Search Results (239)

With the continuous evolution of network attack techniques, efficiently selecting the most discriminative feature subset from massive network traffic data has become a key issue for improving the performance of intrusion detection systems. Metaheuristic algorithms, as a core approach for wrapper-based feature selection, directly determine the quality of the selected feature subset through their optimization capability. The Grey Wolf Optimizer (GWO) is popular due to its simple structure and few parameters, where three leader wolves guide the search through weighted cooperation. However, its static weight mechanism cannot adapt to dynamic changes in individual search states and population evolution stages, limiting optimization capability and convergence performance. To address this issue, this study proposes a Deep Reinforcement Learning-based Grey Wolf Optimizer (DGWO), which pre-trains a weight adjustment decision model offline and dynamically adjusts the guiding weights of leader wolves during the online search process, thereby improving the optimization ability of the algorithm. Experimental results on NSL-KDD, UNSW-NB15, and CIC-IDS-2017 datasets show that DGWO outperforms seven comparative feature selection methods. It achieves classification accuracies of 93.59%, 93.40%, and 94.84%, respectively, demonstrating superior performance in accuracy, precision, recall, and F1-score. DGWO promotes symmetry between cybersecurity requirements and reliable intrusion detection. Full article

Urban traffic anomaly detection is essential for intelligent transportation systems, particularly in smart city environments where fast identification of abnormal events can improve road safety and traffic management. This work proposes a novel ULSTM-driven architecture that explicitly models temporal dependencies across consecutive traffic frames to achieve more stable and temporally coherent reconstructions. The proposed framework leverages sequential spatio-temporal representations to improve the distinction between normal traffic patterns and anomalous events. To further enhance reliability, we introduce a Hybrid Weighted Fusion strategy that synergistically combines structural, perceptual and pixel-wise metrics. The framework’s parameters are optimized using a Discrete Dirichlet Sampling approach, achieving a peak F1 Score of 70.28%. Evaluations were conducted on a manually curated traffic anomaly dataset with frame-level annotations. Experimental results demonstrate that the ULSTM framework significantly outperforms frame-independent generative models by suppressing high-frequency reconstruction noise, providing a robust solution for real-world smart city deployments. While highly effective in complex scenarios, the proposed framework is strictly applicable to highly dynamic traffic environments with active motion, as static background ensembles can degrade performance. Full article

Urban traffic congestion prediction is an important problem in smart city sensing and intelligent traffic governance. Existing methods mostly rely on single-source traffic flow sensing data or static road topology, making it difficult to sufficiently characterize the dynamic congestion propagation process driven by multisource sensing information, such as traffic flow, vehicle trajectories, road images, public transportation, meteorological conditions, and sudden events. To address this issue, a spatiotemporal causal graph learning framework based on multisource urban sensing data is proposed for urban traffic state prediction, congestion identification, and explainable early warning. In this framework, traffic flow detector data, GPS trajectories, roadside camera data, public transportation data, weather data, and event records are first fused through a multisource urban sensing data collaborative encoding module, and the influence of low-quality or missing sensing modalities is suppressed using a reliability-aware attention mechanism. Subsequently, time-varying causal propagation relationships among road segments are adaptively learned from historical traffic states, road topology, and external disturbances through a dynamic spatiotemporal causal graph learning module. Finally, spatial diffusion and temporal evolution are jointly modeled by a causality-explanation-driven congestion prediction module, and key congestion sources, propagation paths, and inducing factors are outputs. Experimental results based on multisource traffic sensing data from the main urban area of Hangzhou show that the proposed method achieves MAE values of $3.21$, $3.79$, and $4.48$ in 15-min, 30-min, and 60-min traffic state prediction tasks, respectively, outperforming ARIMA, XGBoost, LSTM, Transformer, STGCN, Graph WaveNet, GMAN, Multimodal Transformer, and the Causal Temporal Graph Network. In the ablation study, the complete model achieves an Accuracy of $0.914$, a Precision of $0.902$, a Recall of $0.889$, an F1 of $0.895$, and an AUC of $0.956$. For congestion identification and early warning under complex scenarios, F1 values of $0.927$, $0.904$, and $0.893$ are achieved under peak-hour, rainy-weather, and traffic-event scenarios, respectively; the corresponding AUC values reach $0.966$, $0.957$, and $0.948$; and the false alarm rate (FAR) values are reduced to $0.061$, $0.072$, and $0.081$. The results indicate that the proposed method can effectively improve traffic state prediction accuracy, congestion early warning reliability, and model interpretability under multisource urban sensing conditions, thereby providing an effective technical pathway for AI-driven intelligent traffic sensing. Full article

