Search Results (414)

This paper investigates the feasibility of using Large Language Models (LLMs) for the structural analysis of flow-based network data. This analysis is carried out in the presence of a structural difference between the multidimensional numerical space of IoT features and the symbolic space in which LLMs operate. The primary objective was the development of a formal framework that enables the controlled transformation of numerical data into linguistically analyzable semantic representations, without resorting to classification or machine learning mechanisms. We propose the Semantic Flow Encoding (SFE) mechanism, a deterministic method for robust discretization and behavioral abstraction that converts the numerical characteristics of Internet of Things (IoT) flows into structural semantic descriptions using the Canadian Institute for Cybersecurity Internet of Things Device Identification and Anomaly Detection (CIC IoT-DIAD) 2024 dataset. Through formal informational measures, it is demonstrated that the existence of an intrinsic structural difference between benign and DDoS traffic in the analyzed dataset. In the validation stage, we evaluated whether these informational differences are reflected at the level of linguistic abstraction through controlled inference experiments in IBM WatsonX. The present paper suggests that LLMs may support semantic auditing of distributional structure when guided by a formal encoding layer. In this manner, a reproducible framework for integrating numerical security data into language-model-based analysis is suggested. Full article

The Internet of Medical Things (IoMT) is becoming a vital part of modern healthcare, enabling ongoing patient monitoring and remote diagnosis. However, as more devices connect to the internet, healthcare systems become more vulnerable to serious security issues such as unauthorized access, patient data manipulation, and Man-in-the-Middle attacks. Conventional Intrusion Detection Systems (IDSs) often struggle with the unclear and uncertain characteristics of IoMT traffic, which leads to reduced detection accuracy and increased false alarms. To address these challenges, this paper proposes ML-FSID-FIS, a multi-level feature selection-based Intrusion Detection System that employs a fuzzy inference system (FIS) for classification in IoMT networks. The model combines multiple feature selection techniques into a three-stage multi-level feature selection strategy to improve detection efficiency and strengthen the security of IoMT networks. In the first stage, four feature selection techniques—Random Forest, XGBoost, ReliefF, and Mutual Information—are applied to identify the most relevant features. In the second stage, a frequency-based consensus strategy is utilized to extract consistently selected features from the four top-ranked sets. In the third stage, an ensemble refinement using bagging-based ranking is employed to rank the remaining features, resulting in the selection of the top five features. From these, three candidate 3-feature groups are formed and evaluated, and the best-performing group is selected as the final input set for the fuzzy logic classifier. The FIS produces a continuous risk score that is mapped to a binary decision using a validation-selected threshold. When the proposed method was tested on the WUSTL-EHMS-2020 dataset and compared with other recent work using the same dataset, it showed strong detection performance while maintaining a very low false positive rate of 0.3%. This study is distinguished by its integrated design, which combines a three-stage multi-level feature selection strategy with fuzzy logic-based intrusion classification to improve feature efficiency and support interpretable intrusion detection in IoMT. Full article

Traffic congestion is a problem in urban traffic that needs to be monitored and managed intelligently. In this study, a hybrid traffic management system is designed based on a combination of drone vision, large language model (LLM) inferences, and deep reinforcement learning (DRL). Using drones videos of real-time traffic, the lightweight You Only Look Once v11 model detects vehicles, and after, traffic flow levels are identified by the proposed LLM agent. A Circular-Deep Q-Networks-based DRL controller is proposed to reduce the average waiting time of vehicles. Simulation experiments validate improved congestion detection, reduced delay, and more effective communication for smart city traffic control. Full article

