Archives: Defences

Monday, May 1, 2023

Youhao Yu defends his PhD thesis

Youhao successfully defended his PhD thesis Reconstruction of Compressive Sensed (CS) Images with Deep Equilibrium Model (DEQ) Based on Iterative Shrinkage-Thresholding Algorithm (ISTA) In this thesis, we explored using learned compressive sensing for image compression using a deep neural network in the form of a deep equilibrium model (DEQ) as an... More

Monday, January 17, 2022

Zahra Ashouri Talouki defends her PhD thesis

Zahra successfully defended her PhD thesis Kernel-Based PET Image Reconstruction using Dynamic PET and MR Anatomical Information In this thesis, we explored PET image reconstruction using kernel expectation maximization (KEM) using multiscale wavelet kernels, MR prior information, and feature-driven spatial weighting. This work was co-supervised... More

Friday, September 3, 2021

Hossein Chahrour defends his PhD thesis

Hossein successfully defended his PhD thesis titled Signal Processing Methods in Riemannian Geometry with Application to Drone Detection In this thesis, we use Riemannian manifolds to project MIMO radar sample covariance matrices and apply this for detection of small drones in cluttered environments. This work was co-supervised with Prof.... More

Tuesday, April 20, 2021

Tayebeh Lotfi Mahyari defends her PhD thesis

Tayebeh successfully defends her PhD thesis Image Separation using Multi-layer Image Segmentation for Translucent Partially Overlapped Objects In this thesis, we adapt graph-based random walker image segmentation and convolutional neural networks (CNNs) to segment and separate cervical cell images. We had great support from an NSERC Discovery... More

Wednesday, September 13, 2017

Ce Peng defends his PhD thesis

Ce Peng successfully defends his PhD thesis Monaural Music Separation via Supervised Non-negative Matrix Factorization with Side-information In this thesis, we develop a single-channel sound separation technique that can isolate different musical instruments in a recording. The technique relies on machine learning with non-negative matrix... More

Monday, August 14, 2017

Assem M. Assem defends his PhD thesis

Assem successfully defends his PhD thesis Low Latency Compressive Sensing using Multi-resolution Analysis in Radar Signal Processing In this thesis, we develop a radar signal processing technique that allows range and Doppler velocity to be extracted from compressed sensed measurements without computationally expensive signal reconstruction.... More

Load More →