This article discusses the relevant problem of ensuring transport connectivity under the conditions of temporal restrictions of the road network, which arise during repair, communal and emergency operations. It is established that the existing organizational and intellectual methods of traffic management do not eliminate physical decrease in road capacity, while construction of stationary structures with different levels is limited by high costs and long terms of implementation. The above substantiates the need for the development of mobile overpasses as adaptive engineering solutions ensuring continuity of the traffic flows. The purpose of the research is to develop a scientifically substantiated theoretical and experimental methodology for designing a mobile overpass as an integrated system “structure-moving load”, taking into account its dynamic behavior. The paper proposes an integrated approach based on the use of physical similarity theory and dimensionless analysis. A differential equation of dynamic bending of a beam on an elastic foundation is formulated taking into account inertia, damping, base reaction and the effect of a moving mass, and then its nondimensionalization is performed to obtain a similarity criteria system. The scientific novelty of the research consists in developing a system of dimensionless criteria to describe the relationship between the structural, dynamic and operational parameters of a mobile overpass, as well as in the formation of a criterion base for large-scale modeling and transfer of the results to full-scale structures. The proposed methodology describes the mobile overpass as an integrated transport-engineering system accounting for the coupled interaction between the deformable structure, moving traffic load, elastic foundation, and damping effects. Experimental verification was performed on a specially designed stand in the scale 1:4. The results obtained showed the quasi-static nature of the structure performance with moderate damping and rigid base. It is established that the distribution of engineering stresses along the span length has a regular character and retains its shape when the load level changes, which confirms fulfillment of similarity conditions. Regression analysis revealed a close to linear dependence of stresses on the load mass with a high degree of confidence $(R^2\approx 0.995)$. The practical significance of the research consists in creating an engineering method for express design of mobile overpasses, which allows for assessing their stress–strain state, stability and serviceability without expensive full-scale tests. The proposed approach can be used in designing temporary transportation structures under the conditions of urban area, and in operation in areas of road operations and emergency situations. Full article

Conventional static indicators such as passenger car equivalent (PCE) factors cannot adequately capture the dynamic bottleneck effects caused by truck speed degradation on long steep freeway upgrades. To address this issue, this study proposes an operational efficiency analysis framework integrating truck crest-speed reliability and microscopic simulation. Vehicle trajectory data were collected using unmanned aerial vehicles, and truck power-to-mass ratio data were obtained from the Chinese truck market to establish a representative truck model. Monte Carlo simulation was employed to quantify crest-speed reliability, whose complement (failure probability) characterizes the likelihood of truck bottlenecks arising. A calibrated VISSIM simulation model was then developed to reproduce truck climbing speed degradation and microscopic driving behavior on long upgrades. Finally, a response surface model was constructed using average delay as the operational efficiency indicator. The results indicate the following: (1) As grade length increases, the probability of truck bottleneck occurrence gradually rises, and the marginal effect of this increase becomes more pronounced with steeper grades. Specifically, truck crest-speed reliability exhibits a nonlinear decreasing trend with increasing grade length. For example, under a design speed of 120 km/h and a 95% reliability threshold, the corresponding grade length for a 2.5% grade is 1367 m, whereas for a 4% grade it drops to 232 m, representing a reduction of 83%. (2) Under high traffic volume conditions, an increase in truck proportion leads to a significant rise in average delay (up to 17.54 s). Although improving crest-speed reliability reduces the probability of truck bottleneck occurrence and partially mitigates delay, it cannot fully offset the traffic pressure induced by high traffic demand. Grade and grade length remain the most critical factors driving operational efficiency deterioration, with a maximum impact on average delay of 38.72 s. (3) The response surface model reveals significant interaction effects between traffic volume and truck proportion, as well as between traffic volume and crest-speed reliability, indicating that traffic demand plays a dominant role in amplifying the impact of truck bottlenecks. The framework proposed in this paper provides probabilistic quantitative decision support for sustainable longitudinal grade design and freight traffic management on mountainous freeways. Full article

