records, and the longest buffered interval grew from 2.02 to 9.86 h. These results show that route segment, operating phase, state definition, and threshold selection materially influence link allocation and buffering implications; live traffic steering and application-level availability were not evaluated. Full article

Many open-source 5G standalone testbeds emphasise deployment rather than continuous detection of application-layer abuse. This work presents a reproducible, RF-free, three-node testbed in which SIP signalling traverses a PDU session while a sensor correlates SIP transactions and Asterisk events with Open5GS session records, providing subscriber and data-network attribution. The detector combines a request-rate window with an unanswered-challenge ratio. A separate 5G-dependent rule determines whether SIP traffic attributed to the UE address pool has a corresponding active PDU session. Before execution, the experimental configurations and per-run ground-truth files were hashed; 67 of 70 runs passed the automated validity gates, and every exclusion is reported with its criterion. The detector identified all 60 attack episodes: REGISTER flooding at 2, 5, 10, and 20 requests/s and INVITE flooding at 10 and 20 requests/s. Median first-alert latency for REGISTER decreased from 11.403 s at 2 requests/s to 2.900 s at 20 requests/s; at the two matched rates, mean latencies for the two methods differed by, at most, 28.9 ms. Seven benign runs totalling 3.50 h produced no false alerts and a one-sided 95% Poisson upper bound of 0.86 alerts per hour, and 300 of 300 eligible alerts carried the expected subscriber identity. Full article

Automatic Dependent Surveillance-Broadcast (ADS-B) is one of the most critical technologies utilized in contemporary air traffic control, providing an automated and broadcast means of periodically sending aircraft identification and location, as well as velocity and other state-related information. This paper assesses the receiving performance of ADS-B signals utilizing multiple software-defined radio (SDR) platforms. Four different SDR platforms (DX Patrol MK4, Adalm-Pluto, USRP B200mini and USRP B210) were considered for evaluation, using a single antenna feed distribution via an active RF splitter. Each receiver’s performance was evaluated by measuring the rate at which each platform was able to decode messages from aircraft, the number of aircraft that were detected, the number of valid position reports received from each aircraft, the distance from the receiver to the aircraft at which each platform could receive valid position reports and each platform’s susceptibility to various forms of interference. The results indicate that the best cost-performance in case of interference-free ADS-B reception is obtained for the Adalm-Pluto platform (882 ADS-B messages received in the analyzed period, 2.84 cost/message), whereas the USRP B210 SDR exhibits the best performance in the presence of strong interference (109 ADS-B messages received). These findings provide insight into the relative trade-offs between low-cost SDR platforms and higher-performance SDR platforms, specifically related to analog-to-digital converter (ADC) resolution, RF front-end architecture, host interface, sensitivity and decoding reliability. Full article

Effective visual communication is key to improving road safety whenever vulnerable road users (VRUs), e.g., pedestrians and cyclists, interact in daily traffic. The importance of such communication continues to grow as higher levels of automation are achieved and fully automated vehicles (AVs) become increasingly prevalent. This is especially true for AVs above Level 3, which means that the driver is ‘not driving’ when autonomous driving features are engaged—even if the ‘driver’s’ seat is occupied. Current research shows that external human–machine interfaces (eHMIs) may facilitate explicit communication when AVs and VRUs interact. We used a Virtual Reality approach to examine the efficiency of different formats of eHMIs for signaling that an AV was going to give way and stop to let a pedestrian cross a road. Participants’ decision times and judgements of the clarity of the signals were measured in studies conducted in the UK and in Germany. Overall, the findings showed that eHMIs were effective in signaling AV intention compared to a no-signal baseline; signal interpretation was more difficult at night than in the day. In addition, the format and type of information displayed influenced the ease of recognition and interpretation of such interfaces, with larger light segments aiding visibility and numerical information aiding interpretation. The results are discussed in terms of recommendations for eHMI design and future field testing. Full article

