Search Results (156)

With the rapid growth of autonomous vehicle technologies, effective path-tracking control has become a critical component in ensuring safety and efficiency in complex traffic scenarios. When a high-level decision-making agent generates a collision-free path, a robust low-level controller is required to precisely follow this trajectory. However, connected autonomous vehicles (CAV) are inherently affected by communication delays and computation delays, which significantly degrade the performance of conventional controllers such as PID or other more advanced controllers like disturbance observers (DOB). While DOB-based designs have shown effectiveness in rejecting disturbances under nominal conditions, their performance deteriorates considerably in the presence of unknown time delays. To address this challenge, this paper proposes a delay-tolerant communication disturbance observer (CDOB) framework for path-tracking control in delayed systems. The proposed CDOB compensates for the adverse effects of time delays, maintaining accurate trajectory tracking even under uncertain and varying delay conditions. It is shown through a simulation study that the proposed control architecture maintains close alignment with the reference trajectory across various scenarios, including single-lane change, double-lane change, and Elastic Band-generated collision avoidance paths under various time delays. Simulation results further demonstrate that the proposed method outperforms conventional approaches in both tracking accuracy and delay robustness, making it well-suited for connected autonomous driving applications. Full article

Preventive maintenance treatments are widely applied to asphalt pavements to mitigate deterioration and extend service life. This study evaluated four common technologies: a high-elasticity ultra-thin overlay, an Stone Mastic Asphalt (SMA)-10 thin overlay, micro-surfacing (MS-III), and a chip seal. Laboratory testing focused on skid resistance, surface texture, and low-temperature cracking resistance. Skid resistance was measured with a tire–pavement dynamic friction analyzer under controlled load and speed, while surface macrotexture was assessed using a laser scanner. Low-temperature cracking resistance was determined through three-point bending beam tests at −10 °C. The results showed that chip seal achieved the highest initial friction and texture depth, immediately enhancing skid resistance but exhibiting rapid texture loss and gradual friction decay. Micro-surfacing also demonstrated good initial skid resistance but experienced a sharp reduction of over 30% due to fine aggregate polishing. By contrast, the high-elastic ultra-thin overlay and SMA thin overlay provided more stable skid resistance, lower long-term friction loss, and excellent crack resistance. The polymer-modified ultra-thin overlay achieved the highest low-temperature bending strain ≈40% higher than untreated pavement, indicating superior crack resistance, followed by the SMA thin overlay. Micro-surfacing with a chip seal layer only slightly improved low-temperature performance. Overall, the high-elastic ultra-thin overlay proved to be the most balanced preventive maintenance option under heavy-load traffic and cold climate conditions, combining durable skid resistance with enhanced crack resistance. Full article

Traffic-induced vibrations from road and rail systems pose a significant threat to the structural integrity and operational safety of buildings, especially masonry structures located near planned infrastructure such as tunnels. This study investigates the dynamic impact of such vibrations on a representative early 20th-century masonry building situated within the influence zone of a design railway tunnel. A comprehensive analysis combining geological, structural, and vibration propagation data was conducted. A detailed 3D finite element model was developed in Diana FEA v10.7, incorporating building material properties, subsoil conditions, and anticipated train-induced excitations. Various vibration isolation strategies were evaluated, including the use of block supports and vibro-isolation mats. The model was calibrated using pre-construction measurements, and simulations were carried out in the linear-elastic range to prevent resident-related claims. Results showed that dynamic stresses in masonry walls and wooden floor beams remain well below critical thresholds, even in areas with stress concentration. Among the tested configurations, vibration mitigation systems significantly reduced the transmitted forces. This research highlights the effectiveness of integrated numerical modelling and vibration control solutions in protecting structures from traffic-induced vibrations and supports informed engineering decisions in tunnel design and urban development planning. Full article

