معرفی
Amir Aghabiglou is a Researcher at Heriot-Watt University, affiliated with the School of Engineering & Physical Sciences and the Institute of Sensors, Signals & Systems. His work focuses on advancing deep learning techniques for high-dynamic range imaging in radio astronomy and medical imaging. He specializes in developing neural network architectures like the R2D2 series, which address challenges in large-scale data processing, uncertainty quantification, and real-time image reconstruction.
Key research contributions include scalable MRI reconstruction methods, robust radio-interferometric imaging frameworks, and spherical extensions of neural networks for wide-field astronomical observations. His collaborations span institutions like the European Southern Observatory and involve datasets such as the VLA and Cygnus A reconstructions.
Aghabiglou’s research integrates signal processing, machine learning, and domain-specific knowledge to solve interdisciplinary problems. He has developed open-source tools and frameworks for assessing scientific productivity metrics, bridging data science with bibliometrics.
His work has been published in leading journals like the Astrophysical Journal and presented at conferences such as EUSIPCO. He actively contributes to both theoretical advancements and practical implementations in imaging sciences.
