Dissertation Defense of Student Natiq Aziz Imran

Visitors: 25377189 Views

Done By: Department of Biomedical Engineering

Post Date: 2024-10-31

Last Browse: 2025-07-03


On Thursday, 31st October 2024, in the Department of Biomedical Engineering, PhD student Natiq Aziz Imran defended his dissertation titled:

"Machine Learning-based Autonomous Training Board for Experimental Study and Rehabilitation of the Upper Prosthetics"

The defense committee was chaired by Professor Dr. Sadiq Hussein Bakhi from the Department of Mechanical Engineering at the University of Technology, with committee members:

  • Professor Dr. Mahmoud Rashid Ismail from the Department of Prosthetics and Orthotics Engineering at Al-Nahrain University
  • Associate Professor Dr. Abbas Fadel Abdul Wahab from the College of Medicine at Al-Nahrain University
  • Associate Professor Dr. Anas Latif Mahmoud from the Department of Electronics and Communications Engineering at Al-Nahrain University
  • Associate Professor Dr. Ahmed Faiq Hussein from the Department of Artificial Intelligence Engineering at Al-Nahrain University

The dissertation was supervised by Professor Dr. Mohammed Abdul Sattar Mohammed from Al-Nahrain University and Professor Dr. Mithaq Naama Rahim from the College of Engineering at the University of Karbala.

The dissertation was reviewed by:

  • Primary scientific reviewer, Professor Dr. Nazem Mujbil Qalah from the Department of Mechanical Engineering at Al-Mustansiriya University
  • Secondary scientific reviewer, Professor Dr. Ali Hussein Mohammed from the Department of Mechanical Engineering at Al-Nahrain University
  • Linguistic review by Lecturer Dr. Muna Mustafa Kareem from the Department of Biomedical Engineering at Al-Nahrain University

The study aimed to design a model for controlling an open-source, 3D-printed robotic arm with six degrees of freedom (DoF) using surface electromyography (sEMG) signals from a Myo Gesture Control Armband. The model distinguishes between various hand gestures from healthy individuals. Six time-domain features were extracted from each segment, enhancing existing models by improving DoF motion control and time-domain features, which significantly reduces patient effort and facilitates arm use. The dissertation was accepted, having met the requirements for the PhD degree.