My research is centered on intelligent and distributed systems for real-world environments. I am particularly interested in how computing systems can become more efficient, adaptive, privacy-aware, and useful in practice. Three major research clusters that I am working are:

• Federated and Embedded AI
  We develop machine learning systems that run on resource-constrained devices and learn collaboratively without sharing raw data. This includes TinyML on microcontrollers, federated learning across mesh networks, and adaptive algorithms for devices with limited memory, bandwidth, and power. Current focus: federated learning for medical imaging in multi-site clinical settings. 

• AI for Health and Environment
  We apply AI to problems with direct societal impact. Our ongoing projects include AI-driven breast cancer detection using federated approaches (preserving patient privacy across hospitals), and community-scale air pollution monitoring in Tetova using low-cost IoT sensors. Collaborations: University of Birmingham.

• Decentralized Systems and IoT
  We build and study decentralized architectures — from LoRa mesh networks and edge computing platforms to blockchain-based coordination systems. Our work spans system design, testbed deployment, and real-world evaluation in community networks. Past contributions include platforms deployed on Guifi.net (Barcelona) and the CityLab testbed (Antwerp).