Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Search Results

Now showing 1 - 10 of 5136
  • No Thumbnail Available
    Item
    Comparative Evaluation of StyleGAN3-Based Augmentation Strategies for Enhanced Medical Image Classification
    (CEUR-WS, 2025) Touazi, Faycal; Gaceb, Djamel; Tadrist, Amira; Bakiri, Sara
    Deep learning models for medical image classification face significant challenges due to class imbalance and the limited availability of annotated datasets, particularly for rare diseases. Traditional data augmentation techniques, such as rotation, translation, etc., often fail to provide sufficient diversity to perform a good classification for minor classes. To address this issue, various strategies have been explored, including oversampling, undersampling, cost-sensitive learning, and synthetic data generation using generative adversarial networks (GANs). In this study, we evaluate the impact of using a generative AI based approaches and demonstrate that the most effective strategy is to combine synthetic augmentation with traditional methods. Specifically, we employ StyleGAN3 to generate high-fidelity synthetic images that, when integrated with traditional data-augmentation techniques, may improve the performance of deep learning models on medical image classification. We validate our method on datasets, including COVID-19 chest X-rays and HAM10000. Experimental results show that this hybrid approach leads to an improvement in classification accuracy, particularly for minority classes, surpassing standalone augmentation strategies. Our findings highlight the potential of AI-driven synthetic data generation as a complementary solution to traditional augmentation, offering a more balanced and diverse dataset for medical image analysis.
  • Thumbnail Image
    Item
    Exploring Multi-Channel GPS Receivers for Detecting Spoofing Attacks on UAVs Using Machine Learning
    (Multidisciplinary Digital Publishing Institute, 2025) Mouzai, Mustapha; Riahla, Mohamed Amine; Keziou, Amor; Fouchal, Hacène
    All current transportation systems (vehicles, trucks, planes, etc.) rely on the Global Positioning System (GPS) as their main navigation technology. GPS receivers collect signals from multiple satellites and are able to provide more or less accurate positioning. For civilian applications, GPS signals are sent without any encryption system. For this reason, they are vulnerable to various attacks, and the most prevalent one is known as GPS spoofing. The main consequence is the loss of position monitoring, which may increase damage risks in terms of crashes or hijacking. In this study, we focus on UAV (unmanned aerial vehicle) positioning attacks. We first review numerous techniques for detecting and mitigating GPS spoofing attacks, finding that various types of attacks may occur. In the literature, many studies have focused on only one type of attack. We believe that targeting the study of many attacks is crucial for developing efficient mitigation mechanisms. Thus, we have explored a well-known datasetcontaining authentic UAV signals along with spoofed signals (with three types of attacked signals). As a main contribution, we propose a more interpretable approach to exploit the dataset by extracting individual mission sequences, handling non-stationary features, and converting the GPS raw data into a simplified structured format. Then, we design tree-based machine learning algorithms, namely decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost), for the purpose of classifying signal types and to recognize spoofing attacks. Our main findings are as follows: (a) random forest has significant capability in detecting and classifying GPS spoofing attacks, outperforming the other models. (b) We have been able to detect most types of attacks and distinguish them
  • No Thumbnail Available
    Item
    Enhancing Data Privacy in Intrusion Detection: A Federated Learning Framework With Differential Privacy
    (John Wiley and Sons Ltd, 2025) Saidi, Ahmed; Khouri, A. Ouadoud
    The 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 systems
  • No Thumbnail Available
    Item
    Predicting Methane Hydrate Formation Temperature in the Presence of Diverse Brines Using Explainable Artificial Intelligence
    (American Chemical Society, 2025) Nait Amar, Menad; Zeraibi, Noureddine; Alqahtani, Fahd Mohamad; Djema, Hakim; Benamara, Chahrazed; Saifi, Redha; Gareche, Mourad; Ghasemi, Mohammad; Merzoug, Ahmed
    Thisstudy presents three advanced techniques, includingthe leastsquares support vector machine (LSSVM), categorical boosting (CatBoost),and cascaded forward neural network (CFNN), to model methane hydrateformation temperature (MHFT) across various brines under a wide pressurerange. Utilizing a comprehensive data set of nearly 1000 samples,the models underwent rigorous training and testing phases. Graphicalanalyses and statistical assessment confirmed the high accuracy ofthe implemented models, with the CFNN scheme outperforming the others,achieving a total root-mean-square error (RMSE) of 0.3569 and an R2 of 0.9977. Comparison with existing modelsfurther highlighted the CFNN model’s superior performance.Additionally, the Shapley Additive exPlanning (SHAP) method was employedto enhance the aspects related to predictions’ explainabilityby assessing the impact of different inputs on the outcomes. Lastly,the proposed model holds significant potential for advancing industrialand academic applications related to hydrate phenomena
  • Thumbnail Image
    Item
    Screening and Docking Molecular Studies of Natural Products Targeting overexpressed Receptors HER-2 in Breast Cancer
    (Razi Vaccine and Serum Research Institute, 2025) Lenchi, Nesrine; Maouche, Naima; Khemili-Talbi, Souad