The widespread deployment of electric vehicles (EVs) has introduced substantial challenges to electricity pricing, grid stability, and renewable energy integration. This paper proposes a real-time pricing optimization framework for large-scale EV charging networks incorporating renewable intermittency, demand elasticity, and infrastructure constraints within a high-dimensional optimization model. The core objective is to dynamically determine spatiotemporal electricity prices that simultaneously reduce system peak load, improve renewable energy utilization, and minimize user charging costs. A rigorous mathematical formulation is developed integrating over 40 system-level constraints, including power balance, transmission capacity, renewable curtailment, carbon targets, voltage regulation, demand-side flexibility, social participation, and cyber resilience. Real-time electricity prices are treated as dynamic decision variables influenced by charging station utilization, elasticity response curves, and the marginal cost of renewable and grid-supplied electricity. The problem is solved over 96 time intervals using a hybrid solution approach, with benchmark comparisons against mixed-integer programming (MILP) and deep reinforcement learning (DRL)-based baselines. A comprehensive case study is conducted on a 500-station EV charging network serving 10,000 vehicles integrated with a modified IEEE 118-bus grid model and 800 MW of variable renewable energy. Historical charging data with ±12% stochastic demand variation and real-world solar and wind profiles are used to simulate realistic operational conditions. Results demonstrate that the proposed framework achieves a 23.4% average peak load reduction per station, a 17.9% improvement in renewable energy utilization, and user cost savings of up to 30% compared to baseline flat-rate pricing. Utilization imbalances across the network are reduced, with congestion mitigation observed at over 90% of high-traffic stations. The real-time pricing model successfully aligns low-price windows with high-renewable periods and off-peak hours, achieving time-synchronized load shifting and system-wide flexibility. Visual analytics including high-resolution 3D surface plots and disaggregated bar charts reveal structured patterns in demand–price interactions, confirming the model’s ability to generate smooth, non-disruptive pricing trajectories. The results underscore the viability of advanced optimization-based pricing strategies for scalable, clean, and responsive EV charging infrastructure management in renewable-rich grid environments. Full article

Quality requirements for mineral aggregate for concrete used to construct pavement for busy highways are high because of the fatigue traffic loads and environmental exposure. The use of local aggregate for infrastructure projects could result in important sustainability improvements, provided that the concrete’s durability is assured. The objective of this study was to identify the potential alkaline reactivity of local greywacke aggregate and select appropriate mitigation measures against the alkali–silica reaction. Experimental tests on concrete specimens were performed using the miniature concrete prism test at 60 °C. Mixtures of coarse greywacke aggregate up to 12.5 mm with natural fine aggregate of different potential reactivity were evaluated in respect to the expansion, compressive strength, and elastic modulus of the concrete. Two preventive measures were studied—the use of metakaolin and slag-blended cement. A moderate reactivity potential of the greywacke aggregate was found, and the influence of reactive quartz sand on the expansion and instability of the mechanical properties of concrete was evaluated. Both crystalline and amorphous alkali–silica reaction products were detected in the cracks of the greywacke aggregate. Efficient expansion mitigation was obtained for the replacement of 15% of Portland cement by metakaolin or the use of CEM III/A cement with the slag content of 52%, even if greywacke aggregate was blended with moderately reactive quartz sand. It resulted in a relative reduction in expansion by 85–96%. The elastic modulus deterioration was less than 10%, confirming an increased stability of the elastic properties of concrete. Full article

In today’s increasingly interconnected digital world, cyber threats have grown in frequency and sophistication, making intrusion detection systems a critical component of modern cybersecurity frameworks. Traditional IDS methods, often based on static signatures and rule-based systems, are no longer sufficient to detect and respond to complex and evolving attacks. To address these challenges, Artificial Intelligence and machine learning have emerged as powerful tools for enhancing the accuracy, adaptability, and automation of IDS solutions. This study presents a novel, hybrid ensemble learning-based intrusion detection framework that integrates deep learning and traditional ML algorithms with explainable artificial intelligence for real-time cybersecurity applications. The proposed model combines an Artificial Neural Network and Support Vector Machine as base classifiers and employs a Random Forest as a meta-classifier to fuse predictions, improving detection performance. Recursive Feature Elimination is utilized for optimal feature selection, while SHapley Additive exPlanations (SHAP) provide both global and local interpretability of the model’s decisions. The framework is deployed using a Flask-based web interface in the Amazon Elastic Compute Cloud environment, capturing live network traffic and offering sub-second inference with visual alerts. Experimental evaluations using the NSL-KDD dataset demonstrate that the ensemble model outperforms individual classifiers, achieving a high accuracy of 99.40%, along with excellent precision, recall, and F1-score metrics. This research not only enhances detection capabilities but also bridges the trust gap in AI-powered security systems through transparency. The solution shows strong potential for application in critical domains such as finance, healthcare, industrial IoT, and government networks, where real-time and interpretable threat detection is vital. Full article

