Search Results (999)

This paper presents a numerical-computational analysis of ${\mathsf{\ell }}_2$-regularized logistic learning for binary intrusion detection under heterogeneous datasets, class imbalance, and cross-dataset shift. Rather than proposing a new intrusion detection architecture, the study examines how numerical conditioning, feature scaling, feature set design, threshold selection, false negative behavior, false alarm behavior, and distribution shift affect operational detection performance. Experiments were conducted on CICIDS2017, UNSW-NB15, and CIRA-CIC-DoHBrw-2020 using reproducible train–validation–test protocols over five fixed random seeds. The numerical audit showed that standard scaling reduced the spectral condition number of traffic feature matrices by several orders of magnitude across datasets and feature configurations. However, scaling did not produce uniformly monotonic predictive gains: in some cases, raw feature optimization achieved comparable or higher F1-score, whereas scaled preprocessing produced more controlled false alarm behavior. In-domain experiments showed that dataset-specific features may improve ranking metrics such as area under the receiver-operating-characteristic curve (AUROC) or area under the precision–recall curve (AUPR) without necessarily improving thresholded operational metrics. Cross-dataset transfer experiments revealed strong source–target asymmetry, with transferred thresholds producing either near-zero positive detection or excessive false alarms. Additional robustness experiments with Random Forest and XGBoost improved in-domain F1-score and false negative rate (FNR), but did not eliminate off-domain degradation, with high FNR persisting under direct cross-dataset transfer. Finally, a Kolmogorov–Smirnov-based distribution shift analysis showed that in-domain discrepancies were small, whereas cross-dataset discrepancies were consistently large under common standardized traffic features. These findings suggest that numerical stability, ranking quality, thresholded detection performance, false negative and false alarm behavior, and distribution shift should be analyzed jointly when evaluating intrusion detection models. Full article

To address the severe coverage blind spots and concurrent collision bottlenecks faced by LoRa networks in dense deployments and complex three-dimensional (3D) occlusion environments, this paper proposes a distributed cross-layer protocol framework for LoRa ad hoc networks supporting heterogeneous traffic. To break through the limitations of a single star architecture, this framework constructs a 3D penetration loss model at the physical layer and designs a distributed relay deployment algorithm based on hybrid simulated annealing, achieving blind-spot-free connectivity in complex spaces. At the MAC layer, a non-preemptive priority access mechanism based on symbol energy detection is introduced. Through differentiated backoff windows with time-domain isolation, it precisely guarantees the quality of service (QoS) requirements of heterogeneous traffic and significantly suppresses concurrent collisions. At the network layer, the CAM-AODV routing algorithm is proposed, which integrates hop count, link quality, MAC queue congestion, and nodal residual energy to achieve dynamic traffic diversion and network-wide energy balancing under bursty high loads. Simulation results demonstrate that this cross-layer framework effectively breaks the traditional network capacity bottlenecks. In a large-scale, high-density scenario with 300 nodes, CAM-AODV reduces the average end-to-end delay by 19.46% compared to the traditional AODV. Under high-concurrent loads, the packet delivery ratio (PDR) of the proposed framework improves by 16.32% over the traditional protocol, while the system delay is reduced by 13.66%. Furthermore, under the two aforementioned evaluation scenarios, the Energy Balancing Index (EBI) is significantly improved by 11.13% and 10.57%, respectively, compared to the traditional protocol. This study provides an efficient joint optimization scheme for building high-capacity, wide-coverage, and long-lifespan complex Internet of Things (IoT) networks. Full article

Automatic Identification System (AIS)-based vessel trajectory prediction is essential for maritime traffic management and navigation safety. Existing deep learning methods typically model vessel motion within a unified temporal representation space, which may entangle long-term navigation trends with local maneuvering behaviors. However, vessel trajectories inherently exhibit heterogeneous dynamics, including steady route evolution and non-stationary maneuver perturbations. To address this issue, this paper proposes MD-EDTCNFormer, a motion-decoupled dual-stream framework for vessel trajectory prediction. A Global Navigation Dynamics Encoder is designed to capture dominant route-level temporal evolution from raw AIS sequences, while a Residual Maneuver Dynamics Encoder explicitly models maneuver-related local perturbations through state transition residual representations. In addition, a state-adaptive motion aggregation mechanism is introduced to dynamically balance global navigation dependencies and local maneuver-aware dynamics under different navigation states. Depthwise separable temporal convolution and efficient channel attention are further integrated to suppress redundant temporal-channel coupling and emphasize dynamically dominant motion cues. Experiments on a real-world AIS dataset from the Zhoushan coastal area demonstrate the effectiveness of the proposed framework under coastal traffic conditions, and show improvements in prediction accuracy and trajectory stability compared with representative baseline methods. Full article

