Objectives: Traffic accidents cause severe social and economic impacts, demanding fast and reliable detection to minimize secondary collisions and improve emergency response. However, existing cloud-dependent detection systems often suffer from high latency and limited scalability, motivating the need for an edge-centric and consensus-free accident detection framework in IoV environments. 

Methods: This study presents a real-time accident detection framework tailored for Internet of Vehicles (IoV) environments. The proposed system forms an integrated IoV architecture combining on-vehicle inference, RSU-based validation, and asynchronous cloud reporting. The system integrates a lightweight ensemble of Vision Transformer (ViT) and EfficientNet models deployed on vehicle nodes to classify video frames. Accident alerts are generated only when both models agree (vehicle-level ensemble consensus), ensuring high precision. These alerts are transmitted to nearby Road Side Units (RSUs), which validate the events and broadcast safety messages without requiring inter-vehicle or inter-RSU consensus. Structured reports are also forwarded asynchronously to the cloud for long-term model retraining and risk analysis. 

Results: Evaluated on the CarCrash and CADP datasets, the framework achieves an F1-score of 0.96 with average decision latency below 60 ms, corresponding to an overall accuracy of 98.65% and demonstrating measurable improvement over single-model baselines. 

Conclusions: By combining on-vehicle inference, edge-based validation, and optional cloud integration, the proposed architecture offers both immediate responsiveness and adaptability, contrasting with traditional cloud-dependent approaches.

Low-latency content delivery is essential in the Internet of Vehicles (IoV) to support autonomous driving, cooperative perception, and infotainment services. However, rapidly changing vehicular mobility and demand patterns limit the effectiveness of existing content prediction and caching strategies, which often capture either short-term temporal trends or long-range dependencies, but not both. This paper proposes a hybrid deep learning architecture that integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to jointly model fine-grained temporal dynamics and global correlations in content requests. The resulting popularity predictions are incorporated into a reinforcement learning (RL)-based caching policy, enabling proactive and adaptive cache placement at roadside units (RSUs) within an end-to-end optimization framework. Simulation results across representative IoV scenarios show that the proposed approach consistently improves cache hit ratio, retrieval latency, and prediction accuracy compared with LSTM-only, Transformer-only, Least Frequently Used (LFU), and Least Recently Used (LRU) baselines. Ablation studies further demonstrate the complementary strengths of the hybrid components, highlighting improved convergence behavior and robustness under varying demand distributions.

first_page

settings

Order Article Reprints

Sétif City, located in the Eastern High-lands of Algeria, faces a resurgence of urban flooding, a phenomenon exacerbated by the soil sealing resulting from rapid urbanization (+351.67% between 1986 and 2021) and the under-sizing of drainage infrastructure. In the context of a lack of integrated spatial assessment tools, this study aims to evaluate and map the flood vulnerability of the urban area by coupling Geographic Information Systems (GIS) and the Analytical Hierarchy Process (AHP). The methodology integrated seven vulnerability criteria (five physicals and two socio-economic), whose AHP-based weighting was judged reliable (Consistency Ratio: 6.4%). The results reveal that 45.65% of Sétif’s urban area (339.22 hectares) exhibits high to very high vulnerability. The AHP analysis identified slope (33.7% of the weight) and land use (29.1% of the weight) as the major determinants of this vulnerability. Critical areas, notably Ararsa, Yahyaoui, and Aïn Sebaâ districts, are characterized by the combination of gentle slopes and a high density of infrastructure. This work confirms the relevance of the AHP-GIS coupling in providing local authorities with an essential decision support tool for the revision of the Master Plan for Development and Urban Planning (PDAU) and for more resilient urban planning.

This work aims to improve the performance of electric vehicles (EVs) based on linear induction mo tors (LIM). The Particle Swarm Optimization (PSO) method is proposed to tune the PID regulator of the Field-Oriented Control (FOC) technique. The main objective of this study is to develop innovative solutions that maximize the efficiency and precision of electric vehicles on various paths. The LIM model is imple mented using the d-q synchronous reference frame and takes into account the end-effect phenomenon. This phenomenon occurs due to the termination of the mo tor’s physical structure, which leads to distortion in the magnetic field at the ends of the motor’s primary (sta tor). It is also highly nonlinear, which increases its complexity and makes control difficult. To overcome this issue, the Field-Oriented Control (FOC) technique is suggested to achieve better efficiency, dynamic per formance, and greater control flexibility of the motor. Furthermore, the use of the (PSO) optimization tech nique enables the determination of optimal control pa rameters to maximize the performance of the (FOC LIM) system under different operating conditions, such as speed variation and disturbance load. A compari son between the PSO-PID and conventional methods in terms of response stability, steady-state error, and rise time is conducted using MATLAB/Simulink. The results demonstrate a more efficient, precise, and high performing electric vehicle system.