Bridge weigh-in-motion (BWIM) systems estimate axle and gross vehicle weights from measured bridge responses, typically strains but also displacements and rotations, via algorithms based on influence lines. Changes in inferred weights have been proposed as damage indicators, allowing existing BWIM installations to contribute to structural health monitoring without additional sensors. However, BWIM accuracy is sensitive to discrepancies between idealised models and actual bridge–traffic conditions, including variability in vehicle configurations, road profiles, measurement noise, multiple-vehicle presence, and uncertainty in vehicle positioning. This paper uses a numerical vehicle–bridge interaction framework to compare the sensitivity of direct structural responses and BWIM-derived gross vehicle weights to global, local, and combined stiffness reductions in a short-span, simply supported bridge. The analysis considers different signal-to-noise ratios and field-representative BWIM error distributions corresponding to COST 323 accuracy classes. Direct monitoring of strain, displacement, and especially rotation provides slightly higher sensitivity to global stiffness changes than BWIM-inferred weights, but BWIM-inferred weights derived from rotations can be more robust than direct responses for detecting local damage under low signal-to-noise ratios. When BWIM calibration and modelling errors are included, detection performance degrades rapidly with decreasing accuracy class; meaningful local-damage detection is achieved only for the highest class. Multi-sensor configurations combining strain and rotation help distinguish quasi-uniform global changes from localised damage by exploiting their differential sensitivity to global and local stiffness variations. Full article

Following China’s completion of the removal of provincial boundary toll stations and expressway network integration reform, a large number of electronic toll collection (ETC) gantries were deployed along expressway mainlines nationwide, transforming these facilities from dedicated toll terminals into pervasive traffic-sensing infrastructure covering the entire road network. However, the data value and technological potential embedded in this major infrastructure transformation have not yet been systematically reviewed. This paper adopts a narrative review methodology, incorporating 71 publications identified through multi-database systematic searches. The review is organized along the functional upgrade path of ETC gantries, covering the progression from toll terminals to traffic sensing nodes, multi-source fusion hubs, and finally vehicle–road–cloud cooperative control nodes, and synthesizes research progress in expressway traffic sensing, multi-source data fusion, safety operations, and emerging applications. The review reveals that ETC data have enabled a diverse methodological repertoire spanning travel time estimation, traffic flow prediction, origin–destination (OD) matrix inference, toll plaza safety analysis, dynamic pricing strategies, and environmental impact assessment. Nevertheless, a single ETC data source suffers from inherent limitations: spatial–temporal resolution constrained by gantry spacing and real-time capability limited by transmission latency. This fundamental contradiction constitutes the core driving force behind multi-source data fusion and vehicle–road–cloud integration technologies. The paper further argues that establishing a closed-loop pipeline integrating sensing, fusion, decision, and control and anchored on ETC gantry nodes represents the key direction for realizing intelligent expressway transformation. Full article

Distributed denial-of-service (DDoS) attacks, a type of Denial-of-Service (DoS) attack in which the targeted server, service or network is overloaded with malicious traffic originating from various different sources with the aim of making such targets inaccessible for legitimate users, continue to pose a pertinent threat to the availability and integrity of organisational digital assets. While many studies have shown that machine learning models can provide high predictive accuracy in detecting such attacks, they often fail to evaluate the practicality of deploying such models to production. This study aims to address this gap by evaluating a considerable amount of pipelines based on five popular supervised classifiers for detecting DDoS attacks using the CICDDoS2019 dataset. The study employs a comprehensive methodology that combines both manual feature removal with automated encoding, scaling and feature selection integrated within pipelines. A total of 210 pipelines formed of five classifiers, three features selectors, two hyperparameter tuners and seven train–test splits were initially evaluated. Pipeline performance was assessed using both conventional and computational performance metrics. To identify the champion pipeline, a two-step approach was employed: composite scoring for shortlisting and statistical testing using Friedman and post hoc Nemenyi tests. The champion pipeline was shown to be Decision Tree coupled with Recursive Feature Elimination (with 20 features selected) and Grid Search hyperparameter tuning with a 90-10 train–test split. It achieved the most optimal balance of predictive capabilities and computational overheads, achieving an MCC of $0.993\pm 0.024$, training time of $0.194\pm 0.001$ s, inference time of $0.000998\pm 0.00008$ s, CPU time of $0.194\pm 0.008$ s and average memory usage of 15,167 ± 322 kilobytes across training and inference. The findings highlight the importance of a holistic and more nuanced approach when selecting a champion pipeline that is not only effective but also feasible for deployment in resource-constrained environments. Full article