Understanding the built environment is essential for explaining road safety outcomes, particularly through individuals’ perceptions of their surroundings, which are linked to perceived travel risk and play an important role in pedestrian decision-making. However, the heterogeneous effects of the built environment across contexts remain insufficiently understood and require further investigation. Thus, this study aims to investigate how perceived built environment attributes are associated with perceived travel risk and whether these associations differ across urban contexts, with specific variation in land-use contexts. Data were collected using questionnaires administered at pedestrian crossings in Bangkok, and ordinal regression was employed for the analysis. The results indicate that some factors are consistently significant across contexts, while others show significance in specific contexts. In particular, land use mix as diversity and traffic speed are among the variables that are consistently significant across multiple contexts. Overall, the findings suggest variation in the patterns of association between built environment attributes and perceived travel risk across contexts. These results provide useful insights for urban and transport planners regarding the role of environmental design and allocation in promoting safer pedestrian environments, thereby contributing to the development of a sustainable transport system by enhancing pedestrian safety and prioritizing pedestrians in planning. Full article

Urban traffic congestion remains a major barrier to sustainable mobility, necessitating a transition from static signaling to Intelligent Traffic Light Systems (ITLS). This study presents a systematic review in computer vision, artificial intelligence, and adaptive control algorithms for urban intersection optimization. Following a methodological framework informed by PRISMA guidelines, the study examines state-of-the-art architectures, including deep learning-based perception models and reinforcement learning agents. The findings indicate that, although two-stage detectors provide benchmark accuracy for vehicle perception, single-stage models and Vision Transformers offer the high-speed processing required for real-time traffic management. In addition, deep reinforcement learning enables autonomous, lane-specific optimization that outperforms traditional actuated and fixed-time systems. The review also identifies a persistent research gap in the deployment of these computational frameworks in the resource-constrained and heterogeneous infrastructures of developing countries. For the urban context of Riobamba, Ecuador, a phased implementation strategy is proposed that balances computational demands with the city’s morphological and social characteristics. By bridging the gap between high-fidelity simulation and practical field deployment, this review provides a scalable framework for improving throughput, reducing emissions, and enhancing safety. Overall, these advances offer a promising pathway toward more resilient transportation systems in rapidly evolving Andean urban centers. Full article

For the task of encrypted traffic classification, existing approaches commonly rely on a single feature view, such as side-channel characteristics or raw packet bytes, often incorporating techniques inspired by natural language processing and computer vision for modeling and classification. In recent years, multi-view learning has gained increasing attention due to its ability to enhance discriminative power and generalization performance by capturing complementary information from different perspectives. However, heterogeneous feature views often exhibit distributional discrepancies, which makes direct multi-view integration difficult. To address this issue, we propose CGF-Net, a multi-view contrastive learning framework for encrypted traffic classification. The proposed model is inspired by cross-modal contrastive learning and employs lightweight adaptation to learn representations from both behavioral and content views. During pre-training, CGF-Net performs instance-level cross-view contrastive learning by treating the behavioral and content views of the same network flow as a positive pair, thereby aligning heterogeneous representations at the flow-instance level. In addition, a lightweight fine-tuning module together with a gating-based fusion mechanism is introduced to improve the collaborative modeling capability of multi-view representations. Extensive experiments on four public datasets show that CGF-Net achieves ACC scores of 95.81%, 93.38%, 96.38%, and 95.72% on CSTNET-TLS1.3, CipherSpectrum, ISCXVPN2016, and ISCXTor2016, respectively. Compared with the best-performing baseline on each dataset, CGF-Net improves the average ACC and F1-score by 0.78 and 0.69 percentage points, respectively, demonstrating the effectiveness of the proposed model. Full article