This paper presents a significant evolution of the Identification of Active Anomalies (IAA) system, moving beyond previous descriptive frameworks by integrating an advanced machine learning pipeline for automated, real-time Structural Health Monitoring (SHM). Utilizing acoustic emission (AE), the upgraded IAA framework combines signal clustering, image recognition, and machine learning to monitor the structural condition of a highway overpass located near a major urban agglomeration. The monitoring results provide a reliable foundation for assessing structural health and implementing automated traffic control, which is essential to ensure safe operations. Unlike baseline implementations, this intelligent system extracts multi-parametric features using Principal Component Analysis (PCA) and transforms temporal wave streams into Continuous Wavelet Transform (CWT) scalograms. These visual representations are processed by a custom 14-layer Deep Convolutional Neural Network (CNN) combined with an unsupervised Self-Organizing Map (SOM) to eliminate operational noise and classify internal failures. AE signals recorded under service loads undergo multi-parametric analysis using pattern recognition techniques and are assigned to specific classes corresponding to active anomalies within the material or structure. Each class is linked to a distinct structural hazard level, ranging from safe operation to a critical loss of structural safety. Corresponding traffic control measures, including vehicle speed and weight restrictions, are dynamically introduced to maintain operational safety. To validate the scalability of the framework, this study synthesizes statistical data across a comprehensive fleet of 180 monitored bridge structures, backed by a predictive ARIMA time-series model that forecasts residual service life. The proposed methodology was experimentally validated on an A2 highway overpass, a vital component of the Łódź transport hub that facilitates north–south and east–west transit in Poland. The IAA system functions as a proactive diagnostic tool for infrastructure management agencies, preventing sudden, unforeseen structural failures. Ultimately, it enables the efficient and safe operation of a Smart City while ensuring that maintenance funds are rationally and optimally allocated. Full article

Smart electric vehicle (EV) charging infrastructures are evolving into large-scale cyber-physical Internet of Things (IoT) systems that depend on distributed communication, real-time sensing, and spatially coordinated charging operations. However, their interconnected communication architecture exposes charging stations, EV communication links, and network gateways to coordinated distributed denial-of-service (DDoS) attacks. Existing intrusion detection approaches primarily rely on localized or static traffic analysis and therefore have limited capability to capture spatially distributed and temporally evolving attack behavior. This study proposes the Spatio-Temporal Attack Graph Guard Network (STAG-GuardNet), an unmanned aerial vehicle (UAV)-assisted spatio-temporal attack graph learning framework for DDoS detection and security monitoring in smart EV charging networks. The framework integrates spatiotemporal signal conditioning, telemetry-adaptive graph aggregation, temporal dependency learning, attack-memory encoding, and adaptive risk-aware attention to model coordinated cyber-physical attack behavior. UAV-assisted telemetry provides complementary spatial and wireless information on communication instability, signal variation, neighboring congestion, and distributed attack-related behavior. A Hybrid Hawk–Manta Adaptive Optimizer (HHMAO) is employed to improve hyperparameter selection and convergence stability under imbalanced, heterogeneous, and nonstationary traffic conditions. The framework is evaluated using a smart-city EV charging cybersecurity dataset and three benchmark IoT intrusion detection datasets, namely TON_IoT, Edge-IIoTset, and X-IIoTID. Experimental results show that STAG-GuardNet achieves 97.7% accuracy, a 97.7% weighted F1-score, and a 98.4% area under the receiver operating characteristic curve (AUC) on the primary dataset. The framework also maintains stable performance under noisy telemetry, missing observations, heterogeneous traffic distributions, and charging-node outages. These findings demonstrate the potential of STAG-GuardNet for resilient and spatially informed security monitoring in UAV-assisted IoT-enabled EV charging infrastructures. Full article

