University of Bordj Bou Arreridj
Welcome to the Digital Repository of University Mohamed El Bachir El Ibrahimi - Bordj Bou Arreridj
Communities in University of Bordj Bou Arreridj Repository
Select a community to browse its collections.
- المكتبة المركزية
- كلية الحقوق والعلوم السياسية
- كلية الآداب واللغات
- كلية الرياضيات و الأعلام الآلي
- كلية علوم الطبيعة و الحياة و علوم الأرض و الكون
- كلية العلوم الاقتصادية والتجارية وعلوم التسيير
- Faculté des sciences et de la technologie
- كلية العلوم الاجتماعية والإنسانية
Recent Submissions
Système de détection de la somnolence basé sur l'apprentissage profond (Deep Learning
(university of bordj bou arreridj, 2026) Yahia BENTALEB; Thabet Amine SAAD SAOUD
As part of our project, we developed an intelligent system aimed at
detecting driver drowsiness in real time, in order to reduce road
accidents caused by loss of concentration while driving. This system
relies on artificial intelligence and image processing techniques to
analyze the driver’s facial features, particularly eye movements,
using a camera. The system was designed using the Python
programming language, relying on several libraries such as OpenCV
and TensorFlow, along with modern development tools and
technologies. It triggers instant (audio) alerts when the driver’s eyes
remain closed for a certain period, helping to restore attention and
prevent potential risks. The main objective of this project is to
provide a practical and effective solution that can be integrated into
modern vehicles or used as a standalone application. This solution
aims to improve road safety and reduce the number of accidents,
especially during long trips and nighttime driving. We believe that
this system represents an important step forward in the development
of intelligent driving systems and the enhancement of road safety
Une approche mobile SaaS pour la sécurisation de l'approvisionnement et de la gestion des stocks en pharmacie
(university of bordj bou arreridj, 2026) Kahia Hind; Zeguelli karima
Given the constant increase in the number of pharmacies and the growing need for efficient medication inventory management, it is no longer sufficient to rely solely on traditional methods, despite their importance. For this reason, we propose developing an intelligent mobile application aimed at individuals and small pharmacies, designed to improve stock medication management and reduce the waste of expired medicines.
The application is built on modern technologies: it allows the user to scan a barcode of medication using their phone's camera to automatically display its name and information. It also integrates an intelligent alert system that sends notifications before the expiration date, enabling the medication to be consumed in time or donated, if necessary, while also warning the user when stock is running low.
To carry out this project, we first defined its objectives and studied its feasibility, then developed a Business Model Canvas and conducted a market analysis to understand user needs and available solutions, as presented in the first chapter. Next, in the second chapter, we addressed the theoretical aspects related to inventory management and supply chain, which form the scientific foundation of the application. The third chapter was dedicated to system analysis and design, during which we designed the application interfaces using Flutter and Dart, then connected them to the Supabase database. Finally, in the fourth chapter, we presented the implementation steps and the results obtained, while demonstrating the application and explaining its key features.
Sentiment Analysis of Algerian Darija Comments on Social Media
(university of bordj bou arreridj, 2026) BAKHA Yamina; BENDJEDDOU Soumaya Amira
(NLP), especially for understanding public opinions expressed on social media.
However, Algerian Arabic remains a low-resource dialect due to the lack of annotated
corpora, linguistic tools, and standardized writing forms. This work focuses on sentiment
analysis of Algerian Darija comments collected from social media platforms,
mainly YouTube and Twitter. In this study, we built and prepared the AlgerianPulse
corpus through several stages, including data collection, cleaning, preprocessing, annotation,
dataset integration, and balancing. The comments were classified into three
sentiment categories: positive, negative, and neutral. Different approaches were investigated,
including traditional machine learning models, word embedding techniques
such as Word2Vec and FastText, deep learning models, pretrained transformer-based
language models, and a Hard Majority Voting ensemble. The experimental results show
that pretrained transformer models outperformed the traditional machine learning and
deep learning approaches, with DziriBERT achieving the best individual performance.