This work aims to improve the performance of electric vehicles (EVs) based on linear induction mo tors (LIM). The Particle Swarm Optimization (PSO) method is proposed to tune the PID regulator of the Field-Oriented Control (FOC) technique. The main objective of this study is to develop innovative solutions that maximize the efficiency and precision of electric vehicles on various paths. The LIM model is imple mented using the d-q synchronous reference frame and takes into account the end-effect phenomenon. This phenomenon occurs due to the termination of the mo tor’s physical structure, which leads to distortion in the magnetic field at the ends of the motor’s primary (sta tor). It is also highly nonlinear, which increases its complexity and makes control difficult. To overcome this issue, the Field-Oriented Control (FOC) technique is suggested to achieve better efficiency, dynamic per formance, and greater control flexibility of the motor. Furthermore, the use of the (PSO) optimization tech nique enables the determination of optimal control pa rameters to maximize the performance of the (FOC LIM) system under different operating conditions, such as speed variation and disturbance load. A compari son between the PSO-PID and conventional methods in terms of response stability, steady-state error, and rise time is conducted using MATLAB/Simulink. The results demonstrate a more efficient, precise, and high performing electric vehicle system.

This work aims to improve the performance of electric vehicles (EVs) based on linear induction mo tors (LIM). The Particle Swarm Optimization (PSO) method is proposed to tune the PID regulator of the Field-Oriented Control (FOC) technique. The main objective of this study is to develop innovative solutions that maximize the efficiency and precision of electric vehicles on various paths. The LIM model is imple mented using the d-q synchronous reference frame and takes into account the end-effect phenomenon. This phenomenon occurs due to the termination of the mo tor’s physical structure, which leads to distortion in the magnetic field at the ends of the motor’s primary (sta tor). It is also highly nonlinear, which increases its complexity and makes control difficult. To overcome this issue, the Field-Oriented Control (FOC) technique is suggested to achieve better efficiency, dynamic per formance, and greater control flexibility of the motor. Furthermore, the use of the (PSO) optimization tech nique enables the determination of optimal control pa rameters to maximize the performance of the (FOC LIM) system under different operating conditions, such as speed variation and disturbance load. A compari son between the PSO-PID and conventional methods in terms of response stability, steady-state error, and rise time is conducted using MATLAB/Simulink. The results demonstrate a more efficient, precise, and high performing electric vehicle system.

Mobile Wireless Sensor Networks (MWSNs) enhance traditional wireless sensor networks by allowing sensor nodes to move, resulting in continuously changing network topologies. Although this mobility enables advanced applications such as disaster response, intelligent transportation systems, and mission-critical monitoring, it poses major challenges for secure and scalable key management in large-scale deployments. Most existing key management and key pre-distribution schemes are tailored to static or lightly mobile networks and therefore suffer from limited scalability, excessive memory consumption, inefficient key utilization, and increased vulnerability to node capture when applied to highly mobile environments. This paper proposes a mobility-aware, zone-based key management scheme that integrates an enhanced composite key distribution mechanism with dynamic key refinement. The network is partitioned into logical zones, each maintaining an independent key pool to confine security breaches and improve scalability. To adapt to mobility-induced topology changes, sensor nodes continuously refine their key rings by preserving only the cryptographic keys associated with persistent neighbor relationships. This selective retention strategy significantly reduces storage overhead while strengthening resilience against key compromise and unauthorized access. Comprehensive analytical modeling and performance evaluations demonstrate that the proposed scheme achieves higher secure connectivity, stronger resistance to node capture attacks, and improved scalability compared to existing approaches, particularly in dense and highly mobile MWSN scenarios.

