Joseph Azar FEMTO-ST · UMLP

Associate Professor (Maître de conférences)

Dr. Joseph Azar

I work on machine learning for resource-constrained systems: making data from IoT devices, sensors and industrial machines smaller, safer and more useful.

  • Computer Science Department, IUT Nord Franche-Comté
  • Université Marie et Louis Pasteur (UMLP)
  • FEMTO-ST Institute, CNRS · DISC Department, AIMOS team

Publications Google Scholar ↗

Portrait of Joseph Azar
842Citations
12h-index
49Publications listed
3PhD theses co-directed

Citation metrics from Google Scholar, October 2026.

About

I am an Associate Professor in Computer Science at the IUT Nord Franche-Comté (Université Marie et Louis Pasteur) and a researcher at the FEMTO-ST Institute (CNRS), where I belong to the AIMOS team of the DISC department.

My research sits where data science meets the Internet of Things. Much of it deals with lightweight data compression and edge machine learning, deep learning on physiological signals for e-health, intrusion detection and security for IoT networks, and fault detection for Industry 4.0. More recently I have been working on trustworthy AI, including vision-language models, knowledge-graph-augmented agents and federated learning.

I received my PhD in Computer Science from the Université Bourgogne Franche-Comté in 2020, with a thesis on data compression and deep learning for IoT healthcare applications based on physiological signals.

Recent publications

All publications →
  1. Journal article

    A reproducible, leakage-free pipeline for censored demand forecasting and inventory optimization on FreshRetailNet-50K

    J. Azar

    Inventions 11(5), 89, 2026

  2. Journal article

    Adaptive Federated Baseline K-Means for Lightweight IoT Intrusion Detection: Auto-Thresholding and Robust Statistics Aggregation

    M. A. Saleh, J. Azar

    IoT 7(3), 67, 2026

  3. Journal article

    A Novel IoT Security Framework Combining X25519 with NIST Lightweight Ascon Encryption and Hybrid Transform-Domain Steganography

    M. Al Saleh, R. Shbaro, J. Azar

    Telecom 7(2), 40, 2026

  4. Conference paper

    Leveraging Mono-Modal Data to Generate Multimodal Representations for Industrial Anomaly Detection

    C. El Achkar, A. Makhoul, J. Azar

    IEEE 50th Annual Computers, Software, and Applications Conference (COMPSAC), 2026

  5. Conference paper

    EHALEYO: Edge AI-Based High-Accuracy, Lightweight, Enhanced YOLOv11 for Real-Time Small UAV Detection in Complex Environments

    A. K. Idrees, S. K. Idrees, J. Azar, R. Couturier, F. Gechter, R. Schuster

    International Wireless Communications and Mobile Computing (IWCMC), 894–899, 2026