Modern network infrastructures have significantly improved global connectivity while simultaneously escalating network security challenges as sophisticated cyberattacks increasingly target vital systems. Intrusion Detection Systems (IDSs) play a crucial role in identifying and mitigating these threats, and recent advances in machine-learning-based IDSs have shown promise in detecting evolving attack patterns. Notably, IDSs employing Graph Neural Networks (GNNs) have proven effective at modeling the dynamics of network traffic and internal interactions. However, these systems suffer from Catastrophic Forgetting (CF), where the incorporation of new attack patterns leads to the loss of previously acquired knowledge. This limits their adaptability and effectiveness in evolving network environments. In this study, we introduce the Elastic Graph Neural Network for Intrusion Detection Systems (EL-GNNs), a novel approach designed to enhance the continual learning (CL) capabilities of GNN-based IDSs. This approach enhances the performance of the GNN-based Intrusion Detection System (IDS) by significantly improving its capability to preserve previously learned knowledge from past cyber threats while simultaneously enabling it to effectively adapt and respond to newly emerging attack patterns in dynamic and evolving network environments. Experimental evaluations on trusted datasets across multiple task scenarios demonstrate that our method outperforms existing approaches in terms of accuracy and F1-score, effectively addressing CF and enhancing adaptability in detecting new network attacks. Full article

The rapid growth of high-quality telecommunications demands enhanced queueing system performance. Traditional bandwidth distribution often struggles to adapt to dynamic changes, network conditions, and erratic traffic patterns. Internet traffic fluctuates over time, causing resource underutilization. To address these challenges, this paper proposes a new adaptive algorithm called Weighted Fair Queues continual Deep Reinforcement Learning (WFQ continual-DRL), which integrates the advanced deep reinforcement learning Soft Actor-Critic (SAC) algorithm with the Elastic Weight Consolidation (EWC) approach. This technique is designed to overcome neural networks’ catastrophic forgetting, thereby enhancing network routers’ dynamic bandwidth allocation. The agent is trained to allocate bandwidth weights for multiple queues dynamically by interacting with the environment to observe queue lengths. The performance of the proposed adaptive algorithm was evaluated for eight queues until it expanded to twelve-queue systems. The model achieved higher cumulative rewards as compared to previous studies, indicating improved overall performance. The values of the Mean Squared Error (MSE) and Mean Absolute Error (MAE) decreased, suggesting effectively optimized bandwidth allocation. Reducing Root Mean Square Error (RMSE) indicated improved prediction accuracy and enhanced fairness computed by Jain’s index. The proposed algorithm was validated by employing real-world network traffic data, ensuring a robust model under dynamic queuing requirements. Full article