Quantum Key Agreement (QKA) is a cornerstone of quantum cryptography, facilitating secure key distribution among multiple participants. Existing QKA protocols often suffer from scalability issues and increased computational complexity as the number of participants grows. This paper proposes an efficient Circle Multiparty Quantum Key Agreement (CMQKA) protocol based on the BB84 protocol. This protocol enhances quantum resource efficiency and ensures equal participation in a circular topology. The key feature lies in the optimized use of quantum resources, minimizing the qubit overhead while ensuring high security standards. By achieving a qubit efficiency of 1/2n, it significantly improves the multiparty quantum communications. A thorough security analysis is conducted to demonstrate the protocol’s resilience against common quantum threats.

This study investigates the integrated planning of production, maintenance, and quality control in a hybrid manufacturing-remanufacturing system, accounting for deterioration, variability in the quality of returned products, carbon emissions, and outsourcing opportunities. The network consists of a manufacturer collaborating with an outsourcing remanufacturing provider. The manufacturer operates a single failure-prone machine to produce new products and to remanufacture returned ones. Recovered products that the manufacturer cannot process are sent to the outsourcing provider for remanufacturing. The system generates harmful emissions, potentially leading to environmental taxes and sanctions. We formulate a mixed-integer nonlinear programming model to determine the optimal integrated manufacturing, remanufacturing, outsourcing, and preventive maintenance plan. Eventually, the proposed strategy minimizes total economic costs and defects and ultimately reduces carbon emissions. We use a global solver for solving small instances, while a genetic algorithm metaheuristic is developed for larger ones. Extensive computational experiments reveal that the developed genetic algorithm is highly efficient, achieving gaps of less than 0.95% within shorter execution times for small instances and significantly outperforming the solver in larger ones. The results show that the integrated outsourcing strategy, combined with accounting for carbon emissions from both new and remanufactured products, significantly reduces the reliance on new products, leading to notable cost savings and environmental benefits. These savings become more pronounced as the number of returns increases.

This article focuses on improving fault tolerance and optimizing energy consumption in the context of a mining prospection mission conducted by a swarm of autonomous robots. Two major contributions are proposed. The first aims to reduce communication between robots in order to increase the system’s robustness in the presence of failures. The second focuses on minimizing the trajectory of a deminer robot to reduce overall energy consumption. To address these goals, two reinforcement learning based algorithms are proposed: Deep Q-Network (DQN) and Federated Reinforcement Learning (FRL), both derived from the Q-learning algorithm. Simulation results examining the impact of the exploration rate α on the number of detected mines show that, with 10 autonomous robots of the same architecture and 30 randomly placed mines over 30 experiments, the FRL algorithm provides better fault tolerance and ensures that the main prospection mission is accomplished even in the presence of some robotic failures or errors. Furthermore, a second series of 60 experiments involving the integration of the deminer robot, focused on optimizing energy consumption, demonstrates that the DQN algorithm is more effective in reducing energy usage, due to improved a better optimization of unnecessary deminer movements, while successfully resolving deadlock situations that the latter may encounter. These findings open the door to the development of a hybrid algorithm combining the strengths of DQN and FRL to ensure both system robustness and minimal energy consumption.

Designing scalable and interpretable control strategies for decentralized multi-agent systems remains a challenge in reinforcement learning (RL). This challenge is particularly evident in pursuit–evasion tasks, which require coordination under partial observability, without explicit communication or centralized guidance. Although deep RL methods achieve strong performance, they typically operate as black boxes, limiting trust and deployment in safety-critical domains. We propose a Multi-Head DDPG architecture that decomposes control into three interpretable force components - pursuit, cohesion, and separation - weighted adaptively to generate context-aware actions. This design enables emergent role differentiation and interpretable self-organization in the model. In grid-based pursuit–evasion benchmarks, our method outperforms DQN, PPO, and standard DDPG in terms of success rate, convergence speed, and generalization, while also yielding transparent collective behaviors. Overall, the results show that weighted force-based behavioral decomposition provides a principled pathway toward achieving both high-performance and explainable multi-agent control.