The rapid growth of Intelligent Transportation Systems (ITSs) and Internet of Things (IoT) technologies has generated massive volumes of distributed traffic data, creating significant challenges related to privacy, scalability, communication overhead, and heterogeneous traffic patterns. To address these challenges, this paper proposes FedTraffic, a hierarchical federated learning framework for traffic flow forecasting that integrates Edge–Fog–Cloud computing, hybrid deep learning, adaptive federated optimization, and Explainable Artificial Intelligence (XAI). The proposed framework combines a Temporal Convolutional Network–Conditional Variational Autoencoder (TCN–CVAE) with traffic-behavior clustering, adaptive client selection, and hierarchical model aggregation to enable accurate, privacy-preserving, and interpretable traffic prediction under heterogeneous non-IID environments. Extensive experiments demonstrate that FedTraffic achieves a best Mean Absolute Error (MAE) of 2.12, a Root Mean Square Error (RMSE) of 4.28, a Mean Absolute Percentage Error (MAPE) of 5.47%, and an $R^2$ score of 0.966. Compared with the strongest federated baseline, it improves MAE by up to 18.77%, RMSE by 16.41%, and MAPE by more than 22%, while reducing communication overhead through an 8:1 latent representation compression ratio. These results demonstrate the effectiveness of FedTraffic as a scalable, privacy-preserving, and interpretable solution for next-generation intelligent transportation systems. Full article

Rapidly developing, mid-sized Canadian municipalities often suffer from a deficit in dedicated modernization capacity, leaving public infrastructure lagging behind growth and reliant on historically “grandfathered” legacy solutions. To overcome the lack of empirical, data-backed planning in these regions, this paper proposes an agile, data-driven smart city framework centered around a localized digital twin (DT) environment. The framework is evaluated through a case study of a proposed new public transit route in Abbotsford, British Columbia, a rapidly expanding city grappling with decentralized commercial zones and low-density sprawl. Our approach synthesizes heterogeneous, multi-source spatial data, including regional commuter trajectories, real-time Abbotsford International Airport (YXX) flight schedules, and points of interest (POI) business densities, to map high-resolution hourly temporal variations in traffic conditions. These streams feed into a virtual simulation framework that evaluates operational cost–benefit trade-offs for proposed transit routes. Crucially, this framework serves as a living, continuously updated system that enables resource-constrained cities to dynamically simulate transit networks as commercial footprints and transit volumes evolve. Finally, we discuss the roadmap for this framework, detailing how integrating predictive AI models and gamified interfaces can democratize urban planning, enabling municipal stakeholders and non-technical operators to interactively co-design public transit systems. Full article

Identifying the spatio-temporal evolutionary patterns and driving mechanisms of rural tourism network attention is essential for predicting the development trends of the rural tourism industry and delivering refined industrial governance. Taking 356 prefecture-level cities in China from 2015 to 2024 as basic research units, this paper constructs a comprehensive evaluation system for rural tourism network attention based on multi-source data. Furthermore, its spatio-temporal evolution characteristics and internal influencing factors are systematically investigated by means of spatial autocorrelation analysis and geographically weighted regression. The results indicate that the overall level of rural tourism network attention in China shows an obvious fluctuating growth trend, which can be divided into three successive stages, namely steady growth (from 0.8530 in 2015 to 1.2028 in 2019), explosive growth (from 1.9563 in 2020 to 3.7471 in 2021) and high-level fluctuation (maintained in the high range of 2.4–3.4). In addition, with the continuous iteration of internet communication media, the guiding influence of traditional search platforms has gradually weakened, while emerging social media and short-video platforms have become the core carriers of online tourism traffic. Correspondingly, media innovation persistently reshapes the spatial distribution pattern of rural tourism network attention. In terms of spatial characteristics, rural tourism network attention has undergone a significant transformation from geographical gradient polarization to overall regional equilibrium. Specifically, from 2015 to 2024, the overall Moran’s I index remained positive, with values ranging from 0.0116 to 0.1358, indicating an overall trend of gradual decline. High-attention areas are predominantly concentrated in economically developed urban agglomerations, whereas remote and economically underdeveloped regions exhibit contiguous low-value aggregation characteristics, which reveals a remarkable trend of balanced development nationwide. In view of driving mechanisms, highway network density, tourism income, rural tourism resource and enrollment of university students are identified as the core driving factors dominating the spatio-temporal evolution of rural tourism network attention. Moreover, the intensity of the influence of each factor presents distinct spatial heterogeneity. This study further reveals that the spatial heterogeneity of rural tourism network attention calculated using multi-source fused data shows a remarkable convergent characteristic, which can reflect the actual distribution of the rural tourism market more objectively and accurately. Meanwhile, rural tourism network attention is typically characterized by scale-dependent with the spatial distribution at the macro-scale being more balanced than that at the meso- and micro-scales. Full article