Cracking in semi-rigid cement-stabilized macadam bases constitutes a prevalent distress in asphalt pavements. While extensive research exists on grouting materials for crack rehabilitation, quantitative assessment methodologies for treatment efficacy remain underdeveloped. This study proposes a novel evaluation framework integrating fiber Bragg grating (FBG) technology to monitor pavement mechanical responses under traffic loads. Conducted on the South China Expressway project, the methodology encompassed (1) a method for back-calculating the modulus of the asphalt layer based on Hooke’s Law; (2) a sensor layout plan with FBG sensors buried at the top of the pavement base in seven sections; (3) statistical analysis of the asphalt modulus based on the mechanical response when a large number of vehicles passed; and (4) comparative analysis of modulus variations to establish quantitative performance metrics. The results demonstrate that high-strength geopolymer materials significantly enhanced the elastic modulus of the asphalt concrete layer, achieving 34% improvement without a waterproofing agent versus 19% with a waterproofing agent. Polymer-treated sections exhibited a mean elastic modulus of 676.15 MPa, substantially exceeding untreated pavement performance. Low-strength geopolymers showed marginal improvements. The modulus hierarchy was as follows: high-strength geopolymer (without waterproofing agent) > polymer > high-strength geopolymer (with waterproofing agent) > low-strength geopolymer (without waterproofing agent) > low-strength geopolymer (with waterproofing agent) > intact pavement > untreated pavement. These findings demonstrate that a high-strength geopolymer without a waterproofing agent and high-polymer materials constitute optimal grouting materials for this project. The developed methodology provides critical insights for grout material selection, construction process optimization, and post-treatment maintenance strategies, advancing quality control protocols in pavement rehabilitation engineering. Full article

The paper presents a novel approach to evaluating the fatigue performance of asphalt pavements using fuzzy set theory to model the uncertainty in the elastic moduli of asphalt layers. The method integrates fuzzy numbers with an analytical multilayer elastic pavement model. By applying α-cut representation and defuzzification techniques, the model delivers fuzzy estimations of critical strain responses and associated fatigue lives under traffic loading. The proposed methodology captures uncertainty in material properties more realistically than conventional deterministic approaches. The effectiveness of this technique is demonstrated through the Asphalt Institute’s fatigue models for tensile and compressive strains. The results provide fuzzy bounds for fatigue life parameters and enable robust pavement design under material uncertainty. By incorporating fuzzy-modulus-based parameters into layered elastic half-space models, the proposed method significantly improves the predictive reliability of pavement performance. Full article

Urban traffic management faces significant challenges in balancing parking supply with user demand. This study introduces a novel parking demand model that integrates simulation-based pricing with elasticity functions derived from revealed preference data, segmented across predefined user categories, such as short-term visitors (e.g., shoppers) and monthly subscribers (e.g., commuters). Unlike previous models, this approach does not rely on survey-based inputs and explicitly accounts for both natural and chaotic demand behaviors, thereby improving forecasting accuracy under oversaturated conditions. The model supports sustainable parking management by optimizing space availability, while simultaneously increasing occupancy and enhancing revenue generation. Full article

The widespread deployment of electric vehicles (EVs) has introduced substantial challenges to electricity pricing, grid stability, and renewable energy integration. This paper presents the first real-time quantum-enhanced electricity pricing framework for large-scale EV charging networks, marking a significant departure from existing approaches based on mixed-integer programming (MILP) and deep reinforcement learning (DRL). The proposed framework incorporates renewable intermittency, demand elasticity, and infrastructure constraints within a high-dimensional optimization model. The objective is to dynamically determine spatiotemporal electricity prices that reduce system peak load, improve renewable utilization, and minimize user charging costs. A rigorous mathematical formulation is developed, integrating over 40 system-level constraints, including power balance, transmission limits, renewable curtailment, carbon targets, voltage regulation, demand-side flexibility, social participation, and cyber-resilience. Real-time electricity prices are treated as dynamic decision variables influenced by station utilization, elasticity response curves, and the marginal cost of renewable and grid electricity. The model is solved across 96 time intervals using a quantum-classical hybrid method, with benchmark comparisons against MILP and DRL baselines. A comprehensive case study is conducted on a 500-station EV network serving 10,000 vehicles, coupled with a modified IEEE 118-bus grid and 800 MW of variable renewable energy. Historical charging data with ±12% stochastic demand variation and real-world solar/wind profiles are used to simulate realistic conditions. Results show that the proposed framework achieves a 23.4% average peak load reduction per station, a 17.9% gain in renewable utilization, and up to 30% user cost savings compared to flat-rate pricing. Network congestion is mitigated at over 90% of high-traffic stations. Pricing trajectories align low-price windows with high-renewable periods and off-peak hours, enabling synchronized load shifting and enhanced flexibility. Visual analytics using 3D surface plots and disaggregated bar charts confirm structured demand-price interactions and smooth, stable price evolution. These findings validate the potential of quantum-enhanced optimization for scalable, clean, and adaptive EV charging coordination in renewable-rich grid environments. Full article

