RIXISAC

This subpage is about RIXISAC: Reflective intelligent surface-assisted, Intelligent, and eXplainable Integrated Sensing and Communication systems. 

• RIXISAC is the Marie Skłodowska-Curie Actions (MSCA) Postdoctoral Fellowship that I was awarded by the European Commission, under call HORIZON-MSCA-2023-PF-01-01. The grant is 187,624.32€, covering my salary and training/travelling costs for 9/2025-8/2027. 

• RIXISAC is based on a research proposal and on previous merits, and in my call it had an acceptance rate of 15.8%. The score i acumulated is 98.2 out of 100, which places my proposal in the Top 3.9% of submissions for my round (link). 

Available thesis projects

Topics:

1. Optimal data granularity for radar sensing in ISAC environments. [TU Delft Link]

2. Cross-Domain Data Fusion within the xApp Ecosystem. [TU Delft Link]

3. Algorithmic Modeling of Environment-Induced Packet Dynamics. [TU Delft Link]

4. Explainable AI (XAI) for Environment-Driven Network Diagnostics. [TU Delft Link]

Feel free to contact me for more information or if you cannot access the links above. 

Approach & Tailored Project Tracks: 

Recognizing the interdisciplinary nature of ISAC, all available theses projects can be tailored to fit your specific background and interests (whether in CS, EE, Applied math, or Cyber Security). All students will initially examine and categorize existing literature on the topic of choice. You and the supervision team will then shape the final scope to lean toward one of two tracks: 

• Track A (Theoretical & Data-Driven): Focus on mathematical modeling, algorithmic design, and machine learning elements using the collected radar/network datasets. You will experiment with empirical datasets to derive conclusions related to the specific topic of choice, and design algorithmic trade-offs emerging in it. 

• Track B (Systems & Engineering): Focus on the practical implementation, O-RAN integration, and real-time execution. You will design and develop baseline algorithms related to the topic of choice, and evaluate them directly against the physical testbed data to assess their real-time performance.  

Supervision and Environment: 

The student will be supervised by Dr. Livia Elena Chatzieleftheriou as the main supervisor for algorithmic design, collaborating seamlessly when needed with the experimental team led by Anup Bhattacharjee. The responsible professor will be Prof. George Iosifidis. See my work philosophy in the "Teaching and Supervision" and "About me" tabs.

Regardless of which track you choose, you will have direct access to our indoor ISAC lab and physical testbed, which features Texas Instruments mmWave radar hardware (AWR2944PEVM and DCA1000EVM) integrated alongside a live, open-source cellular stack. 

All theses topics offer an excellent springboard for a master's thesis publication, a future PhD, or highly sought-after industry roles such as an AI/ML Engineer, Data Scientist, Explainable AI (XAI) Specialist, or an R&D Engineer in the telecommunications and edge computing sectors.