Back
Previous Next
Feten Slimeni

Feten Slimeni

Research

Project name: RF-TrafficSense (Radio-Frequency Traffic Sensing Network for Security and Efficiency)

Drones are becoming part of our cities – delivering medical supplies, monitoring traffic, or assisting in search-and-rescue operations. But the same technology can also be misused for smuggling, spying, or even attacking critical infrastructure. To protect citizens and essential services, cities need to know what is flying in their airspace. RF-TrafficSense uses radio sensors and machine learning to detect and classify drones in real time.

At the same time, drones share the same crowded radio frequencies as Wi-Fi, 5G, and public safety communications. Too many devices talking over each other causes harmful interference. This project develops a self-learning "cognitive spectrum engine" that dynamically allocates radio resources, ensuring that security monitoring and drone operations do not disrupt the connectivity that citizens and businesses rely on.

By addressing the societal challenges of Mobility (safe integration of drones into urban transport) and Resource Optimisation (efficient sharing of the radio spectrum), RF-TrafficSense aims to become a cornerstone for secure, sustainable, and connected urban living in the Brussels Capital Region and beyond.

Biography

Feten Slimeni is a postdoctoral researcher at ULB (Université libre de Bruxelles) working at the intersection of wireless communications, machine learning, and security. She holds a PhD in applied science from the Royal Military Academy (RMA) and has over a decade of experience in RF signal processing, software-defined radio (SDR), and AI-driven detection systems. Her work focuses on enhancing both urban airspace security and radio spectrum efficiency.

Publications

  • F. Slimeni, T. Dalleji, and A. Siala, "Robust Drone Swarm Identification Through Wavelet Scattering Transform and Hybrid Machine Learning," in IT Professional, vol. 28, no. 2, pp. 67-75, March-April 2026, doi: 10.1109/MITP.2026.3651841.
  • F. Slimeni, T. Delleji, and A. Siala, "Lightweight vs. Advanced Architectures: Performance Analysis of YOLOv8n and YOLOv9T in RF Spectrogram-Based UAV Detection" 2025 11th International Conference on Control, Decision and Information Technologies (CoDIT), Split, Croatia, 2025, pp. 1-6, doi: 10.1109/CoDIT66093.2025.11321881. 
  • Delleji, T., Slimeni, F., et al. (2025). Real-Time Detection and Identification of mini-UAVs Using RF Signal Features and a Customized MLP Model. Journal of Electrical Engineering & Technology.
  • Slimeni, F., et al. (2023). Real time implementation of SDR-based RF source detection and localization in restricted area. Telecommunication Systems.
  • Slimeni, F., et al. (2022). Optimal Power Allocation Based Unlicensed Spectrum Sharing for Cellular Networks. IEEE IC_ASET

Outreach activities

I am planning public demonstrations at events such as European Researchers' Night and workshops on AI for RF sensing. I am open to engaging with schools, policymakers, and industry stakeholders to explain how intelligent radio systems can make cities safer and more efficient.