ESSAT Institutional Repository

Higher School of Applied Sciences of Tlemcen (ESSAT)

Welcome to ESSAT DSpace

Welcome to the Institutional Repository of the Higher School of Applied Sciences of Tlemcen (ESSAT).

This platform showcases, preserves, and provides open access to our academic and scientific output, including:

  • Doctoral dissertations
  • Master’s theses
  • Course handouts and lecture notes
  • Conference proceedings
  • Scientific publications and research papers

We invite you to explore our collections and visit regularly, as the repository is continuously updated with new content.

Photo by @inspiredimages

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 10

Recent Submissions

  • Thumbnail Image
    Item type:Item,
    Étude et conception d’un système IoT intelligent pour la collecte, l’analyse et la distribution à la demande des données industrielles
    (directeur Dr. Karaouzene Zoheir, co-directeur Pr. Zidi Salah, 2026-06-20)
    Ahmed Ghezal
    ;
    Mohammed Nehila
    Ce mémoire présente l'étude et la conception d'un système IoT intelligent pour la collecte, l'analyse et la distribution à la demande des données industrielles, appliqué à la maintenance prédictive d'une pompe industrielle par analyse vibratoire. Le système repose sur une architecture IoT en trois couches intégrant les protocoles MQTT et Modbus TCP pour la collecte, InfluxDB pour le stockage des séries temporelles, et Node-RED et Grafana pour la visualisation. Un pipeline de traitement en huit étapes, entièrement simulé sous MATLAB, combine le prétraitement du signal (filtrage, agrégation, FFT), le Machine Learning supervisé (Random Forest — accuracy 100%) et non supervisé (K-Means), la surveillance par seuils ISO 10816 et la prédiction de défaillance par régression linéaire. Les résultats confirment la faisabilité et l'efficacité de l'approche IoT-IA intégrée, avec une distribution à la demande adaptée à trois profils de clients distincts : opérateur de maintenance, ingénieur de diagnostic et superviseur de production.
  • Thumbnail Image
    Item type:Item,
    Développement D’un Prototype De Plateforme D’IA Pour La Prévision à Court Terme De La Production Photovoltaïque à Partir De Données Météo
    (directeur Dr. Anisse CHIALI, co-directeur Dr. Imane NEDJAR, 2026-06-20)
    Yousra Oum El kheir HAMMADI
    ;
    Nor El Houda BEKADA BENCHAIB
    Ce travail consiste à développer un prototype de plateforme basée sur l’intelligence artificielle pour la prévision à court terme de la production d’un système photovoltaïque à partir de données météorologiques. Le projet inclut la collecte et le prétraitement des données de production et des variables météo, la conception et l’entraînement de modèles de prédiction, ainsi que leur évaluation à l’aide d’indicateurs de performance appropriés. Le prototype vise à fournir un outil simple d’aide à la décision pour les exploitants de centrales solaires, et à démontrer le potentiel d’une future solution orientée «prévision et optimisation énergétique».
  • Thumbnail Image
    Item type:Item,
    Simulating and compensating kinematic defects in 5-Axis CNC machining A linear feedforward approach
    (directeur Mrs Amel GHOUALI, directeur Mr Hicham MEGNAFI, 2026-06-08)
    Selsabil DJELLOULI
    Multi-axis CNC machining accuracy is limited by inherent geometric and kinematic flaws. This thesis investigates volumetric error generation in a 5-axis bi-rotary CNC prototype, which accumulates 43 distinct geometric errors. A mathematical digital twin was constructed using Homogeneous Transformation Matrices (HTM) to model these deviations. To mitigate this, a novel offline Hybrid Analytical- Numerical Inverse Kinematics compensation algorithm was developed. Applied via Post-CAM G-code modification to finishing trajectories, MATLAB simulations demonstrated that the algorithm successfully reduced volumetric deviations to a sub-micron tolerance (below 0.0001 mm).
  • Thumbnail Image
    Item type:Item,
    Integration of Computer Vision AI (Camera + Image Processing) into an IoT Calving Detection Device
    (directeur Dr.Didi Ibtissem, directeur Dr. BOUKLI HACENE Lotfi Fazil, 2026-06-21)
    TESSOUMI Mohamed Amine Bennedjadi
    ;
    CHERIFI Mohamed El Amine
    Calving is one of the most critical events in dairy cattle farming. Complications during delivery, if undetected in time, lead to significant calf and cow mortality, substantial economic losses, and increased veterinary costs. Traditional monitoring methods, based on manual farm inspections, are labor-intensive and unreliable, particularly during nighttime hours when the majority of calvings occur. This memoir presents CalvingSafe, a low-cost, IoT-based intelligent system designed to automatically detect pre-calving behavioral patterns and deliver real-time alerts to farmers and veterinarians. The system integrates three MPU6050 sixaxis inertial measurement units mounted along the cow’s tail, connected through a TCA9548A I2C multiplexer to an ESP8266 NodeMCUWi-Fi microcontroller. Sensor data is transmitted via UDP over a localWi-Fi network to a Python backend, where it is processed through a sliding window of 20 consecutive readings and fed into a hybrid artificial intelligence engine. The AI engine combines a feedforward Artificial Neural Network (ANN), implemented as a two-hidden-layer MLPClassifier (128 × 64 neurons, tanh activation, threshold = 0.2, trained with SMOTE balancing on a Kaggle-published dataset), with a seven-input Mamdani Fuzzy Logic System (FLS) operating on eight handcrafted inference rules. A two-model voting mechanism with a 10-consecutive-frame temporal filter produces three confidence levels: HIGH, MEDIUM, and LOW, each mapped to a specific alert behavior. Detected events are pushed to a Firebase Realtime Database and reflected in real time on the CalvingSafewebdashboard, deployed on Vercel, which provides role-differentiated views for farmers and veterinarians. A three-channel alert system combining in-dashboard banners, Firebase event logging, and Blynk mobile push notifications ensures that no calving event goes unnoticed. System validation was conducted through a CSV simulation mode exercising the complete inference and cloud pipeline on a labeled IMU dataset. Results confirmed correct end-to-end behavior across all subsystems, with an estimated total pipeline latency below one second. The system demonstrates the feasibility of deploying an intelligent, low-cost calving detection solution adapted to Algerian farming conditions.
  • Thumbnail Image
    Item type:Item,
    SmartCalve: Design and Implementation of an IoT Device for Early Calving Detection in Cattle
    (directeur 1 Dr.Didi Ibtissem, directeur2 Dr. BOUKLI HACENE, 2026-06-21)
    CHERIFI Mohamed El Amine
    ;
    TESSOUMI Mohamed Amine Bennedjadi
    Bovine calving is a critical event in livestock farming that requires timely human intervention to prevent calf and cow mortality. Existing detection systems suffer from invasiveness, high cost, or limited real-time precision, restricting their adoption in conventional farming environments. This work presents CalvingSafe, a non-invasive IoT-based multi-node kinematic monitoring system designed for realtime detection of bovine parturition. The system integrates a distributed array of MPU6050 inertial measurement units mounted along the bovine tail, managed by a TCA9548A I2C multiplexer and controlled by an ESP8266 microcontroller. Raw accelerometer data is converted into spherical coordinates (R, φ, θ) and transmitted wirelessly to a processing backend. A proprietary dataset of 3,060 kinematic frames was extracted from 60 video sequences using an OpenCV-based multi-segmental 3D tracking pipeline, covering three behavioral states: normal behavior, waste elimination, and pre-calving agitation. The hardware prototype was assembled and validated through serial monitor testing, confirming the integrity of the full data acquisition chain across all three sensor nodes.