6G promises ultra-low latency, high data throughput, and seamless global connectivity. However, providing uninterrupted connectivity in remote and underserved regions remains a critical challenge for Terrestrial Networks (TNs), where the cost of deploying infrastructure is difficult to justify against sparse user density. Standardized under 3GPP Release 17, Non-Terrestrial Networks (NTNs) have emerged as a viable solution to close this digital divide. Among NTN platforms, High-Altitude Platform Stations (HAPS) occupy a strategic middle ground, as they deliver lower propagation delays than Low-Earth Orbit (LEO) satellites while achieving far broader coverage than TN-based Base Stations (BS). Despite these advantages, battery-powered Internet of Things (IoT) devices communicating via HAPS face a fundamental energy efficiency (EE) challenge: transmit power must be carefully managed to maximize data throughput while preserving battery life and minimizing packet queuing delays. To address this, we propose a Q-learning-based Reinforcement Learning (RL) framework. The RL agent observes the instantaneous battery level and queue state of the IoT device, and dynamically selects optimal power levels from a discrete action space across successive time slots. Unlike traditional heuristic algorithms, such as Round Robin (RR), Max Single-to-Noise Ratio (Max-SNR), and fixed-power allocation, which rely on static rules or greedy channel-based decisions, the proposed Q-learning agent learns adaptive, long-term optimal policies through direct interaction with the environment, without requiring explicit mathematical modeling of the channel or traffic dynamics. Extensive simulations demonstrate that the proposed framework achieves up to 40% higher average EE compared to all benchmark schemes, maintains consistently lower power consumption, and exhibits superior statistical reliability as evidenced by a right-shifted Cumulative Distribution Function (CDF) of EE. These results demonstrate Q-learning as a promising candidate for scalable, energy-aware power control of next-generation HAPS-assisted IoT deployments in 6G NTN ecosystems. Full article

Precast multi-girder bridges are widely utilized in highway infrastructure but are susceptible to transverse connection deterioration, which can lead to single-girder load-bearing failures. Existing structural health monitoring methods based on the correlation of total dynamic strain responses often fail to identify early-stage damage due to the static masking effect, where dominant, in-phase quasi-static components overshadow subtle, damage-sensitive dynamic features. To overcome this limitation, this paper proposes a novel condition indicator based on the correlation of high-frequency dynamic strain increments. An online streaming processing pipeline is developed, incorporating automated single-vehicle crossing event extraction, frequency-targeted signal decoupling, and indicator smoothing. Theoretical derivations on a dual-beam model demonstrate that the proposed indicator is a structural-intrinsic metric, exhibiting high sensitivity to joint stiffness while remaining robust against variations in vehicle weight and speed. Numerical simulations on an 8-slab finite element bridge model under stochastic traffic flow further verify the effectiveness of the framework. Results indicate that the proposed indicator can localize both progressive degradation and sudden brittle failures. Additionally, the method maintains reliability down to a signal-to-noise ratio of 30dB and robustness to hyper-parameter selection. While the current framework is established based purely on numerical validation and has not yet been tested using real bridge strain data, it shows numerical feasibility and provides a solid theoretical and algorithmic foundation for the automated condition evaluation of precast multi-girder bridges, supporting future field validation for both long-term maintenance and emergency response. Full article

Control subarea division is essential for coordinated signal control, but methods based mainly on local correlation or static topology may not adequately capture traffic-state propagation under dynamic traffic loading. This study proposes a control subarea division method that explicitly models traffic-state propagation by integrating state-guided colored random walk and path entropy analysis. Intersection correlation degree and traffic state are used to construct a state-guided colored random walk process, in which transition probabilities are updated according to network connectivity and traffic-state consistency. Path entropy characterizes propagation uncertainty, and control subareas are identified by minimizing the distribution discrepancy between node-level and subarea-level path responses. To compare partitioning schemes, five complementary metrics were adopted: variance reduction rate of spatial delay, delay reduction rate, congestion mitigation index, stop reduction rate, and queue reduction rate. A VISSIM microsimulation model with dynamic traffic loading was developed to compare the proposed method with the Whitson and Fast Newman methods. The proposed method achieved the best performance across all five metrics, with values of 41.47%, 23.77%, 25.96%, 23.59%, and 15.08%, respectively. These results indicate that the proposed method improves spatial balance and network efficiency while mitigating bottlenecks, reducing stops, and suppressing queue accumulation. Full article