    Breast cancer is the first cancer to affect a community. Because of its extremely high mitotic activity, breast cancer that tests positive for HER 2 is considered to have a poor prognosis. Due to the side effects of chemical drugs, patients are increasingly turning to natural medicine, such as phytotherapy and nutritherapy. The study uses a bioinformatics approach (molecular docking) to searchfor new, non-toxic anti-cancer inhibitors. The studyscreens 102 ligands from natural and dietary compounds that are likely to interact with the HER-2. The virtual screening results of the allow us to select the 23 best compounds which can be proposed as the most effective HER-2 inhibitors. Lycopene would be a very promising ligand which presents a DeltaG of -9.82 kcal/mol. Other promising ligands include beta-carotene (DeltaG of -8.58), P-cumaric acid kcal/mol (DeltaG of -8.57) and Curcumin (DeltaG of -8.46). Other compounds, luteolin, anacardium (Anacardic acid),and alpha-Tocopherol, were found to have the strongest inhibitory effects with DeltaG values of -7.92 kcal/mol, - 7.89 kcal/mol, and-7.85 kcal/mol, respectively. These compounds act directly on residues keys found in the hydrophobic pocket II (ATP binding site) and the hydrophobic region (the αC-β4 loop) of the EGFR domain. Pinoresinol, Kaempferol and Caffeic acid have DeltaGs of -7.48 Kcal/mol, -6.88 Kcal/mol and -6.34 kcal/mol, respectively. These three ligands are specific to the conserved regions of the HER-2 receptor and interact with the C-terminal, the C-lobe activation loop and the N-lobe P loop of the tyrosine kinase domain, respectively. Lapatinib (chemical compound) and quercetin (natural compound) have DeltaG of -7.58 kcal/mol and -7.28 kcal/mol, respectively, form a hydrogen bond with the same residue in the hydrophobic region. All the natural molecules seem very promising and, after in vitro/in vivo tests, could constitute good substitutes for the chemotherapies which are currently used to treat breast cancers as well as other cancers. Copy right
  • Thumbnail Image
    Item
    Classical and Quantum SVM for Electromyography-Based Myopathy Detection: A Comparative Exploration
    (Sciendo, 2025) Hammachi, Radhouane; Messaoudi, Noureddine; Belkacem, Samia; Pasetto, Edoardo; Delilbasic, Amer
    Introduction: Electromyography (EMG) analysis is one of the most fundamental approaches for diagnosing neuromuscular diseases. Current advancements in technology have the potential to improve diagnosis accuracy using artificial intelligence (AI). Quantum machine learning (QML), while still in its early stages, offers promising potential for various medical applications, but its effectiveness in real-world diagnostic tasks needs further exploration. Thus, the aim of this study is to employ both quantum and classical support vector machines (SVMs) to classify EMG signals into two classes, healthy and myopathy, and compare their performance. Methods: Various approaches were tested; classical SVM and quantum-kernel-based SVM, both with manually extracted features, and convolutional neural network (CNN)-based deep features extraction techniques. This allows for an evaluation of the strengths and limitations of this new technology, acknowledging the potential of both classical and quantum methods. Results: The obtained results showed that the proposed quantum methods yielded promising outcomes and comparable to classical methods. Particularly, the competitive results of the quantum SVM (QSVM) with the CNN-based deep feature extraction approach, which delivered a high training and testing accuracies of up to 96.7% and 85.1%, respectively. Conclusion: These findings encourages the necessity for more advanced QML research, particularly in medical applications as quantum technology progresses
  • No Thumbnail Available
    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, Alper
    Sustainable 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 priorities
  • No Thumbnail Available
    Item
    Improving the Detection Quality of the Clutter Map-Constant False Alarm Rate Detector in a Non-Homogeneous Environment
    (Springer Nature, 2025) Rouabah, Abdellatif; Hamadouche, M.’hamed; Teguig, Djamal; Zeraoula, Hamza; Imessaoudene, Amira; Boughambouz, and Abdenacer
    This paper concerns the proposal of two innovative techniques for a clutter map-constant false alarm rate (CM-CFAR) detector. These techniques are called, respectively, adaptive linear combined-CM-CFAR (ALC-CM-CFAR), which operates without requiring any prior environmental knowledge, and knowledge-based systems ALC-CM-CFAR (KBSALC-CM-CFAR) that requires a previous environmental knowledge. The first technique, ALC-CM-CFAR, combines the performance of both detectors, cell averaging-CM-CFAR (CA-CM-CFAR) and ordered statistics-CM-CFAR (OS-CM-CFAR). In contrast, the second one, KBSALC-CM-CFAR, exploits the prior knowledge about the environment, KBS, considering both the Geographic Information System (GIS) and Kolmogorov–Smirnov (K–S) test as a knowledge source on the one hand, and the other hand, merging detection capabilities of CA-CM-CFAR and OS-CM-CFAR to build a robust detection system. This innovative approach aims to enhance the Nitzberg detector’s performance in detecting targets with low speeds and weak radar cross sections (RCS) across various environmental conditions. The performance of the proposed techniques was evaluated using Monte Carlo simulation using MATLAB software (MATLAB 8.6 R2015b). The results of the simulation reveal that the KBSALC-CM-CFAR surpasses all classical CM techniques; CA-CM-CFAR, OS-CM-CFAR, hybrid CM/L-CFAR, and CM/ordered data variability (ODV)-CFAR in terms of increasing the probability of detection (Pd) in different environment situations, especially in cases of non-homogeneity caused by interferences, slow, and weak RCS targets that persist in a cell map for several scans causing self-masking effect. The CM-CFAR technique was implemented on the field-programmable gate array (FPGA) processing board, and the process is run at a clock frequency of 50 MHz (execution time: 20 ns). After the simulation and execution of the algorithm, the execution time was evaluated at 5.636 ns. This is less than the running time of the FPGA board clock, which is equal to 20 ns, so processing takes place in real time. The consumption of hardware resources by the CM-CFAR algorithm is more than sufficient for implementation on the chosen FPGA (between 0.12 and 19.68%).
