Equalization in Optical Fiber Communication

Ph.D. Research · Télécom Paris & Infinera GmbH · 2019–2023

My doctoral research focused on applying model-based neural networks to equalization in coherent optical fiber communication systems. I developed learned digital back-propagation (LDBP) algorithms that combine classical DSP structure with deep learning optimization, reducing receiver complexity while maintaining performance in dispersion-managed long-haul and metro systems. I also designed low-complexity convolutional neural network equalizers targeting practical transceiver constraints. This work was conducted within the EU H2020 MSCA REAL-NET network.


Machine Learning for Wireless Communications

M.Sc. Research · University of Idaho · 2016–2019

During my master’s studies, I investigated low-complexity automatic modulation classification (AMC) algorithms using statistical moments and likelihood maximization. I implemented and compared machine-learning-based and parametric classifiers under realistic fading and noise conditions, culminating in an IEEE Communications Letters publication.


Robotics & Embedded AI

Ongoing Research · American College of the Middle East · 2024–Present

I am currently developing AI-assisted segment detection and PID gain scheduling methods for competitive line-following robots using IR sensor arrays and physics-based simulation. This work explores where machine learning should be inserted within the sensing and control pipeline—sensor processing, segment recognition, or action generation—without replacing classical PID control.

Google Scholar Profile →

  1. M. Abu-Romoh, F. Ziyad, W. Dawaghreh, O. Al-Attia, and Y. Imamverdivey, “Machine Learning Placement in Line-Following Robot Control: A Comparative Study of Classical and Learned Pipelines,” manuscript in preparation. In Progress
  2. M. Abu-Romoh, “AI-assisted Fast Segment Detection and PID Gain Scheduling for Competitive Line-Following Robots,” in Proc. 15th Int. Conf. Pattern Recognition Applications and Methods (ICPRAM 2026), SciTePress, 2026. Under Review
  3. M. Abu-Romoh, N. Costa, Y. Jaouën, A. Napoli, J. Pedro, B. Spinnler, and M. Yousefi, “Equalization in dispersion-managed systems using learned digital back-propagation,” Optics Continuum, vol. 2, no. 10, pp. 2088–2105, Oct. 2023. Journal Editor’s Pick
  4. M. Abu-Romoh, N. Costa, A. Napoli, B. Spinnler, Y. Jaouën, and M. Yousefi, “Learned Digital Back-Propagation for Dual-Polarization Dispersion Managed Systems,” in Proc. ECOC 2022, pp. We1C.6, Sep. 2022. Conference
  5. M. Abu-Romoh, N. Costa, A. Napoli, J. Pedro, Y. Jaouën, and M. Yousefi, “Low Complexity Convolutional Neural Networks for Equalization in Optical Fiber Transmission,” in Proc. SPPCom 2021, pp. SpM5C.5, Jul. 2021. Conference
  6. M. Abu-Romoh, A. Aboutaleb, and Z. Rezki, “Automatic modulation classification using moments and likelihood maximization,” IEEE Communications Letters, vol. 22, no. 5, pp. 938–941, Feb. 2018. Journal

Marie Skłodowska-Curie Early-Stage Researcher

REAL-NET (Horizon 2020), European Union France & Germany · Nov. 2019 – Feb. 2023

  • Funded Ph.D. fellowship on advanced equalization techniques for optical fiber networks within the REAL-NET ITN/EID consortium.

Research Assistantship

University of Idaho, Dept. of Electrical Engineering Moscow, ID, USA · Oct. 2016 – Oct. 2018

  • Graduate research assistantship supporting work on machine-learning-based modulation classification for wireless communications.