Publications Internationales
Permanent URI for this collectionhttps://dspace.univ-boumerdes.dz/handle/123456789/13
Browse
3162 results
Search Results
Item Incremental fuzzy with PSO optimization for improving the pressure stability of hydrogen and oxygen recovery 5 kW PEM fuel cell system under variable load conditions(Elsevier, 2025) Kabache, Sabah; Reguieg, Djelloul; Essaid Bousbiat; Kendil, DjamelThe longevity and efficiency of the proton exchange membrane fuel cell (PEMFC) is related to the stability of the hydrogen (H2) and Oxygen (O2) pressures within. Variations in these pressures may cause detrimental me- chanical limitations. Controlling the difference between the pressures is essential to preventing reactant insuf- ficiency or fuel waste. Conventional control techniques like PID controller often struggle with dynamic system variations and load fluctuations. This paper introduces two advanced control strategies to enhance pressure stability: an improved incremental fuzzy logic controller (IFLC) utilizing a (7 × 7) membership function scaling and a PID controller optimized by particle swarm optimization (PSO). Unlike previous studies that focused on smaller PEMFC systems (3 kW and 500 W) and relied primarily on conventional PID controllers, this work evaluates a larger 5-kW PEMFC system, providing a more comprehensive assessment of H2/O2 pressures regulation. Simulation results, conducted in MATLAB/Simulink, demonstrate that the IFLC and PSO-optimized PID significantly enhance H2/O2 pressures stability under varying load demands. The IFLC, in particular, ach- ieves superior robustness, quick response time, and zero overshoot, minimizing performance indices such as integral absolute error (IAE) (0.0067, 0.0165), integral square error (ISE) (0.0016, 0.0035), mean absolute error (MAE) (0.0007, 0.002). These results confirm the effectiveness of the IFLC in ensuring long-term PEMFC reli- ability and efficiency.Item Tourism Investment in Algeria: Bridging the Gap Between Potential and Performance in the SDAT 2030 Framework(Université de Bordj Bou Arréridj, 2025) Badreddine, Amina; Telkhoukh, SaidaThis study focuses on tourism investment environment in Algeria and its potential to drive economic diversification beyond hydrocarbon reliance. The study used a mixed methodology, reviewing the official tourism statistics (2018-2025) and legislative frameworks and the Tourism Development Master Plan (SDAT 2030) to evaluate the current performance in relation to the strategic goals. Even with recent legislative changes under the 2022 Investment Law and the ambitious target of reaching 12 million visitors annually rather than 2.5 million by 2030, research indicates that there are still ingrained issues: tourism has become a mere contributor to GDP at 1.47% in 2023 compared to the Mediterranean average of 10%, accommodation facilities are critically inadequate at 0.1 hotel rooms per 100 inhabitants and 66% of registered tourism projects are either not started or uncommented. The study concludes that although Algeria holds considerable comparative advantages in desert, coastal and heritage tourism, the opportunities in the country could only be actualised by overcoming the shortcomings in infrastructure, institutional coordination and international marketing.Item Enhancing sustainability in CNC turning of POM-C polymer using MQL with vegetable-based lubricant: machine learning and metaheuristic optimization approaches(Springer Science and Business Media, 2025) Hakmi, Tallal; Abderazek, Hammoudi; Yapan, Yusuf Furkan; Hamdi, Amine; Uysal, AlperSustainable machining of polymer parts, which is still less advanced than metal machining, aims not only to improve machinability but also to address environmental and economic challenges. Therefore, this study analyzes the sustainability of polyoxymethylene copolymer (POM-C) turning by incorporating minimum quantity lubrication (MQL) parameters (Q: flow rate, θ: nozzle angle, and d: nozzle distance) and conventional cutting parameters (Vc: cutting speed, f: feed, and ap: depth of cut), while replacing conventional oil with a biodegradable and environmentally friendly lubricant derived from Eraoil KT/2000. Additionally, the methodology relies on sustainability indicators such as surface roughness (Ra), total energy consumption (Etotal), total carbon emissions (CEtotal), and overall cost (Ctotal). To achieve this, several approaches are employed, including analysis of variance (ANOVA), artificial neural networks (ANN), k-fold cross-validation (k-fold CV), and two multi-objective metaheuristic optimization algorithms, namely SHAMODE (success history-based multi-objective adaptive differential evolution) and RPBILDE (real-code population-based incremental learning and differential evolution), are used to identify significant factors, establish mathematical models, and determine optimal conditions. The multi-objective optimization highlights trade-offs between the four sustainability criteria. Thus, a low feed value and a low MQL flow rate, combined with significant angle and distance, as well as moderate cutting speed and depth of cut, provide minimal surface roughness (Ra = 1008 µm), low energy consumption (Etotal = 0.0947 MJ), low carbon emissions (CEtotal = 0.0583 kgCO₂) but with a slightly higher cost (Ctotal = 1701 $). These results confirm a Pareto front where the improvement of one criterion negatively impacts another, guiding industrial decisions based on prioritiesItem A Comprehensive Review of Pesticide Elimination Methods from Fruits and Vegetables Over the Past Two Decades: Optimizing Produce Safety for Sustainable Food Systems(Research Institute of Food Science and