  • No Thumbnail Available
    Item
    Chemical composition, antimicrobial and insecticidal activities of Olea europaea L. ssp. sativa. collected from East of Algeria
    (Springer, 2025) Brahmi, Fairouz; Benlefki, Nawal; Koullal, Radwa; Kebbouche-Gana, Salima; Lenchi, Nesrine
    Olea europaea L., commonly known as the olive tree, is extensively utilized in Algeria for its medicinal properties. This plant is rich in alkaloids, phenolic acids, and flavonoids. The aim of this study was to evaluate the antimicrobial and insecticidal activities of methanol extracts and oils harvested from the aerial parts of Olea europaea L. ssp. sativa from two different regions (Bouira and Bordj Bouarreridj). Adult aphids (Aphis fabae) treated with crude methanol extracts exhibited high mortality rates, reaching up to 100%, while diluted extracts caused mortality rates between 80 and 100%. In terms of antimicrobial activity, all tested strains exhibited resistance (including E. coli, B. subtilis, S. aureus, K. pneumoniae, S. agalactiae, and C. albicans) for all methanol extracts and both oils. However, significant inhibition percentages were noted against the fungus Cladosporium sp. across the various tested extracts. These extracts have the potential to be used in the food, pharmaceutical and agricultural industries
  • Thumbnail Image
    Item
    Comparative Study of Opuntia ficus-indica Polymers, HPAM, and Their Mixture for Enhanced Oil Recovery in the Hassi Messaoud Reservoir, Algeria
    (Multidisciplinary Digital Publishing Institute, 2025) Bourkaib, Kamila; Elamri, Adel; Hadjsadok, Abdelkader; Izountar, Charaf Eddine; Abimouloud, Mohamed Fouad; Bouhafs, Amin; Isseri, Ammar; Maatalah, Djamila; Braik, Meriem; Guezei, Abdelali
    This study explores the potential of biopolymers as sustainable alternatives to synthetic polymers in enhanced oil recovery (EOR), aiming to reduce reliance on partially hydrolyzed polyacrylamides (HPAM). Mucilage extracted from Opuntia ficus-indica cladodes was investigated individually and in combination with HPAM in an 80/20 blend. The objective was to evaluate the physicochemical and rheological properties of these formulations, and their efficiency in improving oil recovery under realistic reservoir conditions. The materials were characterized using thermogravimetric analysis (TGA), X-ray diffraction (XRD), scanning electron microscopy (SEM), and Fourier-transform infrared spectroscopy (FTIR). Rheological tests showed that both Opuntia mucilage and the HPAM–mucilage blend displayed favorable viscoelastic behavior in saline environments (2% NaCl) at high concentrations (10,000 ppm). The mucilage also exhibited thermal stability above 200 °C, making it suitable for harsh reservoir conditions. Core flooding experiments conducted at 120 °C using core plugs from Algerian reservoirs revealed enhanced oil recovery performance. The recovery factors were 63.3% for HPAM, 84.35% for Opuntia mucilage, and 94.28% for the HPAM–mucilage blend. These results highlight not only the synergistic effect of the blend but also the standalone efficiency of the natural biopolymer in improving oil mobility and pore permeability. This study confirms the viability of using locally sourced biopolymers in EOR strategies. Opuntia ficus-indica mucilage offers a cost-effective, eco-friendly, and thermally stable alternative to conventional polymers for enhanced oil recovery, particularly in saline and high-temperature reservoirs such as Hassi Messaoud in Algeria