The continuous emergence of new attack classes challenges intrusion detection in edge Internet of Things (IoT) networks. Although federated learning enables distributed devices to collaboratively train a shared detector without exchanging raw traffic data, most federated intrusion detection systems assume a fixed label space. Retraining with all historical data incurs substantial storage and computation costs, whereas updating only with newly collected samples can cause catastrophic forgetting. The detector must mitigate catastrophic forgetting of previously observed attack classes while preserving sufficient new-class plasticity to learn emerging attacks under highly non-IID device data, intermittent client availability, constrained local memory, and repeated communication over bandwidth-limited and intermittently connected links. To address these challenges, this paper proposes EdgeFedCIL, a communication-efficient federated class-incremental intrusion detection framework. EdgeFedCIL preserves historical knowledge through client-local replay and knowledge distillation while reducing repeated model transmission through adaptive low-rank compression, quantization, and error feedback. A classifier-head protection strategy further limits compression-induced degradation of class discrimination. Experiments on public intrusion-detection datasets show that EdgeFedCIL achieves competitive or superior detection and historical-knowledge retention performance, particularly under highly heterogeneous client distributions, while reducing cumulative client-to-server model transmission by up to approximately 10.54 times relative to full-precision transmission. These results demonstrate the effectiveness of EdgeFedCIL for continual and communication-efficient intrusion detection in resource-constrained edge IoT networks. Full article

Satellite–terrestrial integrated networks (STINs) can extend remote sensor telemetry, remote Internet of Things (IoT), and emergency communication services beyond terrestrial coverage, but their evaluation is complicated by heterogeneous mobility, channel, resource, and control-plane dynamics. This study presents a software-based modular testbed and performance-emulation framework for STINs. The framework integrates scenario generation, model-driven data processing, replaceable algorithm engines, scheduler-based execution control, and a Kafka-style message interface. It models terrestrial, unmanned aerial vehicle, and low-Earth-orbit satellite entities and provides link-budget abstraction, access control, mobility-aware handover, traffic generation, scheduling, load balancing, adaptive routing, and multi-mode transmission for mixed sensing and communication traffic. The representative strategies are evaluated using a lightweight emulation model parameterized by standards-informed NTN and link-budget assumptions. Representative results reveal tradeoffs between access, handover, routing, and scheduling strategies, together with sensitivity to workload, mobility, outage, demand, and selected model parameters. The proposed framework therefore supports traceable STIN strategy evaluation for remote sensor networks, sensing-data backhaul, and remote-IoT service scenarios under explicit emulation assumptions. Full article

Industrial Internet of Things (IIoT) edge computing supports latency-sensitive services through task offloading to distributed edge resources. However, large-scale emergencies such as node failures and traffic surges may trigger cascading failures, leading to severe performance degradation and poor post-crisis recovery. Existing offloading methods mainly optimize operational efficiency under normal conditions while overlooking resilience against cascading disruptions. To address this issue, we propose Cascade-Emergency Resilient Offloading (CERO), an adversarial deep reinforcement learning framework for resilient task offloading in IIoT edge computing. Distinct from existing works, CERO introduces a structure-aware shared node encoder to capture heterogeneous topological roles of edge nodes, providing critical structural information for cascade-aware decision making, and incorporates cascade-oriented adversarial training to enhance robustness against compound disturbances. CERO integrates structure-aware state representation, minimax adversarial training, and potential-based reward shaping to learn resource-allocation policies balancing task efficiency and system resilience. By interacting with dynamically generated crisis scenarios, the agent learns resilient offloading policies and achieves high post-crisis recovery performance after cascading disruptions. All performance evaluations are conducted via discrete-event simulation experiments. Simulation results for normal, single-crisis, and compound-crisis scenarios show that CERO achieves comparable task efficiency under normal conditions and significantly superior post-crisis recovery performance compared to conventional rule-based strategies. In the hardest compound-crisis case involving simultaneous node failures and load surges, CERO achieves a post-recovery task-completion rate of 97.8%, surpassing the best rule-based baseline by more than 63 percentage points. Statistical significance is confirmed by the Wilcoxon signed-rank test with Bonferroni correction over 10 independent runs. These results demonstrate that CERO effectively improves the robustness and recoverability of IIoT edge-computing systems under cascading emergency scenarios. Full article