Traffic sign recognition (TSR) sits on the critical path of advanced driver assistance and autonomous driving, yet deployed classifiers fail in two qualitatively distinct regimes that prior work has largely defended against in isolation worst case adversarial manipulation from imperceptible digital perturbations to physically realizable stickers, patches, and outline-conforming edge attacks and average case environmental degradation such as fog, glare, motion blur, fading, and occlusion. We observe that, despite their differing origins, both regimes leave the same observable signature on the over specified structure of a sign whose class is redundantly encoded by the silhouette, color scheme, and central pictogram: a spatially localized disagreement among otherwise independent cues, scored against a small, enumerable grammar of physically valid attribute tuples. Recasting robustness as detection of this signature rather than defense against any single threat, we propose SAFER-Sign, which integrates four components that each repair a documented failure mode of prior approaches: (i) class conditionally decorrelated shape, color, and glyph encoders that render over the specification genuine rather than nominal; (ii) evidential per channel uncertainty that lets a degraded cue abstain instead of voting confidently wrong; (iii) a soft, factorized, confidence gated sign grammar prior that rewards jointly consistent tuples without becoming a single attribute attack surface; and (iv) a jointly trained spatial reliability gate anchored to a parameter-free cross-channel disagreement signal, so it cannot be suppressed like a decoupled front end. Taken together, these components mean that a successful adaptive attack in our evaluated settings had to jointly address class evidence, cross channel consistency, grammar compatibility, reliability gating, and abstention. This raises the number of coupled attack objectives, but we emphasize that it does not guarantee that all three channels must be corrupted. Full article

Traffic signal control plays a critical role in mitigating congestion and improving urban mobility, particularly in multi-intersection networks where fixed-time strategies cannot adapt to fluctuating demand. Although reinforcement learning has shown strong potential for adaptive signal optimization, purely learning-based controllers often rely on reward shaping rather than explicit enforcement of traffic engineering constraints, which may lead to unstable phase switching and operational inefficiencies. This study proposes a Hybrid Reinforcement Learning and Rule-based algorithm (Hybrid-RL-RB), a constraint-aware traffic signal control algorithm that combines reinforcement learning with a rule-based supervisory layer for multi-intersection traffic signal control. In the implemented version, the learning component is based on tabular Q-learning with a discretized traffic state representation, while the rule-based layer supervises the final executable signal action. The objective is to improve adaptive signal control while preserving operational feasibility through minimum green time, maximum green time, spillback protection, and phase-safety constraints. The framework was implemented in SUMO through TraCI and evaluated under three scenarios of low, medium, and high traffic demand conditions across multiple network configurations, including a real-network topology (Casablanca-OSM). Experimental results show that Hybrid-RL-RB reduces average queue length by up to 51.47% and waiting time by up to 68.10% compared with Fixed-Time control. Compared with Simple-RL, the proposed method provides modest but consistent queue reductions on the 16 × 16 network, while MaxPressure remains the strongest queue-minimization baseline. In the high-demand Casablanca-OSM scenario, Hybrid-RL-RB reduces queue length by 20.50%, reduces waiting time by 21.41%, and increases throughput by 16.83% compared with Fixed-Time control. These results indicate that explicit rule-based projection can improve the operational feasibility and extensibility of RL-based traffic signal control, although further validation with additional seeds and longer real-network simulations is required. Full article

The efficient use of existing road infrastructure has become increasingly important in densely developed urban areas where large-scale roadway expansion is constrained. Variable directional lanes (VDLs) and traffic signal control can reallocate roadway capacity and improve network performance. However, most existing studies optimize lane configurations and signal timing under a fixed route-flow distribution and therefore do not capture the feedback between control decisions and travelers’ route choices. To address this limitation, this study proposes a bi-level framework for coordinating VDLs and traffic signals at multiple intersections. The upper-level model determines the VDL functions and signal-control parameters to minimize total system travel time, while the lower-level static Logit-based stochastic user equilibrium model endogenously redistributes fixed origin–destination (OD) demand among candidate paths. Thus, OD demand remains fixed within each analysis period, whereas the route-flow distribution responds endogenously to the interaction between traffic control and aggregate route-choice responses. A hybrid solution procedure combining the Non-dominated Sorting Genetic Algorithm II and the Method of Successive Averages is used to solve the coupled control–assignment problem. Numerical experiments on a hypothetical network showed that incorporating route-choice feedback improved coordinated VDL–signal control under the tested conditions. In a supplementary comparison with the pre-optimization BPR-based reference scenario, the average route travel time decreased by 7.67–12.84% across the five representative demand periods, including reductions of 12.52% and 12.84% during the morning and evening peak periods, respectively. Microscopic simulation provided an additional numerical consistency check, with average discrepancies of 4.66% before optimization and 4.38% after optimization between the analytical and simulation results. These findings indicate that incorporating aggregate route-choice feedback can support sustainable urban traffic management by reducing travel time and congestion and improving the utilization of existing transportation infrastructure. However, further validation using real-world data and larger-scale networks is required, and environmental benefits should be evaluated explicitly using energy-consumption and emission indicators. Full article