Highway ramp merging requires autonomous vehicles to make safe and efficient decisions in dense mixed traffic, where strong vehicle interactions and rapidly changing acceptable gaps make the task particularly challenging. Existing reinforcement learning methods are often unimodal and overly conservative, while diffusion-based policies, despite their ability to generate multimodal actions, usually suffer from high inference latency and safety risks caused by unconstrained sampling. To address these issues, this paper proposes AM-DIMPO, an action-mask-guided safe diffusion-implicit policy optimization framework for ramp-merging tasks. The proposed method combines DDIM-based implicit sampling with a state-dependent continuous action mask to improve multimodal action generation efficiency while enhancing action feasibility. In addition, the mask correction signal is incorporated into policy learning to encourage the policy to generate actions closer to the safe feasible region. Experiments are conducted in a Gym-based ramp-merging simulator under both light-traffic and dense-traffic scenarios, where the proposed method is compared with classical reinforcement learning baselines, diffusion reinforcement learning baselines, and a safety-aware PPO baseline. The results show that, in dense traffic, AM-DIMPO achieves a merging success rate of 97.3%, an average speed of 16.27 m/s, and an inference latency of 68 ms; in light traffic, the success rate reaches 98.1%. Moreover, the proposed method maintains robust performance under the tested noisy-observation and reduced-visibility settings. Overall, AM-DIMPO achieves a favorable balance among empirical safety, traffic efficiency, robustness, and real-time inference performance in dense highway ramp-merging tasks. Full article

Traffic flow forecasting provides essential support for the construction of smart transportation systems. Despite the superiority of the ASTGCN, which uses an attention mechanism to capture spatio-temporal correlations, it lacks an explicit physical interpretation and thus falls into a more general category known for its lack of such interpretation. As a result, in the presence of sparse or unstable congestion, these data-driven models often violate conservation laws and may generate “physical anomalies” or other logically impossible states. To close the gap of data-driven expressiveness and physical consistency, we propose the congestion-aware physics-guided STGCN (CAP-STGCN). This framework builds a synergistic model that achieves intrinsic coupling between the macroscopic traffic flow kinematics (fundamental diagram) and the spatio-temporal learning process. That is to say, under the model’s solution-space constraining effect, its motion space is bound on a feasible manifold. In terms of kinematics, it restricts consistency in the flow, density and speed. Concurrently, to address slow convergence under long-tailed distributions due to a lack of training samples, such as when there are fewer users or higher-quality items, a dynamic congestion-rectification mechanism is introduced. The aforementioned mechanism redefines the optimization landscape by prioritizing hard-to-predict saturation occurrences. Experiments show that, compared with other models, CAP-STGCN achieves higher prediction accuracy; more importantly, it is free of physical anomalies during inference and can be directly used in practice. Full article

Vehicular ad hoc networks (VANETs) operating in dense urban environments are characterized by highly dynamic topology, fluctuating traffic conditions, and stringent latency requirements, which significantly complicate reliable data routing and packet forwarding. To address these challenges, this paper proposes an Intelligent Fuzzy Protocol (IFP) for adaptive vehicle-to-vehicle data routing under uncertain and rapidly changing traffic scenarios. The proposed protocol integrates fuzzy logic decision making with the real-time vehicular context, including vehicle velocity, traffic congestion level, distance to road junctions, and data urgency, to dynamically select appropriate forwarding actions. IFP employs a structured fuzzy inference engine comprising fuzzification, rule evaluation, inference aggregation, and centroid-based defuzzification to determine routing and forwarding decisions in a decentralized manner. To further enhance performance robustness, the fuzzy membership parameters and rule weights are optimized using metaheuristic techniques, namely, genetic algorithms (GAs) and particle swarm optimization (PSO). Extensive simulations are conducted using NS-3 coupled with SUMO under realistic urban mobility scenarios and varying network densities. The simulation results demonstrate that IFP significantly outperforms conventional routing approaches in terms of end-to-end delay, packet delivery ratio, and routing overhead. In particular, the optimized IFP variants achieve notable reductions in latency and improvements in delivery reliability under high-congestion conditions, while maintaining low computational and communication overhead. These findings confirm that IFP offers an interpretable, scalable, and energy-aware routing solution suitable for large-scale intelligent transportation systems and next-generation vehicular networks. Full article

