image

Muhammad Umer

Aspiring Researcher
thisismumer@gmail.com   +92 (335) 052-6986

About Me

I am currently an R&D engineer at Adept (ATS) Inc. Prior to this, I was an undergraduate student at the National University of Sciences & Technology (NUST), where I graduated with a Bachelor's degree in Electrical Engineering. I am also serving as a research assistant at the Information Processing and Transmission Lab (IPT) under the supervision of Dr. Syed Ali Hassan. My final year project involved developing a novel reinforcement learning-based optimization framework for resource allocation in next-generation wireless networks.

I have a keen interest in the intersection of artificial intelligence and communication theory, and I am particularly passionate about applying cutting-edge AI techniques to tackle the evolving challenges of 6G networking. Through my research and expertise, I am committed to fostering innovation and enhancing global connectivity.

Research & Work Experience

July 2024 - Present
Adept (ATS) Inc.

R&D Engineer

  • Contributing to the development of Ascend, a cutting-edge tool for generating synthetic data.
  • Focusing on data anonymization and implementing correlative masking techniques to preserve the statistical integrity of original datasets during synthesis.
  • Leading the integration of generative AI into Ascend to enable the creation of high-fidelity synthetic data from limited or no pre-existing data.
  • Actively mentoring interns, sharing knowledge and experience to support their professional growth while simultaneously gaining valuable teaching experience.
May 2023 - Present
Information Processing and Transmission Lab (IPT)

Research Assistant

  • Conducting research focused on addressing the evolving challenges of beyond 5G and 6G wireless networks.
  • Actively engaged in pioneering novel network architectures and leveraging the synergy between artificial intelligence and communication theory to enhance future communication systems.
  • Serving as a teaching assistant for the course on Mobile Communication Systems for Fall 2024.
June 2022 - Mar. 2023
TUKL Research and Development Lab

Research Assistant

  • Contributed to the advancement of table recognition in image-based documents to automate information extraction.
  • Designed and implemented a scalable tabular data augmentation pipeline for effective training of vision transformers.
  • Proposed a novel convolution-less vision transformer architecture specifically tailored for table recognition tasks.
Oct. 2021 - Jan. 2022
Signal Processing & Machine Learning Lab (SIGMA)

Research Assistant

  • Contributed to the development of a sickle cell anemia detection system.
  • Collected and processed blood smear images for analysis.
  • Utilized deep learning techniques to detect sickle-shaped red blood cells, enabling automated diagnosis.

Publications

Journals

  • Intelligent Spectrum Sharing in Integrated TN-NTNs: A Hierarchical Deep Reinforcement Learning Approach
    M Umer, MA Mohsin, AA Nasir, H Abou-Zeid, and SA Hassan
    Submitted to IEEE Wireless Communications [under review]
  • RIS-Assisted Aerial Non-Terrestrial Networks: An Intelligent Synergy with Deep Reinforcement Learning
    M Umer, MA Mohsin, A Kaushik, QUA Nadeem, AA Nasir, and SA Hassan
    Accepted | IEEE Vehicular Technology Magazine    [Preprint]
  • Transforming ISAC with STAR-RIS: Design, Challenges, and Opportunities
    M Umer, S Basharat, SA Hassan, A Mahmood, and M Gidlund
    Published in IEEE Network    [Paper]
  • Analysis of STAR-RIS Assisted Downlink CoMP-NOMA Multi-Cell Networks under Nakagami-m Fading
    M Umer, MA Mohsin, M Gidlund, H Jung, and SA Hassan
    Published in IEEE Communications Letters    [Paper]

Conferences

  • On Energy Efficient Passive Beamforming Design of RIS-Assisted CoMP-NOMA Networks
    M Umer, MA Mohsin, A Mahmood, H Jung, H Pervaiz, M Gidlund, and SA Hassan
    Submitted for IEEE ICC '25 [under review]
  • Deep Reinforcement Learning for Trajectory and Phase Shift Optimization of Aerial RIS in CoMP-NOMA Networks
    M Umer, MA Mohsin, A Mahmood, K Dev, H Jung, M Gidlund, and SA Hassan
    Accepted | IEEE GLOBECOM '24    [Preprint]
  • PyramidTabNet: Transformer-based Table Recognition in Image-based Documents
    M Umer, MA Mohsin, A Ul-Hasan, and F Shafait
    Published in ICDAR '23    [Paper]

Workshops

  • Performance Analysis of STAR-RIS Enhanced CoMP-NOMA Multi-Cell Networks
    M Umer, MA Mohsin, SA Hassan, H Jung, and H Pervaiz
    Published in IEEE GLOBECOM '23 WC    [Paper]

Service

  • Reviewer – ICDAR '23, GLOBECOM '23, IEEE Transactions on Vehicular Technology, IEEE Vehicular Technology Conference, GLOBECOM '24
  • Mentor – Adept Summer Internship Program (2024), IPT Undergraduate Research Program (2024)
  • Organizer – STEM Workshop @ The Mashal School (2024)

Awards & Accolades

  • Recipient of NUST Merit Scholarship (2021 to 2024)
  • Recipient of Travel Award for KAIST EE Camp, South Korea (2023)
  • Recipient of PM's Laptop under the PM's Youth Laptop Scheme Phase III (2023)
  • Recipient of Financial Award for Undergraduate Research (2024)

Education

  • B.E. in Electrical Engineering
    National University of Sciences & Technology (NUST)
    Oct. 2020 - July 2024
    CGPA: 3.97/4.00
    Rector's Gold Medalist
    Chancellor's Silver Medalist
  • Intermediate in Pre-Engineering
    HITEC School & College
    Mar. 2016 - Apr. 2020

Research Interests

  • Communication Theory
  • Wireless Communications
  • 6G
  • Machine Learning
  • Deep Learning
  • Reinforcement Learning

Technical Skills

  • Python
  • C/C++
  • MATLAB
  • Mathematica
  • PyTorch
  • JAX
  • RLlib
  • TorchRL
  • LangChain

Projects

Comyx

Modular python library for analysis and simulation of wireless communication systems.

i-POET

Deep reinforcement learning for intelligent power control in IoT.

AeCC

Image compression, transmission, and denoising through Vision Transformer (ViT) based autoencoder.

RL-Wireless

Reinforcement learning based resource allocation for wireless networks.

Deep-Suppressor

Denoising of speech signals using fourier transforms and deep learning.

PyramidTabNet

Transformer-based table recognition in image-based documents.

Languages

  • Urdu
  • English