Furthermore, the proposed Hard Majority Voting ensemble achieved the highest overall
performance, reaching an accuracy of 86.42% and demonstrating the effectiveness of
combining multiple classifiers to improve the robustness and reliability of sentiment
prediction. Overall, this work contributes to the development of sentiment analysis resources
and models for Algerian Arabic. It highlights the challenges of dialectal Arabic
processing, particularly spelling variation, code-switching, informal expressions, and
the scarcity of labeled data, while proposing a practical methodology for building and
evaluating sentiment classification systems in a low-resource language context.
Breast Cancer Detection Based on Texture Analysis and Deep Learning Techniques
(university of bordj bou arreridj, 2026) Benchaib Haidar
Breast cancer is one of the leading causes of cancer-related mortality among women
worldwide. Early and accurate diagnosis is essential for improving patient survival and
reducing treatment complexity. Mammography remains the gold standard imaging
modality for breast cancer screening; however, the interpretation of mammographic
images is often challenging due to low contrast, dense breast tissue, image noise, and
the subtle appearance of suspicious lesions.
This thesis presents ONCO-VISION, an intelligent Computer-Aided Detection
(CAD) framework designed to improve breast lesion detection and segmentation by
integrating handcrafted texture analysis with deep learning. The proposed approach
combines Laws’ Texture Energy Measures (TEM) with the YOLOv11m-seg architecture
to enhance the visibility of suspicious mammographic structures, including microcalcifications,
spiculated masses, and architectural distortions.
The preprocessing pipeline consists of DICOM image normalization, Contrast Limited
Adaptive Histogram Equalization (CLAHE), and multi-channel texture feature extraction
using Laws’ kernels (L5S5, E5L5, E5S5, and R5R5). These texture-enhanced
representations are combined into a five-channel input that improves lesion characterization
and localization.
The proposed framework was evaluated using the publicly available INbreast
dataset, which contains 410 full-field digital mammography images with expert
annotations. Performance was assessed using standard object detection metrics,
including Precision, Recall, F1-score, and mean Average Precision (mAP).
Experimental results demonstrate that integrating texture enhancement with deep
learning improves the detection and localization of subtle breast lesions. Although
challenges remain, particularly in dense breast tissue and under class imbalance, the
proposed ONCO-VISION framework highlights the potential of combining handcrafted
texture descriptors with modern deep learning techniques to develop more accurate and
reliable computer-aided breast cancer diagnosis systems
Système de prédiction proactive des crises d’asthme
(University of Mohamed El Bachir El Ibrahimi - Bordj Bou Arréridj, 2026) Asma BOUGUETAYA; Samah ZAHRAOUI; Dina KHARFELLAH; Yousra YOUCEFI
L’asthme est une pathologie respiratoire chronique dont l’imprévisibilité des crises altère
gravement la qualité de vie des patients. Ce travail de fin d’études présente la conception
et le développement d’AsthmaGuard, un système prédictif intelligent et non invasif dédié
au suivi personnalisé de l’asthme chez l’adulte. Reposant sur le paradigme de la santé mobile
(m-Health), le système extrait passivement et en continu les biomarqueurs physiologiques
(fréquence cardiaque, variabilité de la fréquence cardiaque, saturation SpO2) à l’aide d’une
montre connectée grand public. L’architecture d’intelligence artificielle implémentée combine
trois modèles complémentaires : XGBoost pour l’évaluation des risques à long terme, Causal-
TFT (Temporal Fusion Transformer) pour la prédiction imminente des crises à court terme
basés sur les séries temporelles, et un système à logique floue intégrant les facteurs exogènes
environnementaux. L’écosystème logiciel comprend une application mobile multiplateforme
développée avec Flutter et une API backend robuste développée avec Laravel, conçues suivant
la méthodologie agile Scrum. Les résultats ouvrent des perspectives majeures pour une
médecine préventive et une meilleure autonomie du patient