image

Muhammad Umer

Wireless Research Scientist
thisismumer@gmail.com   +92 (335) 052-6986

About Me

I am currently an undergraduate student at the National University of Sciences & Technology (NUST), pursuing a B.S. in Electrical Engineering. My final year project involves developing an innovative framework based on reinforcement learning for optimizing future wireless networks under the guidance of Dr. Syed Ali Hassan.

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

Research Experience

May 2023 - Present
Information Processing and Transmission Lab (IPT)

Research Assistant

  • I am actively addressing the evolving challenges of 6G networking by pioneering novel network architectures and leveraging the synergistic convergence of artificial intelligence and communication theory.
June 2022 - Mar. 2023
TUKL Research and Development Lab

Research Assistant

  • I contributed to the advancement of table recognition in document images by developing a transformer-based architecture and devising a novel tabular image generative augmentation technique, enabling more effective training of vision transformers.
Oct. 2021 - Jan. 2022
Signal Processing & Machine Learning Lab (SIGMA)

Research Assistant

  • I contributed to the development of a sickle cell anemia detection system by collecting and processing blood smear images, and subsequently using deep learning for detection of sickle-shaped red blood cells.

Publications

Conferences

  • Performance Analysis of STAR-RIS Enhanced CoMP-NOMA Multi-Cell Networks

    Muhammad Umer, Muhammad Ahmed Mohsin, Mikael Gidlund, Haejoon Jung, and Syed Ali Hassan
    IEEE Communications Society, IEEE GLOBECOM 2023

  • PyramidTabNet: Transformer-Based Table Recognition in Image-Based Documents

    Muhammad Umer, Muhammad Ahmed Mohsin, Adnan Ul-Hasan, and Faisal Shafait
    Springer Nature Switzerland AG, ICDAR 2023

Journals

  • Analysis of STAR-RIS Assisted Downlink CoMP-NOMA Multi-Cell Networks under Nakagami-m Fading

    Muhammad Umer, Muhammad Ahmed Mohsin, Mikael Gidlund, Haejoon Jung, and Syed Ali Hassan
    IEEE Communications Society, IEEE Communications Letters

Awards & Accolades

  • NUST Merit Scholarship - Year 2021 to 2023
  • Travel award for KAIST EE Camp
  • Recipient of PM's Laptop under the PM's Youth Laptop Scheme Phase III

Education

  • B.S. in Electrical Engineering
    National University of Sciences & Technology (NUST)
    Aug. 2020 - Present
  • 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
  • PyTorch
  • JAX
  • MATLAB
  • RLlib

Projects

AeCC

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

Comyx

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

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