03/14/2023
By Hengyong Yu

The Francis College of Engineering, Department of Electrical & Computer Engineering (ECE), invites you to attend a Ph.D. dissertation defense by Dayang Wang on “Machine learning and application to medical imaging & food science.”

Ph.D. Candidate: Dayang Wang
Defense Date: Tuesday, March 28, 2023
Time: 3 to 4:30 p.m.
Location: This will be a virtual defense via Zoom. Those interested in attending should contact the student (Dayang_Wang@student.uml.edu) or committee chair (Hengyong_Yu@uml.edu) at least 24 hours prior to the defense to request access to the meeting.

Committee Members:

  • Chair: Advisor Hengyong Yu, Professor, Electrical and Computer Engineering, University of Massachusetts Lowell
  • Tricia Chigan, Ph.D., Professor, Electrical & Computer Engineering, University of Massachusetts Lowell
  • Yan Luo, Ph.D., Professor, Electrical & Computer Engineering, University of Massachusetts Lowell
  • Thanuka Wickramarathne, Ph.D., Assistant Professor, Electrical & Computer Engineering, University of Massachusetts Lowell

Abstract: In recent years, artificial intelligence has been prevailing over various science and engineering fields. Inspired by the great success, the candidate is motivated to engage in the machine/deep learning research and its applications in various fields. In this dissertation, the candidate will present what he has achieved during his Ph.D. studies. First, he will introduce a new type of machine learning model that can derive the decision boundaries directly from the raw data. Second, he will introduce the application of the deep learning in the lettuce browning prediction field by prototyping a new high-order transformer. Third, he will introduce deep learning application for medical image denoising where we developed a new convolution-free transformer model. Fourth, he will introduce the application of the self-pretraining to LDCT denoising where Masked autoencoders are first applied to LDCT to improve the denoising performance and alleviate the demand for ground truth data. Fifth, he will introduce a new iterative transformer method that is the first deep learning method proposed to simulate the contrast doses in MRI. Finally, he will summarize his work during PhD.

All interested students and faculty members are invited to attend the online defense via remote access.