Marouane Hajri

Implemented and compared three detection approaches: a matched filter, a CNN, and an autoencoder. Developed Python/PyTorch reference models, implemented custom processing logic in VHDL, and deployed the neural-network models through a PyTorch-to-FPGA toolchain. Integrated the accelerator using Vivado, Vitis, and Xilinx Runtime (XRT), with image data transferred through the U55C’s onboard HBM. Evaluated detection accuracy, processing latency, throughput, and FPGA resource utilization.

- Developed Python/Matlab scripts to automate test procedures and measurements using vector network analyzers and other laboratory equipment - Expanded a long-term drift measurement test bench for vector network analyzers - Measured and analyzed settling times of RF components - Implemented a small FPGA-based controller on Xilinx Zynq-7010 for fan-speed synchronization - Designed, routed, assembled, and tested PCB prototypes - Created interactive Jupyter notebook reports to support technical decision-making

Zweitstudium