With the development of artificial intelligence and automated driving technologies, traffic signal control is evolving toward greater flexibility and faster response. From the perspective of the Transportation Cyber-Physical System (T-CPS), this paper focuses on mixed traffic scenarios involving connected and automated vehicles (CAVs) and human-driven vehicles (HVs). It proposes integrating a Large Language Model (LLM) into signal control: roadside devices perceive traffic states, prompt engineering is constructed, and the LLM is driven to reason and generate control signals. On this basis, a CAV speed guidance algorithm is proposed. Controlled SUMO simulations of a single isolated intersection under ideal V2X communication assumptions show that the proposed method improves delay performance under the tested mixed-traffic conditions. As the CAV penetration rate increases, traffic performance is further improved. Additional experiments under emergency-vehicle priority, road-construction constraints, different traffic-demand levels, perception noise, and different decision intervals and guidance ranges provide simulation-based evidence of training-free scenario adaptability and robustness within the examined scope. Although inference latency and remote-API delays constrain the timely availability of fresh LLM actions, the hard-deadline policy and deterministic fallback mechanism maintain continuous signal execution and favorable traffic performance in the controlled SUMO simulations. Full article

Intelligent systems deployed in smart cities, smart grids, environmental monitoring, and other data-driven applications increasingly depend on reliable multivariate time-series forecasting. Recent deep forecasting models have achieved strong performance on various benchmarks, but their final predictions are often generated through a fixed forecast-generation process. This one-size-fits-all approach may be suboptimal because input windows exhibit different values, trends, and periodic patterns. We propose gap-aware residual selection (GARS), a plug-in correction module for time-series forecasting that is attached to a base forecasting model and adjusts its initial forecast rather than replacing the model. From the observed input window and the initial forecast alone, GARS constructs deterministic reference forecasts, uses their differences from the initial forecast as gap-aware residual information, and forms three component forecasts: the initial forecast, a gap-aware residual component, and a direct residual component. GARS combines these components with soft weights over segments of the forecast horizon, and future target values are used only for training and evaluation. Experiments on five multivariate benchmark datasets related to solar energy, weather, electricity consumption, traffic, and exchange rates, using four representative forecasting models trained on the complete chronological training splits, show that GARS reduces the normalized-scale mean squared error by an average of $6.6\%$ across the 80 evaluated settings. This comparison is between GARS trained jointly with each base model and the same base models trained without it. The mean absolute error is not consistently improved, and the difference between the two metrics is associated with a redistribution of error across the test samples. Under the same protocol, a direct conditional mixture without the gap signal performs at least as well as GARS on average and a parameter-matched control also improves on the base models, and thus the gain cannot be attributed to the gap-based construction. On two datasets not used elsewhere in this study, the same configuration increased the mean squared error, and thus the improvements are not established beyond the evaluated benchmarks. Full article

Conventional traffic signal control methodologies are deficient in adapting to rapid traffic flow variations and capturing the complex dynamic interactions between intersections within regional road networks. In order to address this specific issue, the present study proposed the Qatten (Q-value Attention Network)-TSC algorithm. The algorithm was constructed on the basis of the dynamic weighted value decomposition principle and was built upon the multi-agent QMIX (Q-value Mixed Network) framework. The model employed a multi-head attention mechanism to effectively fuse individual agent Q-values with global states and individual features to compute global Q-values. Furthermore, the model incorporated multidimensional state information to comprehensively characterize complex traffic networks. Extensive experiments were conducted on small- and large-scale SUMO simulation platforms based on the real road network of Yangzhou. The experimental results demonstrated that in comparison to VDN and QMIX, Qatten-TSC attained average reward increments of 26.4% and 3.46%, correspondingly, in small-scale road networks, and 34.12% and 12.81%, correspondingly, in large-scale road networks. Furthermore, in large-scale scenarios, the average time loss was reduced by 19.28% and 7.15%, respectively, while the average speed increased by 3.00% and 0.87%, respectively. In addition, the baseline algorithm (Qatten) is unstable and poor-performing. The dynamic weighting mechanism is robust and effective, even as the road network complexity increases. Full article