LoRaWAN’s role in global maritime logistics has allowed for efficient monitoring of ships and cargo, but it also comes with critical cybersecurity vulnerabilities. Experimental validation of three attack vectors—replay attacks, narrowband jamming and metadata inference—is conducted using a reproducible digital-twin LoRaWAN dataset reflecting Rotterdam port-like operational patterns (N = 20,000 baseline transmissions). Using controlled simulations and Kolmogorov–Smirnov statistical analysis, we show that: (1) replay attacks are feasible under Activation by Personalization (ABP) configurations lacking enforced frame-counter validation and exhibit no univariate separation from legitimate traffic under Kolmogorov–Smirnov analysis (p > 0.46 for all evaluated radio features); (2) narrowband jamming leads to significant SNR degradation (p = 2.36 × 10⁻⁵) on targeted channels without inducing broad distributional anomalies across other radio features; and (3) metadata-only analysis supports elevated metadata-based re-identification susceptibility (median $R_d=0.834$), indicating high predictability under passive observation which can reveal operationally relevant signals even when AES-128 is employed. Our proposed layered mitigation framework consists of mandatory Over-the-Air Activation (OTAA), cryptographic key rotation, channel diversity incorporating Adaptive Data Rate (ADR), gateway hardening, and protocol-level enforcement considerations, customized for maritime LPWAN scenarios. We provide experiment-backed evidence and actionable recommendations to connect academic LPWAN security research to that of industrial maritime practice. Full article

Urban mental health is increasingly influenced by daily environmental exposures, yet limited empirical evidence exists regarding how the spatial configuration of blue–green environments, rather than their mere quantity, relates to emotional behavior in high-density cities. Guided by restoration theories and a perception-based perspective on landscape integration, this study analyzes the urban core of Shanghai by linking blue–green configurations to emotional states inferred from 20,907 geotagged social media facial photographs. Facial expressions serve to derive indices for emotional valence and arousal. The results demonstrate significant spatial clustering of emotional behavior, where hotspots are concentrated in higher-quality and more open settings, while coldspots cluster in dense areas with sparse vegetation. Emotional behavior also exhibits demographic heterogeneity, as females display higher valence and arousal than males. Furthermore, happiness tends to increase with age across both genders, whereas arousal declines specifically among male age groups. Crucially, emotional outcomes align more consistently with landscape integration and configuration than with isolated blue or green areas. Factors such as high connectivity, superior vegetation condition, and configurations featuring water embedded within green space are associated with favorable emotional responses. Conversely, extensive edge-dominated interfaces and high traffic exposure correlate with less favorable outcomes. These findings suggest a shift in blue–green planning from increasing total area toward optimizing spatial composition. Specifically, priority should be given to embedded and cohesive designs alongside the reduction of ambient stressors to foster emotionally supportive environments in dense urban cores. Methodologically, image-derived behavioral traces provide a scalable and ecologically grounded approach for investigating place-based affect at a city scale. Full article

A methodology was developed to evaluate the behavior of reinforced concrete slabs used in temporary traffic bridge systems installed over uncured cement concrete pavement sections using highly scaled-down experimental reinforced concrete slabs. A full-scale reinforced concrete slab was first designed and its behavior, such as strain and deflection, was numerically analyzed. A small-scale reinforced concrete slab was then designed considering a dimensional reduction ratio of 1/6. When using this reduction ratio, there is no actual reduced size steel bar, so the smallest size steel bar available must be used for placement. Therefore, numerical analyses were performed to design the steel bar arrangement of the small-scale slab so that the same behavior as that of the full-scale slab occurred. To conduct experiments, small-scale experimental slabs were fabricated according to the design. Since the size of coarse aggregates must be reduced in concrete used for small-scale slabs, specimens using the concrete mix design for full-scale slabs were also produced and the compressive strengths were compared to confirm that the strengths were the same. Next, a study was conducted on the selection of strain gauges that can be used in small-scale slab experiments, and a method for installing displacement gauges to accurately measure slab deflection was also designed. Based on this series of basic studies, load tests were performed to measure the strains and deflections of small-scale slabs. Comparing the measured behavior of the small-scale slab with the numerical analysis results, it was confirmed that the same behavior was observed. Therefore, the experimental results and numerical analysis results of the small-scale slab were consistent, and the numerical analysis results of the small-scale slab and the full-scale slab were identical, proving that the experimental results of the full-scale slab can be inferred through experiments using the small-scale slab. This study confirmed that if small-scale slabs are designed and manufactured to appropriately reflect the characteristics of full-scale slabs, even though the process is challenging, the behavior of full-scale slabs can be approximately determined through experiments using small-scale slabs. Full article