Urban Unmanned Aerial Vehicle (UAV) logistics operations are frequently constrained by the intersection of limited battery endurance and dynamic ground traffic. When mobile depots are delayed by congestion, onboard drone fleets experience extended idling periods, leading to constrained sortie generation and reduced asset utilization. To address this bottleneck, this paper introduces a traffic-predictive multi-UAV dispatch framework for deterministic day-ahead planning under modeled urban operating conditions. By coupling a count-derived macroscopic speed surrogate learned using XGBoost with a Particle Swarm Optimization (PSO)–Mixed-Integer Linear Programming (MILP) optimization architecture, the framework synchronizes mobile depot trajectories with forecasted low-congestion windows and pre-allocates endurance-feasible parallel aerial sorties. Controlled computational experiments across 30 synthetic routing instances demonstrate the potential value of this approach within the stated modeling assumptions. Compared to baseline clustered deployments, the traffic-aware framework raises mean fleet utilization from 0.43 to 0.63—a 46.2% relative improvement driven by temporal compression of the mission window rather than an absolute increase in flight hours. Furthermore, the proposed framework reduces total mission completion time by 69.87% relative to the conventional truck-only baseline, while achieving a 29.58% incremental gain over static speed drone deployments. These findings suggest that incorporating predictive ground traffic information into day-ahead UAV scheduling can improve modeled fleet efficiency; however, field validation with measured route-level speeds, real delivery demand, and operational constraints remains necessary before deployment-level claims can be made. Full article

In this study, the transition of intersection coordination models was explored using a Dynamic Game framework. The performance limitations of traditional static models, which define payoffs based on fixed geometric conflicts, were also investigated to propose a novel dynamic utility function and evaluate it at each simulation step. Its important function is a continuous dynamic risk penalty derived from the immediate traffic state, allowing adaptive, risk-aware decisions to be made by vehicles. Based on the assumption of complete information, all vehicles have full knowledge of the characteristics of their rival vehicles, such as driving styles, as well as emergency vehicles like fire trucks and ambulances. Emergency vehicle priority is ensured through a high-cost penalty structure. The Pure Strategy Nash Equilibrium is solved for using the Iterated Best Response (IBR) algorithm. Through the MATLAB simulation of urban mobility, the dynamic, risk-aware framework was found to significantly improve safety metrics (e.g., near-collision events) compared to its static counterpart. Finally, the stability of the decision is analyzed by evaluating the IBR convergence rates across various driver-type compositions. Full article

Adverse weather conditions, particularly thunderstorms, are the primary cause of flight delays and safety threats, accounting for approximately 58.7% of irregular flights in 2025. Traditional static rerouting methods often fail to adapt to the non-linear evolution of convective weather. This paper proposes a high-fidelity dynamic rerouting framework to enhance flight safety and efficiency. In the perception layer, a RainNet deep learning model is employed for short-term recursive nowcasting of radar reflectivity, which is subsequently transformed into Dynamic Avoidance Zones (DAZ) via clustering and convex hull algorithms. In the decision layer, a two-stage improved Genetic Algorithm (GA) is developed to solve the rerouting path. The first stage generates initial collaborative solutions under a receding-horizon framework, while the second stage applies a “path-straightening” module to reduce cumulative turning angles and curvature fluctuations. The comparative results in actual scenarios demonstrate a distinct dual-advantage over baseline methodologies. Compared to sampling-based strategies, the proposed model reduces the path length by 14.79%. Furthermore, when compared to heuristic algorithms, it actively trades a negligible 1% distance margin to achieve a massive 92.7% reduction in the cumulative turning angle. With a maximum single turn of only 32.51°, the trajectory completely eliminates sawtooth jitter and redundant detours. Ultimately, this research provides essential technical support for improving air traffic management efficiency and reducing controller workload during severe weather events. Full article

The foot structure plays a decisive role in the trafficability of legged robots on granular media. Traditional foot-ends (spherical, cylindrical, flat-bottomed) are prone to sinkage and slippage, resulting in unstable locomotion. To solve this problem, a novel bionic-inspired reconfigurable foot with active opening and closing adjustment capability is designed based on bionics, combining the stable phalangeal contour of goat hoof capsules and the high-adhesion feature of beetle foot-end spines. A coupled EDEM–Adams simulation model is established, and physical experiments combined with simulation inversion are used to calibrate contact parameters between particles and between particles and the foot, including the coefficient of restitution, static friction and rolling friction. A high-fidelity numerical platform for foot–ground dynamic interaction is thus constructed. By comparing and analyzing the differences in anti-sinkage and traction performance between the bionic-inspired foot and traditional foot-ends, this study systematically revealed the influence law of bionic morphology on the mechanical behavior of the foot, and clarified the intrinsic mechanism through which bionic design improves foot–ground interaction. The results demonstrate that the spine structures of the bionic-inspired foot reshape the mechanical constitutive relationship of granular media. By expanding the ground contact area and optimizing contact pressure distribution, the maximum reduction in foot sinkage depth reaches 70.11%, and the traction coefficient is increased by up to 37.13%. Full article

