Efficient compression at the edge for real-time data acquisition in a billion-pixel x-ray camera

HE Rahali, MM Rahimifar, CÉ Granger, Z Wang… - Nuclear Instruments and …, 2024 - Elsevier
Recent advances in radiation detectors have significantly improved the resolution and frame
rate of X-ray imaging systems at the cost of large data throughputs that can be challenging to …

Exploring machine learning to hardware implementations for large data rate x-ray instrumentation

MM Rahimifar, Q Wingering… - Machine Learning …, 2023 - iopscience.iop.org
Over the past decade, innovations in radiation and photonic detectors considerably
improved their resolution, pixel density, sensitivity, and sampling rate, which all contribute to …

rule4ml: An open-source tool for resource utilization and latency estimation for ML models on FPGA

MM Rahimifar, H Ezzaoui Rahali… - Machine Learning …, 2025 - iopscience.iop.org
Abstract Implementing Machine Learning (ML) models on Field-Programmable Gate Arrays
(FPGAs) is becoming increasingly popular across various domains as a low-latency and low …

Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II

MM Rahimifar, Q Wingering… - Machine Learning …, 2024 - iopscience.iop.org
New scientific experiments and instruments generate vast amounts of data that need to be
transferred for storage or further processing, often overwhelming traditional systems. Edge …

Combining optimized quantization and machine learning for real-time data reduction at the edge

B Gouin-Ferland, MM Rahimifar… - 2022 IEEE Nuclear …, 2022 - ieeexplore.ieee.org
More and more physics and light source experiments are set to surpass TB/s data rates,
which are unsustainable for data acquisition, transfer and storage systems. To keep costs …

A survey of machine learning to fpga tool-flows for instrumentation

MM Rahimifar, CÉ Granger, Q Wingering… - 2022 IEEE Nuclear …, 2022 - ieeexplore.ieee.org
In the past decade, new developments in radiation and photonic detectors have caused
significant improvements in resolution, sensitivity, readout rate and size, which all contribute …

Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning

P Ai, L Xiao, Z Deng, Y Wang, X Sun… - Machine Learning …, 2023 - iopscience.iop.org
Pulse timing is an important topic in nuclear instrumentation, with far-reaching applications
from high energy physics to radiation imaging. While high-speed analog-to-digital …

A Versatile Edge Machine Learning Test Bench for High Bandwidth Instrumentation

Q Wingering, MM Rahimifar… - 2023 IEEE Nuclear …, 2023 - ieeexplore.ieee.org
New scientific experiments and instruments generate large volumes of data that need to be
transferred to storage or processing. Edge machine learning could allow us to reduce the …

Building Real Time Edge Machine Learning Systems for High Data Rate Acquisition

MM Rahimifar, Q Wingering… - 2023 IEEE Nuclear …, 2023 - ieeexplore.ieee.org
Over the past decade, a developments in radiation and photonic detectors has significantly
improved their resolution, pixel density, sensitivity, and sampling rate. The increase in …

[PDF][PDF] Traitement et compression de données en temps réel en utilisant l'intelligence artificielle pour des détecteurs à haut débit

B Gouin-Ferland - 2023 - savoirs.usherbrooke.ca
RÉSUMÉ Le SLAC National Accelerator Laboratory démarrera bientôt la prochaine
génération de lasers à électrons libres rayons X; le Linac Coherent Light Source-II (LCLS-II) …