In this study, a numerical investigation was conducted on the seismic behavior of low-strength reinforced concrete columns, strengthened with steel bars and wrapped with fiberglass tapes and fabrics, using finite element software. The columns were subjected to both monotonic and cyclic loading, and the analysis focused on fracture patterns, failure mechanisms, lateral hysteresis loops, ductility degradation, and stiffness degradation. The results showed that the reference column exhibited brittle shear failure and insufficient ductility. In contrast, the second column, reinforced with steel bars and partially wrapped with fiberglass tapes, demonstrated 30% higher tensile strength compared to the reference column, achieving stable hysteresis loops, improved energy dissipation, and 25% less cracking. The third column, fully wrapped with fiberglass fabric in addition to the steel bars, exhibited 50% higher tensile strength and 75% reduced probability of cracking in the plastic hinge area. These findings underscore the effectiveness of advanced reinforcement techniques in improving the seismic performance of reinforced concrete columns.

The automated inspection of complex freeform components, such as helical gears, is a persistent challenge in advanced manufacturing due to their intricate geometries and strict precision requirements. Conventional inspection methods, such as those using coordinate measuring machines or optical techniques, are often time-consuming and lack adaptability to subtle deviations. Recent deep learning approaches show promise but are typically limited to point-based or scan-to-scan comparisons, which remain sensitive to noise and alignment errors. We propose a voxel-based 3D inspection framework that integrates an XGBoost-guided perturbation model with a 3D convolutional autoencoder (3D CNN-AE). CAD-derived gear models are systematically perturbed with controlled Gaussian deformations to emulate tolerances, defects, and sensor noise, then voxelized for autoencoder training. This enables robust learning of nominal gear geometry distributions. Extensive experiments conducted against PointNet++, a Variational Autoencoder, and a GAN-based reconstruction model demonstrate that our method consistently achieves superior performance across various metrics, including PSNR, SSIM, accuracy, precision, recall, and F1-score. The results highlight the potential of voxel-based learning with data-driven perturbation for scalable and high-accuracy inspection in industrial applications.

Oil well drilling is an expensive process that needs a particular focus. For this reason, Rate Of Penetration (ROP) has been widely approved as a measure of drilling efficiency and adequate configuration parameters. Our aim in this work consists in the elaboration of a smart system using Hoeffding trees for predicting the Rate of Penetration (ROP) in oilfield drilling. The choice of Hoeffding trees to build our model is motivated by their adaptive learning capability and drift detection. They offer continuous, fast, and efficient learning both online on data streams and offline on batch data. To validate our approach, we used real drilling data from the “Hassi-Terfa” oilfield located in Southeast Algeria. The obtained results show in comparison to the eXtreme Gradient Boosting (XGBoost) algorithm that Hoeffding trees maintain their learning capacity and produce more accurate predictions even in the presence of drifts. This is thanks to the combination of the Adaptive Windowing (ADWIN) algorithm to manage drifts and least mean squares (LMS) filters to reduce noise. This observation highlights the effectiveness of our approach to predict the ROP while oil-well drilling. The proposed smart system offers more efficient solution to predict the ROP, whether in real-time or offline. By leveraging its adaptability to changes in data distribution, our approach ensures more accurate and adaptive predictions, facilitating drilling operations optimization and boosting the overall efficiency of the process.

Wild chicory, or Hyoseris radiata L., is indigenous to the Mediterranean region, is a plant used in traditional medicine as a diuretic, blood depurative, and against kidney stones. The present study aimed to assess for the first time the acute and subacute toxicity, to quantify the total amount of polyphenols and flavonoids, and to assess the antioxidant activity of H. radiata collected from Setif, Algeria. The overall amount of flavonoids and polyphenols was quantified spectrophotometrically. The antioxidant activity of the extract was evaluated according to two methods, DPPH and FRAP. The acute toxicity of H. radiata was carried out according to the OECD guideline 423 to determine the median lethal dose LD50 and the subacute toxicity was evaluated according to OECD guideline 407 to assess the possible pathological effects of the extract administered for 28 days by oral route. The results show that the total amount of polyphenols and flavonoids was 132.53 ± 2 µg of GAE·1 mg-1 and 96.11 ± 3.65 µg of QE·1 mg-1 of extract, respectively. The extract shows a good antioxidant potential in both tests. The administered dose (2 g·kg-1 of BW) didn’t produce any changes in general behaviors or mortality, so the LD50 is greater than 2 g·kg-1 of BW. Moreover, the daily administration of the extract with 2 doses, 100 mg·kg-1 and 200 mg·kg-1 didn’t cause any changes in body weight, behavior test, hematological parameters, and organ relative weight. A significant decrease in triglyceride was recorded in both concentrations. Based on the present findings, the extract of H. radiata has no significant toxicity. These findings offer valuable information about the toxicity profile of the traditional medicine plant Hyoseris radiata L.