Driving style, reflected in recurrent patterns of acceleration, braking, speed selection, following distance, gear use, and lane-changing behavior, plays an important role in road safety and is also associated with fuel consumption, emissions, passenger comfort, and vehicle wear. This paper presents a structured review of recent research on driving style analysis, with particular emphasis on its relationship with road-safety outcomes and risk indicators. Following a PRISMA-oriented methodology, studies published between 2015 and 2025 were identified, screened, and synthesized to examine how driving styles are defined, detected, classified, and evaluated. The review shows a clear shift toward data-driven approaches, including feature-based machine learning and representation-learning methods using support vector machines, ensemble models, convolutional neural networks, recurrent neural networks, and hybrid deep learning architectures. Common data sources include smartphone inertial and GNSS signals, CAN/OBD vehicle data, telematics platforms, naturalistic driving datasets, and camera-based perception systems. Safety impact is most often assessed through crashes, near-miss events, traffic conflicts, time-to-collision measures, harsh maneuvers, and composite risk scores. Across the reviewed literature, aggressive and unstable driving patterns are generally associated with reduced safety margins and increased risk, although comparability remains limited by inconsistent label definitions, heterogeneous datasets, indirect safety proxies, and varied validation protocols. The paper also proposes a reproducible database architecture linking drivers, trips, driving events, and safety events to support transparent analysis, benchmark development, and future implementation in fleet monitoring, driver feedback, and connected vehicle applications. Full article

Artificial intelligence (AI) is changing the way we study transport systems, yet its contribution to sustainable transportation planning remains uneven. While AI-based methods have shown strong performance in operational tasks such as traffic prediction and signal control, their integration into strategic planning is still fragmented. This paper provides a narrative review of AI applications in transportation planning and, more specifically, on-demand modeling, arguably the most challenging side of transport planning, and will focus on three arbitrary field macro-aggregations: machine learning (ML), artificial neural networks (ANN), and neurosymbolic AI (NeSy). The findings show that AI methods can improve predictive performance and capture complex nonlinear mobility patterns; however, predictive accuracy alone is insufficient for planning practice. Strategic planning requires models that are interpretable, transparent, and able to accommodate expert-defined constraints. The European Union AI Act further reinforces this requirement by classifying AI systems used in critical infrastructure, including road-traffic management, as high risk; this creates a regulatory need that many current AI applications do not yet satisfy. The paper argues that neurosymbolic AI architectures offer a promising research direction by combining neural learning from heterogeneous mobility data with symbolic representations of behavioral rules, network constraints, as well as accessibility, equity, and environmental objectives. Full article

Air quality monitoring is an essential component of urban environmental management; however, medium-sized cities such as Ibarra often lack updated measurements, limiting evidence-based decision-making. This study presents the design and implementation of an Internet of Things (IoT) system for monitoring nitrogen dioxide (NO₂) and ozone (O₃), pollutants closely associated with vehicular traffic and atmospheric degradation. The system integrates calibrated electrochemical sensors, a data acquisition and wireless transmission module, and a web-based platform for real-time data visualization. To improve signal interpretation, a multilayer artificial neural network was implemented and trained over 71 epochs, achieving a classification accuracy of 97.55% on the independent test dataset for three-class air quality level classification. Field measurements conducted at locations with high vehicular flow reported NO₂ concentrations between 0.00 and 0.03 ppm (approximately 0–57 µg/m³) and O₃ concentrations ranging from 15 to 33 ppb (approximately 30–65 µg/m³), remaining below World Health Organization guideline limits. The results indicate that the proposed solution constitutes a low-cost and scalable tool for preliminary urban air quality assessment and real-time classification, particularly useful for municipal environmental agencies, researchers, urban planners, and public health stakeholders in intermediate cities with limited monitoring infrastructure. Full article