The growing sophistication of the internet and web space has spawned highly dynamic, multi-vector cyber threats that cannot be handled by automated detectives and hence the necessity to introduce analyst-oriented, cognitively powerful security analysis apparatus. The character of current visualization-based security frameworks is that they are inclined to deliver data unproactively, fail to engage the dynamic setting, and fail to comprehend the evolving motive of assailants, resulting in subsequent identification and a fractured understanding of coordinated web attacks. The paper introduces a new model of interactive security visualization known as Context-Oriented Visual Exploration of Resilient Threats (COVERT), a hybrid of behavioral context modeling, adaptive visual storytelling, and intent-sensitive interaction. COVERT is dynamically rearranged to the development of threats, patterns of interaction between analysts, and objectives of the possible attacks, which helps in releasing relevant security capabilities gradually. The framework integrates graphical threat flows, attention-directed visual cues, and real-time feedback loops to align system responses to the thinking processes of the analysts. The evaluation of high-scale web traffic and attack simulation dataset indicates that COVERT is much more effective in the multi-stage detection of attacks, false-positive interpretation is minimized, and the investigation period is reduced compared to the visualization infrastructure of the static and semi-interactive infrastructure. According to user studies, there is higher situation awareness, enhanced correlation of distributed events, and enhanced decision-making in complex web intrusion situations, such as advanced persistent threats and web exploitation coordination. Combining contextual intelligence with adaptive interaction and visualization of security, COVERT reveals that intent-based visual analytics may greatly improve internet and web threat detection and analysis systems to support more agile and resilient cyber defense procedures. The proposed COVERT strategy achieved 93% threat-detection rate, the false positives were reduced to 6%, the response time of the analysts was reduced to 140 s, and the situational awareness was increased to 88%. Full article

Traffic prediction is a fundamental task in intelligent transportation systems, yet developing accurate prediction models remains challenging because of the complex spatial and temporal dependencies in real road networks. Existing methods commonly rely on discrete modeling paradigms to characterize spatiotemporal features. However, these approaches often fail to adequately capture the intrinsic spatiotemporal coupling among nodes and mainly depend on static adjacency matrices constructed from prior knowledge, which limits their ability to represent dynamic spatiotemporal correlations in real traffic scenarios. To address these limitations, this paper proposes a dynamic prediction model using continuous ordinary differential equations termed DPMCODE. The proposed method enables collaborative aggregation of global and local information through continuous neural ordinary differential equations and dynamically learns spatiotemporal dependencies via graph ODE networks for traffic prediction. Specifically, a continuous ordinary differential equation modeling strategy is introduced to alleviate the over-smoothing problem in discrete networks. Meanwhile, an adaptive dynamic graph structure is designed to reduce the reliance on prior knowledge graphs and capture richer latent spatiotemporal correlations. In addition, a local correlation-aware ODE module is developed to model potential dependencies between non-adjacent nodes, while a spatiotemporal fusion prediction module is further designed to promote effective collaboration between global and local information. Compared with conventional discrete network models, the proposed model generates more realistic and accurate predictions. Extensive experiments and theoretical analysis on five benchmark traffic prediction datasets demonstrate the superiority and state-of-the-art performance of DPMCODE. Full article

Traditional traffic flow forecasting methods still face challenges in capturing complex spatiotemporal correlations. Static graph convolutional networks are unable to capture spatiotemporal dynamics, while dynamic graphs can adaptively adjust spatial dependencies but often ignore the inherent static connectivity of traffic networks. To address these limitations, this paper proposes a Dynamic–Static Graph Fusion Multi-Head Flow Attention Network (DSGFMFAN). Specifically, an Information-Enhanced Gated Recurrent Unit (IE-GRU) is designed to more effectively capture temporal correlations. Meanwhile, a Dynamic–Static Graph Fusion Gating (DSGFG) mechanism is introduced to integrate dynamic and static graphs, enabling more comprehensive modeling of latent spatial dependencies. Furthermore, a Gated Multi-Head Flow Attention mechanism (G-MFA) is proposed, which replaces the conventional linear projection in multi-head attention with a dynamic–static graph fusion gating module to capture complex spatiotemporal interactions. In addition, flow attention is incorporated into the model, along with a source competition mechanism and a sink allocation mechanism, to efficiently capture critical information while alleviating the quadratic complexity caused by similarity computations in traditional attention mechanisms. Extensive experiments on four real-world traffic datasets demonstrate that DSGFMFAN significantly outperforms existing baseline methods in terms of prediction accuracy. Full article