Bridges are critical nodes in transportation networks, and the evaluation of their service performance is of vital importance. Rapid assessment techniques based on the theory of influence lines have become a significant research topic. This study proposes a rapid testing method for the influence lines of beam-type bridges, with the synchronous monitoring of dynamic vehicle positions and a wireless network of multiple sensors. Field testing on a 30 m span T-beam bridge revealed that the measured vertical displacement during slow continuous driving corresponded with the static load test data within a deviation of ±6%, with the entire testing process completed in only 5 min, demonstrating efficiency and minimal traffic interference. Based on the measured influence lines, rapid bridge bearing capacity assessments and finite element model updating were researched. A case study of a simply supported T-beam bridge composed of prefabricated prestressed concrete showed that the calculated values using the proposed rapid assessment method deviated from traditional load test values between −5.68% and 4.69%, indicating a small error margin. After applying this method to the model updating of a (25 + 45 + 25) m continuous beam bridge on a highway, the inversion errors of the concrete elastic modulus and prestress were 1.40% and 1.20%, respectively, confirming the reliability of the precision. The rapid testing method for influence lines can be applied to bridge inspection, evaluation, and model updating. Full article

This paper presents an advanced framework for real-time monitoring and analysis of network traffic and endpoint security in large-scale enterprises by addressing the increasing complexity and frequency of cyber-attacks. Our Network Security Traffic Analysis Platform employs a comprehensive technology stack including the Elastic Stack, ZEEK, Osquery, Kafka, and GeoLocation data. By integrating supervised machine learning models trained on the UNSW-NB15 dataset, we evaluate Random Forest (RF), Decision Trees (DT), and Support Vector Machines (SVM), with the Random Forest classifier achieving a notable accuracy of 99.32%. Leveraging Artificial Intelligence and Natural Language Processing, we apply the BERT model with a Byte-level Byte-pair tokenizer to enhance network-based attack detection in IoT systems. Experiments on UNSW-NB15, TON-IoT, and Edge-IIoT datasets demonstrate our platform’s superiority over traditional methods in multi-class classification tasks, achieving near-perfect accuracy on the Edge-IIoT dataset. Furthermore, Network Security Traffic Analysis Platform’s ability to produce actionable insights through charts, tables, histograms, and other visualizations underscores its capability in static analysis of traffic data. This dual approach of real-time and static analysis provides a robust foundation for developing scalable, efficient, and automated security solutions, essential for managing the evolving threats in modern networks. Full article

Emulsified asphalt is widely used for pavement maintenance due to its ease of application. However, its use is limited by poor high-temperature stability and low bonding strength. This study attempted to prepare a self-crosslinking waterborne acrylate (SWA)-type admixture using a diacetone acrylamide (DAAM)-adipic dihydrazide (ADH) crosslinking system and applied it to emulsified asphalt to ultimately obtain self-crosslinking waterborne acrylate-modified emulsified asphalt (AMEA). The research explored the effects of SWA on the fundamental properties, rheological characteristics, microscopic morphology, and bonding performance of AMEA. Results indicated that SWA undergoes self-crosslinking reactions during the demulsification process, forming a continuous and stable network structure that significantly enhances the strength of emulsified asphalt while improving softening point and high-temperature stability. Rheological analysis revealed that within the 10–15 phr dosage range, the influence of frequency on emulsified asphalt was minimized, with notable improvements in high-temperature elastic recovery and deformation resistance. Particularly when the dosage exceeds 10 phr, the material demonstrates adaptability to high-traffic environments. Pull-off tests demonstrated that SWA can increase the interlayer bonding strength of emulsified asphalt by over 50%. However, SWA exhibits some negative impact on the low-temperature ductility of emulsified asphalt, necessitating cautious dosage control during application. This novel self-crosslinking waterborne acrylate-modified emulsified asphalt, with its excellent bonding performance and superior high-temperature stability, emerges as a crucial material choice for pavement preventive maintenance. Full article