Technology, 2025) Meghlaoui, Zoubeida; Remini, Hocine; Remini-Sahraoui, Yasmine; Mellal, Mohamed Khalil; Boudalia, Sofiane; Brahimi, Yasmine; Negrichi, Samira; Allam, Ayoub; Medouni-Haroune, Lamia; Messaoudene, LyndaThe increasing use of pesticides in agriculture, valued at approximately 43.2 billion USD, has raised significant concerns regarding food safety and human health. This study reviews the effectiveness of various pesticide residue removal methods applied to fruits and vegetables (F & V). A total of 57 studies published between 2005 and 2022 were analyzed, categorizing the methods into 28 household techniques, 19 advanced methods, and 10 combined approaches. Household methods, such as washing under running water, achieved removal rates of up to 90%, while peeling ensured complete (100%) elimination of residues. The addition of salt or vinegar solutions improved removal efficiency, reaching 92%. Advanced methods, notably ozonation, demonstrated high efficacy with up to 95% removal. The most effective approaches were combined techniques, integrating washing, ultrasound, and ozonation, which achieved residue elimination rates of up to 99%. Despite their efficiency, advanced methods face limitations due to high costs and technological constraints, reducing their accessibility for widespread use. This review underscores the necessity of an integrated approach to enhance food safety. Additionally, it highlights the need for further research on the long-term impact of these removal methods on the nutritional quality of F & V. These findings provide essential insights for consumers, farmers, and the food industry, contributing to the development of more effective and practical food safety strategiesItem Environmental Impacts and Behavioral Adaptations of Honeybees in Algeria: A Review of Apis mellifera intermissa and Apis mellifera sahariensis Characteristics(Multidisciplinary Digital Publishing Institute, 2025) Haider, Yamina; Adjlane, Noureddine; Haddad, NizarHoneybees are vital for pollination and the overall health of ecosystems. Since the 18th century, the intricate biology of honeybees has been a subject of scientific inquiry. Understanding their biological and behavioral characteristics is essential for effective beekeeping, honey production, and ecosystem sustainability. This review examines the environmental impact and management practices on the health of local honeybees in Algeria, focusing on Apis mellifera intermissa and Apis mellifera sahariensis. We summarize research findings on genetic diversity, morphometric traits, behavioral characteristics, and adaptation of local honeybees. Additionally, we discuss the threats posed by abiotic and biotic stressors and highlight the importance of conservation and sustainable management. The reviewed studies indicate that environmental factors significantly influence the behavioral characteristics and adaptation of local honeybees. Notably, the hygienic behavior of A. m. intermissa contributes to their resistance against diseases and the Varroa destructor mite. Further research in these areas is important for enhancing our understanding of honeybee health and population dynamics in Algeria, thereby informing strategies for sustainable beekeeping practicesItem Design and implementation of a self-driving car using deep reinforcement learning: A comprehensive study(Elsevier, 2025) Djerbi, Rachid; Rouane, Anis; Taleb, Zineb; Saradouni, SafiaThis paper presents a groundbreaking and comprehensive study on the design, implementation, and evaluation of a self-driving car utilizing deep reinforcement learning, showcasing significant advancements in autonomous vehicle technology. Our robust framework integrates three innovative AI models for essential functionalities: road detection, traffic sign recognition, and obstacle avoidance. The system architecture, structured around a three layers “DDD” (Data, Detection, Decision) approach, involves meticulous data preprocessing for traffic signs and road data, followed by specialized Deep Learning models for each detection task, including a CNN for traffic signs, a CNN for road detection, and the pre-trained MobileNet-SSD for obstacle detection. A reinforcement learning agent in the Decision Layer processes these outputs for real-time control (steering, acceleration, braking) through a continuous learning process with environmental feedback. The research encompasses both extensive simulation in Unity, leveraging the ML-Agents toolkit for agent training across diverse environments, and crucial real-world deployment. Our reward/punishment system in the simulation environment, based on collisions with road markers and obstacles, refined the agent's decision-making. The trained AI models were successfully exported and deployed onto a physical prototype, controlled by a Raspberry Pi and equipped with a camera and ultrasonic sensors. Real-world testing affirmed the robust performance of the physical model in detecting roads, recognizing traffic signs, and effectively avoiding obstacles. Quantitative results demonstrate compelling performance, including over 90% accuracy in obstacle detection and a 15% improvement in navigation efficiency compared to traditional algorithms under controlled simulation conditions. Model evaluation metrics show a 98% accuracy, 12% loss, and a prediction rate exceeding 77%. This study not only contributes a comprehensive framework for autonomous vehicle development but also highlights the transformative potential of deep reinforcement learning for creating intelligent and adaptable autonomous systems in both virtual and real-world scenarios, paving the way for safer and more efficient transportation