Low Earth orbit (LEO) satellite networks require real-time routing to cope with dynamic topology variations caused by continuous orbital motion. As an alternative to conventional routing approaches, deep reinforcement learning (DRL) has recently gained attention as an effective means for optimizing routing paths. To solve routing problems modeled as a grid-based Markov decision process (grid-based MDP), DRL methods such as CNN-based Dueling DQN have been proposed. However, these approaches are difficult to implement in practice. In particular, the substantial floating-point computation and memory traffic of CNN inference make real-time onboard inference challenging under the stringent power and resource constraints of satellite platforms. To address these constraints, this paper proposes an INT8 quantization and hardware–software co-design framework using heterogeneous SoC FPGA acceleration. We offload compute-intensive CNN inference to the programmable logic (PL), while the processing system (PS) orchestrates overall control and data movement, forming a collaborative PS–PL architecture. Furthermore, we integrate the NITI-style two-pass scaling with PS–PL exponent propagation to preserve end-to-end integer consistency without floating-point conversion. To demonstrate its practical onboard feasibility, we employ standard accelerator implementation choices—such as output-stationary scheduling and on-chip prefetching—and conduct an ablation study over independently tunable axes (PE array size and PS-side buffer reuse) to quantify their incremental contributions. Experimental results show that the proposed PS–PL cooperative scheme dramatically reduces computation time compared to a PS-only reference implementation on the same platform. Full article

The proliferation of next-generation Internet infrastructures and the Internet of Things (IoT) has exponentially increased network traffic complexity. While deep learning (DL)-based intrusion detection systems (IDSs) show immense potential, they persistently suffer from challenges including high computational overhead, vanishing gradients in deep architectures, and acute sensitivity to noise. Consequently, these issues impede their real-time deployment in resource-constrained edge computing environments. To overcome these limitations, we propose a novel, lightweight, and robust intrusion detection framework based on deep neural networks (DNNs). Initially, we employ a Robust Scaler-based statistical preprocessing strategy to supersede traditional Z-score standardization, effectively mitigating the adverse impacts of outliers and burst traffic noise. Subsequently, we design an advanced architecture that integrates self-normalizing residual blocks with a channel attention mechanism. Leveraging compressed hidden layers alongside the Scaled Exponential Linear Unit (SELU) activation function, this architecture not only mitigates the vanishing gradient problem but also amplifies critical traffic features. Concurrently, it achieves a substantial reduction in both parameter count and inference latency. Furthermore, we introduce a cosine annealing strategy to dynamically adjust the learning rate during training, thereby facilitating the model’s escape from local optima and accelerating convergence. Extensive experiments on standard benchmark datasets demonstrate that our proposed framework achieves superior detection accuracy while maintaining exceptional computational efficiency compared to state-of-the-art baselines. Full article

In high-density expressway environments, lane-changing (LC) maneuvers act as stochastic perturbations that compromise the hydrodynamic stability of traffic flow, leading to safety hazards and operational delays. While existing literature has extensively modeled crash severity in static complex environments (e.g., tunnels and mountainous terrains), there remains a critical deficiency in quantifying the dynamic, systemic risks induced by LC maneuvers under saturation conditions. To address this gap, this study proposes a novel Systemic Risk Assessment Framework. First, a Hidden Markov Model (HMM) is employed to decode the latent state transitions of following vehicles, quantifying the systemic consequence of LC maneuvers as “operational delay” based on traffic wave theory. Second, a Bayesian Network (BN) is constructed to infer the causal probability of risk, integrating geometric proxies such as insertion angle with kinematic variables. Validated with real-world trajectory data, the model achieves high accuracy in identifying risk accumulation precursors. This research contributes to the field of transportation systems by shifting the risk paradigm from static collision prediction to dynamic system reliability analysis, offering theoretical support for Connected and Autonomous Vehicle (CAV) decision logic. Full article