Communautés dans DSpace
Sélectionner une communauté pour parcourir les collections sous-jacentes.
📚
6669
Documents disponibles
Dépôts récents
Diagnostic des pratiques culturales et des contraintes de production de l’orge dans la wilaya d’Ain Témouchent : perspectives d’amélioration de la durabilité
(2026) Labdelli Kheira; Mahimda Riham; Benahmed Chekroun Meryem
Barley (Hordeum vulgare L.) plays a strategic role in Algerian cereal farming, serving as an
essential grain and fodder resource, especially in semi-arid areas like the Aïn Témouchent province.
However, this crop remains highly dependent on climate conditions and relies on conventional farming
methods, the agronomic, economic, and environmental limits of which are still insufficiently documented
at the local level. This study aims to provide an overview of barley farming practices and production
constraints in this province, in order to identify opportunities for improving the sustainability of
production systems.
A field survey was conducted among 80 cereal farmers across seven communes representative of
the province’s agroclimatic diversity. The data, collected using a structured questionnaire, were
processed with Microsoft Excel.
The results reveal an aging farming population (76.3% over 55 years old) with low education
levels, using largely conventional technical methods: medium-depth plowing is dominant (76.3%),
almost exclusive monoculture of the Saïda 183 variety (93.8%), seeding density below recommended
levels (117.1 kg/ha), and flat-rate, unplanned fertilization. Water deficit (60.0%) and input costs (35.0%)
are the two main reported constraints, in a context where access to agricultural credit is almost
nonexistent (2.5%). The median observed yield is 22 qx/ha, well above the national average, but
irrigation provides a +60% gain compared to strictly rain-fed conditions, while direct seeding shows
higher yields than conventional plowing.
The sustainability analysis highlights signs of weakening across the environmental, economic, and
social dimensions, as well as a significant gap between awareness of conservation agriculture (43.8%)
and its actual adoption (16.3%).
These results support the cautious expansion of irrigation, the gradual adoption of no-till farming
and suitable crop rotations, as well as stronger training and access to agricultural financing.
Recherche de contamination bactérienne dans le contenu des œufs issus des élevages traditionnels de poule
(2026) SENHADJI Nesrine; RAHMANI Lina; MADANI Khadidja
This study was conducted to evaluate the microbiological quality of the internal contents of
eggs from traditional farms and to investigate the presence of pathogenic bacteria that may pose
a risk to consumers. Thirty-five (35) eggs, divided into three batches, were analyzed in the
laboratory. The analyses focused on staphylococci, coliforms, and salmonellae using selective
culture media and appropriate enrichment procedures. Suspected colonies obtained were
subsequently subjected to macroscopic, microscopic, and biochemical examinations.
The results showed a complete absence of staphylococci and coliforms in all analyzed samples.
No strains of Salmonella spp. were detected. However, isolated bacterial colonies recovered
after selective enrichment were identified as belonging to the species Citrobacter freundii.
Microscopic analyses revealed motile, Gram-negative bacilli that were oxidase-negative, while
biochemical profiles obtained using the API 20E system confirmed the identification of this
bacterium.
The presence of Citrobacter freundii in the internal contents of some eggs suggests
contamination of fecal or environmental origin, favored by insufficient hygienic conditions in
traditional farming systems. This bacterium represents an indicator of microbiological
contamination and a potential health risk to consumers. These findings highlight the importance
of adhering to good practices in egg production, collection, transportation, and storage in order
to ensure microbiological quality and reduce the risk of foodborne bacterial transmission.
Classification intelligente des modulations radio par Deep Learning
(2026) BERRICHI Bouchera; BOUCHIBA kheira samah; SOUIKI Sihem
Automatic Modulation Classification (AMC) is a key technology for many modern wireless applications, such as cognitive radio, spectrum monitoring, and intelligent networks. This thesis presents the study and development of a hybrid Deep Learning architecture designed to automatically identify the modulation type of received radio signals without prior information. The proposed model combines Convolutional Neural Network (CNN) layers for spatial feature extraction with a Transformer, a Bidirectional Gated Recurrent Unit (BiGRU), and an attention mechanism to efficiently capture long- term sequential dependencies in I/Q signals. The approach is validated using the benchmark RadioML 2016.10a dataset, which includes 11 classes of analog and digital modulations. This architecture aims to improve the robustness and accuracy of modulation recognition in complex transmission environments affected by noise, frequency offsets, and channel impairments.
L’Utilisation de la poudre de verre pour la stabilisation des talus (Étude expérimentale et numérique)
(2026) BELMECHRI NAZIHA; BELMECHRI HAYET; BELABBACI Z
The phenomenon of slope instability is one of the most complex geotechnical
problems, as clearly illustrated by the slope located on National Road N2
connecting the municipalities of Bensekrane and Amieur, where this site is subject
to repeated landslides that threaten the safety of road users and nearby
infrastructures. The stability of this slope mainly depends on the mechanical
properties of the soil, particularly cohesion (c) and the internal friction angle (φ).
This study aims to evaluate the effectiveness of recycled glass powder as a
sustainable additive to improve soil stability at the studied site, by adopting a
methodology that combines laboratory tests to determine shear strength
characteristics after addition, and numerical modelling of the slope behaviour
under both static and dynamic conditions using PLAXIS 2D and Géo-Slope
software. The obtained results show a significant improvement in shear strength,
reflected in an increase in the safety factor (FS), which confirms the effectiveness
of glass powder as a relevant geotechnical and environmental solution for
enhancing slope stability.
Conception et réalisation d’un système intelligent de gestion automatisée des présences basé sur la reconnaissance faciale : ClassTrack DZ
(2026) YAGOUBI Asmaa; ZIGH Hanaa; MERAD BOUDIA
Manual attendance tracking in higher education institutions remains time-consuming,
error-prone, and susceptible to fraud. This thesis presents the development of ClassTrack
DZ, an intelligent automated attendance system based on facial recognition technology.
The study begins with a theoretical overview of artificial intelligence and deep learning,
followed by a critical analysis of state-of-the-art detection and recognition algorithms.
A rigorous experimental methodology was employed to reproduce reference benchmarks
while evaluating a key innovation: the integration of the YOLOv8 architecture to replace
conventional detectors (Viola-Jones, HOG, MTCNN). Hybrid pipelines were compared
across two datasets using standardized metrics (accuracy, precision, recall, F1-score, and
inference time). Results demonstrate that YOLOv8 significantly accelerates multi-face de-
tection while maintaining optimal accuracy. The YOLOv8 + Dlib configuration emerged
as the most suitable compromise for real-time deployment in lecture halls. The modu-
lar Python-based implementation ensures scientific reproducibility and features a secure
pedagogical interface compliant with ethical standards for biometric data. This work
validates the operational viability of facial recognition for modernizing academic admin-
istration and paves the way for future enhancements, including liveness detection and
embedded platform deployment.