technologiesItem Rigorous Explainable Artificial Intelligence Models for Predicting CO2-Brine Interfacial Tension: Implications for CO2 Sequestration in Saline Aquifers(American Chemical Society, 2025) Nait Amar, Menad; Youcefi, Mohamed Riad; Alqahtani, Fahd Mohamad; Djema, Hakim; Ghasemi, MohammadCarbon capture and sequestration (CCS) is an attractive approach for reducing carbon dioxide (CO2) emissions, with saline aquifers offering promising sites for long-term sequestration. Interfacial tension (IFT) between CO2 and brine plays a crucial role in the trapping efficiency. This study develops explainable artificial intelligence (XAI) models to accurately predict the IFT in CO2–brine systems. Three advanced machine learning models, namely, Super Learner (SL), Elman Neural Network (ENN), and Power Law Ensemble Model, were implemented based on a data set comprising 2616 measurements. Among the established paradigms, SL achieved the highest accuracy (RMSE = 0.7813 and R2 = 0.9953) across diverse conditions. To enhance model transparency, Local Interpretable Model-agnostic Explanations and SHAP (SHapley Additive Explanations) interpretability techniques were employed, confirming strong alignment with experimental trends. Comparative analysis further demonstrated that the SL scheme surpasses existing literature models. Overall, this study highlights the effectiveness of XAI-based predictive modeling for accurately estimating the CO2–brine IFT under diverse operational conditions. Future implementation in real CCS projects can offer valuable insights into injection strategies, trapping mechanisms, and long-term formation stabilityItem Enhancing Data Privacy in Intrusion Detection: A Federated Learning Framework With Differential Privacy(John Wiley and Son, 2025) Saidi, Ahmed; Khouri, A. OuadoudThe rise of cyber threats has underscored the critical need for robust intrusion detection systems (IDS). While traditional approaches, including statistical, knowledge-based, and AI-driven methods, have been pivotal, they often face limitations such as data privacy concerns, scalability challenges, and low detection accuracy on unfamiliar threats. This paper addresses these issues by adopting a federated learning (FL) paradigm for collaborative intrusion detection, allowing data to remain local and enhancing privacy protection. The proposed solution integrates advanced encryption techniques and differential privacy to safeguard confidentiality while ensuring system scalability and adaptability. By introducing a robust separation of agents' roles and leveraging FL's decentralized architecture, the system overcomes the limitations of centralized learning, including single points of failure and communication overhead. Experimental results validate the proposed architecture, demonstrating significant improvements in performance and offering a promising direction for modern network security. This work not only highlights the potential of FL-based IDS but also explores the integration of distributed ledger technologies to further enhance trust and security. These findings contribute to the growing field of privacy-preserving computing and lay the groundwork for future innovations in scalable, secure, and efficient intrusion detection systemsItem Adsorbents Made from Cotton Textile Waste—Application to the Removal of Tetracycline in Water(Multidisciplinary Digital Publishing Institute, 2025) Akkouche, Fadila; Madi, Katia; Aissani-Benissad, Farida; Ali, Fekri Abdulraqeb Ahmed; Assadi, Amine Aymen; Assadi, Amir Achraf; Azzaz, Ahmed Amine; Yahiaoui, IdrisThe adsorptive removal of tetracycline (TC) in aqueous solution, a widely used antibiotic, was investigated using activated carbon derived from cotton textile waste. The valorization of textile waste provides a sustainable strategy that not only reduces the growing accumulation of discarded textiles but also supports a circular economy by transforming waste into efficient adsorbent materials for the removal pharmaceutical contaminants. This dual environmental and economic benefit underscores the novelty and significance of using cotton-based activated carbons in wastewater treatment. In this study, cotton textile waste was utilized as a raw material for the preparation of adsorbents via pyrolysis under nitrogen at 600 °C followed by chemical modification with H2SO4 solutions (1, 2, and 3 M). The sulfuric-acid modified-carbons (SMCs) were characterized by BET surface area analysis, FTIR spectroscopy and SEM imaging. Batch adsorption experiments were carried out to evaluate the effects of key operational parameters including contact time, initial TC concentration and solution pH. The results showed that the material treated with 2 M H2SO4 displayed the highest adsorption performance, with a specific surface area of 700 m2/g and a pore volume of 0.352 m3/g. The pH has a great influence on TC adsorption; the adsorbed amount increases with the initial TC concentration from 5 to 100 mg/L and the maximum adsorption capacity (74.02 mg/g) is obtained at pH = 3.8. The adsorption behavior was best described by Freundlich isotherm and pseudo-second-order kinetic models. This study demonstrates that low-cost and abundantly available material, such as cotton textile waste, can be effectively repurposed effective adsorbents for the removal of pharmaceutical pollutants from aqueous mediaItem Retraction notice to "Feasibility study of a grid-connected PV/wind hybrid energy system for an urban dairy farm" [Heliyon 10 (2024) e40650](Cell Press, 2025) Bouregba, Hicham; Hachemi, Madjid; Samatar, Abdullahi Mohamed; Mekhilef, Saad; Stojcevski, Alex; Seyedmahmoudian, Mehdi; Hamidat, Abderrahmane