Smart grids with renewable energy sources require communication platforms that can evaluate heterogeneous links before field deployment. This article presents a centralized software-defined radio (SDR)-based performance analytics platform for physical/MAC-layer assessment of RF900, G3-PLC, GPRS CS2–CS3, hybrid PLC–GPRS, and renewable-event communication profiles. The platform combines a controlled UPS SDR/USRP experimental-simulation reference with reproducible packet-level simulations using traffic generation, channel impairment abstractions, CRC-based integrity verification, and centralized metrics: latency, bit error rate (BER), packet error rate (PER), useful throughput, and offered channel load. The revised evaluation uses a 120 s window, 3444 packets per baseline scenario, and 30 independent random seeds. The RF900 AWGN baseline achieved $36.58\pm 0.01$ ms mean latency, $1.78\times {10}^{-4}$ BER, $0.175\pm 0.003$ PER, and 24.23 kbps useful throughput. Hybrid PLC–GPRS reduced PER to $0.025\pm 0.001$, while the renewable-event hybrid profile achieved $89.33\pm 0.13$ ms and $0.028\pm 0.001$ PER. This study provides a reproducible pre-deployment analytics framework, not full utility field validation or application-layer interoperability certification. Full article

Accurate short-term load forecasting for EV public charging stations is essential for grid and station operations. However, predictions are challenging because charging loads are non-stationary, spatially heterogeneous, and closely coupled with external factors such as weather and pricing. In this study, we forecast hourly regional charging energy using the open UrbanEV benchmark dataset, which includes hourly charging records from 1362 public charging stations across 275 traffic-analysis zones in Shenzhen from September 2022 to February 2023. We propose ST-Attention, a lightweight and modular forecasting model. It integrates temporal self-attention, spatial self-attention, an adjacency-matrix bias, and a residual prediction head. We compare ST-Attention with five baselines using a leakage-free rolling time-series evaluation protocol. For the 3 h horizon, ST-Attention achieves an MAE of 62.44 kWh, an RMSE of 291.8 kWh, and an MAPE of 5.91%, reducing the MAE by approximately 41% compared with the last-observation baseline. The model also maintains superior MAE performance at the 6 h and 9 h horizons. A modular ablation study shows that temporal attention and the residual head are the most stable sources of improvement, whereas dense spatial attention does not automatically provide benefits at hourly granularity with limited samples; removing it further reduces the 3 h MAE to 59.58 kWh. We present this as a cautionary finding: local temporal inertia dominates dense spatial coupling in hourly forecasting, and spatial model complexity must align with data granularity. Full article

In dynamic Vehicular Edge Computing (VEC) environments, rapidly changing vehicle mobility and traffic lead to fluctuating edge resource demands, challenging task offloading and scheduling. Accurate prediction of future traffic flow and traffic-state-derived workload representations is thus crucial for proactive resource management. To address the limitations of existing methods in short-term dynamic characterization, complex spatial interaction modeling, and heterogeneous target prediction, this paper proposes a Spatio-Temporal Graph Attention Network (TA-STGAT). The proposed model constructs multi-dimensional RSU-level state sequences from simulated trajectories generated on a real-world road network and separately forecasts vehicle flow within RSU coverage areas and the associated traffic-state-derived workload representation under a unified spatio-temporal modeling framework. By integrating gated dilated temporal convolutions with a topology-constrained multi-head graph attention mechanism, the model captures multi-scale temporal dependencies and nonlinear spatial correlations. Experimental results show that, compared with the best-performing baseline in terms of RMSE for each forecasting task, TA-STGAT reduces RMSE by 10.89% and 11.29% in workload-representation prediction and traffic flow prediction, respectively, demonstrating its effectiveness for short-term edge-state forecasting. Full article