Publications Scientifiques
Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10
Browse
4 results
Search Results
Item Machine learning algorithms prediction of methyl orange removal by Fenton oxidation process(Springer Science and Business Media, 2025) Ouazene, Naima; Harrar, Khaled; Gharbi, Amine; Zahi, Salah Eddine; Mokrane, Said; Mokrane, HindFenton oxidation, an advanced oxidation process (AOP), effectively mineralizes azo dyes, mitigating their environmental impact. The Fenton oxidation process (Fe2⁺/H₂O₂) was employed for the degradation of methyl orange (MO) under varying operational conditions, with its efficiency assessed through chemical oxygen demand (COD) analysis. This study aims to develop predictive models for MO degradation efficiency using four machine learning (ML) algorithms: Gaussian process regression (GPR), multilayer perceptron (MLP), decision tree (DT), and support vector regression (SVR). These models were developed and validated using 42 experimental data points obtained under controlled conditions. Experimental findings revealed a 99% COD removal at an initial MO concentration of 125 mg/L, optimized at pH 3.5, [Fe2⁺] = 25 mg/L, reaction time = 90 min, and a molar ratio of [H₂O₂]/[MO] = 42.5. The predictive accuracy of the ML models was evaluated using the coefficient of determination (R2) and root mean square error (RMSE). The GPR model demonstrated the highest predictive performance (R2 = 0.970), followed by DT (R2 = 0.964). The MLP and SVM models exhibited slightly lower predictive capacities, with R2 values of 0.946 and 0.910, respectively. Feature importance analysis indicated that reaction time was the most significant parameter influencing COD removal, underscoring the necessity of its optimization in practical applications. The integration of ML-based predictive modeling with AOPs provides a robust approach for enhancing wastewater treatment efficiency. The outcomes of this study hold particular relevance for water reuse applications in arid and semiarid regions, where effective pollutant removal is critical for sustainable water resource managementItem Progressive Deep Transfer Learning for Accurate Glaucoma Detection in Medical Imaging(Institute of Electrical and Electronics Engineers, 2024) Yakoub, Assia; Gaceb, Djamel; Touazi, Fayçal; Bourahla, NourelhoudaGlaucoma leads to permanent vision disability by damaging the optic nerve, which transmits visual images to the brain. The fact that glaucoma doesn't exhibit any symptoms as it progresses and can't be halted in later stages makes early diagnosis critical. Although various deep learning models have been applied to detect glaucoma from digital fundus images, the scarcity of labeled data has limited their generalization performance, along with their high computational complexity and specialized hardware requirements. In this study, a progressive transfer learning with preprocessing techniques is proposed for the early detection of glaucoma in fundus images. The performance of this approach is compared against transfer learning and convolutional neural networks using three benchmark datasets: Cataract, Glaucoma and Origa. The experimental results demonstrate that reusing pre-trained models from ImageNet and applying them to a database containing the same disease leads to improved performance, compared to using databases with different diseases in progressive transfer learning. Additionally, applying preprocessing techniques to the databases further enhances the results.Item Application of Deep Transfer Learning in Medical Imaging for Thyroid Lesion Diagnostic Assistance(Institute of Electrical and Electronics Engineers, 2024) Chaouchi, Lynda; Gaceb, Djamel; Touazi, Fayçal; Djani, Djouher; Yakoub, AssiaThis academic work evaluates and compares the performance of various deep convolutional neural network (DCNN) architectures in classifying thyroid nodules into two categories, malignant and benign, using ultrasound images. The dataset comprises 269 cases of benign lesions and 526 cases of malignant lesions. Given the limited dataset size, we employ a progressive learning approach with three established CNN models: VGG-16, ResNet-50, and EfficientNet. Initially pretrained on ImageNet, these models undergo further fine-tuning using a radiographic image dataset related to a different medical condition but similar to our domain. Different levels and fine-tuning strategies are applied to these models. A supervised softmax classifier is used for classifying lesions as malignant or benign, with the exception of the VGG-16 model. For the VGG-16 model, two additional classifiers, Support Vector Machine (SVM) and Random Forest (RF), are evaluated. The results obtained demonstrate the possibility of easily transitioning from the classification of one disease to another, even with a limited number of images, by leveraging the knowledge already acquired from another extensive database.Item Choosing the adapted artificial intelligence method (ANN and ANFIS) based MPPT controller for thin layer PV array(Springer, 2023) Bouchetob, Elaid; Nadji, BouchraBecause of the many advantages that artificial intelligence technologies provide in comparison to more conventional methods, a rising number of solar power plants are beginning to use them in their monitoring of the MPP. When there is a sudden change in solar temperature and irradiance, it is possible that the MPP will not be tracked as accurately. As a consequence of this, these methods could make up for the deficiencies of those that are more well-established (P&O, IC, etc.). Aside from that, there is a wide range of methods to AI, each of which has a particular advantage. By making some minor adjustments to the architecture, an artificial neural network (ANN) and an adaptive neuro-fuzzy inference system (ANFIS) were used to monitor the MPP of Thin Layer panel technology at the Oued Nechou installation in Ghardaia. Each connection channel now has six panels rather than the previous maximum of 12 panels, and the junction box has 210 channels rather than the prior maximum of 105 channels. In the last step, a DC-DC boost converter is used to increase the power output voltages produced by the module