تتناول هذه الدراسة تدريب القوة العضلية في حالتي التقلص المركزي والتقلص اللامركزي، وتأثيرهما على كمية كريات الدم البيضاء والتغيرات التي تحدث فيها، بغية معرفة مدى تأثير كل نمط تدريب على هذا المكون الدموي، وإن كان الكريات البيض تعد مبينا لما يحدث على مستوى النسيج العضلي المتعرض لتدريب القوة العضلية في هاذين النمطين، وذلك لدى عينة قصدية من نخبة رياضة الجودو قوامها 10 رياضيين مقسمين إلى مجموعتين، مجموعة معنية بالتقلص المركزي والأخرى بالتقلص اللامركزي، واعتمدنا على الاختبارات البدنية (1RM) لتقنين الأحمال حسب متطلبات الطريقة المستخدمة في الحصة التجريبية (10×10)، وعلى التحليلات الدموية في 3 مراحل (قبلي، بعدي، تتبعي). وبعد جمع البيانات ومعالجتها إحصائيا تم تأكيد الفرضية القائلة بأن تأثير الحصة التدريبية للقوة العضلية المقترحة يختلف بشكل كبير حسب حالات التقلص العضلي (المركزي، اللامركزي)، وخلصنا إلى أن تدريب القوة العضلية يختلف تأثيره على كريات الدم البيضاء حسب نوع التقلص العضلي، وأن النمط اللامركزي يتميز بإحداث تلف كبير على مستوى النسيج العضلي وفترة استشفاءه كبيرة لكن نتائجه أفضل، مقارنة بالنمط المركزي. الكلمات المفتاحية: التدريب الرياضي؛ القوة العضلية؛ التقلص المركزي؛ التقلص اللامركزي؛ كريات الدم البيضاء؛ تلف الخلايا العضلية.

Thermal runaway of a chemical process is a dangerous phenomenon that threatens human life, equipment, installations, and the environment. The aim of our work is to propose a methodology for analyzing and quantitatively assessing the risk of thermal runaway in a polymerization reactor. Firstly, HAZard and OPerability analysis(HAZOP)is used to determine the most critical deviations likely to occur in the polymerization reactor under study and leading to the thermal runaway phenomenon. The various accident sequences are determined and evaluated using event tree analysis (ETA). The causes of the failure of safety barriers implemented in the reactor to prevent the runaway phenomenon are determined using fault tree analysis (FTA). Finally, an economic analysis is carried out to show the economic impact of safety failure barriers on the company. Application resultsof the proposed methodology show its relevance as a decision-making tool for good industrial risk management. The novelty of this hybrid approach lies in its systematic workflow. Qualitative identification (HAZOP) directly informs quantitative frequency estimation (ETA), which in turn relies on detailed reliability analysis (FTA) to assess safety barrier performance. This integrated methodology not only provides a quantitative risk frequency but also identifies the most critical safety barriers and offers an economic rationale for investment decisions through cost-benefit analysis (CBA), thereby bridging the gap between technical risk assessment and managerial decision-making

This paper presents ELAREES, a task scheduling algorithm for heterogeneous multiprocessor real-time systems, designed to optimize energy savings while enhancing fault tolerance. ELAREES addresses the dual challenges of fault tolerance in task execution and communication reliability between tasks, alongside efficient power management. The algorithm employs a primary/backup strategy, assigning each task a primary execution on a low-power (LP) core and a backup on a high-performance (HP) core to ensure resilience against execution faults. Furthermore, ELAREES integrates a robust communication protocol that monitors data transmission over shared media connection buses, dynamically selecting optimal transmission paths and initiating retransmissions when necessary to mitigate communication errors. By leveraging Dynamic Voltage and Frequency Scaling (DVFS) and Dynamic Power Management (DPM) techniques, ELAREES achieves significant power savings while maintaining high system reliability. Simulation results demonstrate consistent power savings of approximately 30% across various scenarios, with only a minimal impact of 0.02% on reliability. This research contributes to the field of energy-efficient computing in real-time systems, offering a comprehensive solution for managing the trade-offs between energy consumption, execution fault tolerance, and communication reliability in heterogeneous multicore environments.