Department of Electrical and Computer Engineering Graduate Theses
Recent Submissions
-
Lensed and Reconfigurable Antennas for Passive Beam Forming and Beam Steering
Wideband antennas are a crucial part of advanced wireless communications systems. When designing wideband antenna, is it imperative to be able to augment an antenna’s performance to meet a desired outcome, be it beam-steering, ... -
Soft-switched three-phase PV microinverter
This thesis presents novel soft-switching converter topologies for designing two-stage PV microinverters. The emphasis is placed on grid-tied, three-phase AC systems. Two-stage microinverter architecture comprises a DC-DC ... -
Attentive Cross-Modal Connections for Learning Multimodal Representations from Wearable Signals for Affect Recognition
We propose cross-modal attentive connections, a new dynamic and effective technique for multimodal representation learning from wearable data. Our solution can be integrated into any stage of the pipeline, i.e., after any ... -
Multistream Gaze Estimation with Anatomical Eye Region Isolation by Synthetic to Real Transfer Learning
We propose a novel neural pipeline, MSGazeNet, that learns gaze representations by taking advantage of the eye anatomy information through a multistream framework. Our proposed solution comprises two components, first a ... -
EdgeNet: Dense Instance Segmentation via Contour-Detection and Foreground Clustering
This thesis proposes a novel method for instance segmentation in the Robotic Bin-Picking problem using a blend of deep learning and classical methods, titled EdgeNet. Pose estimation is used on sensed data to relay ... -
Graph-based Hyperspectral Unmixing Using Deep Convolutional Neural Networks
Hyperspectral image unmixing (HU) is a remote sensing technique that has numerous applications in ecology, earth observation, and agronomy. Recently the research surrounding hyperspectral unmixing are using deep convolutional ... -
Distributed Deep Learning in IoT: Splitting Neural Networks in Inference and Training
In this thesis, we first propose a scheme to solve the inference problem of Network of Neural Networks (NoNN) under changing channel conditions. The proposed scheme is composed of two methods: two devices work in parallel ... -
Deep Learning for Touchless Human-Computer Interaction using 3D Hand Pose Estimation
This thesis focuses on hand pose estimation (HPE) as a crucial component for human-computer interaction, for example in gesture-based control for physical or virtual/augmented reality devices. We start by introducing an ... -
Radial Voting Based Keypoint and 6DoF Pose Estimation
A novel keypoint voting scheme named radial voting based on intersecting spheres is proposed. It is more accurate than existing schemes and accepts a relatively smaller set of sparse keypoints. Radial voting forms the ... -
Miniaturized Antenna for Satellite Broadband Application
User antenna is a crucial component of a high-speed satellite internet system. High directivity, broadband characteristics, and circularly polarized radiations are essential for a user antenna to maintain a reliable ... -
Towards Efficient Hydraulic Manipulator Control using Learning-Based Model Predictive Control
Large-scale hydraulic manipulators are notoriously difficult to control due to the prevalent nonlinear and complex dynamics. As a result, automation and control of such machines has only proceeded as far as tele-operation. ... -
Enforcing Security on Autonomous Vehicle Searches Through the Quantification of Opacity
Recently, topics of security have been explored in the field of discrete-event systems (DES). By modelling these systems with DES, the evolution of the processes can be captured, allowing for different vulnerabilities to ... -
Planar Multilayer Thin Film Coatings for Passive Winter Thermal Management
Buildings are responsible for 40% of global energy consumption. 76% of that energy is spent on comfort control including heating, cooling and ventilation. This large energy consumption results in significant greenhouse gas ... -
Path Following using Frequency Modulated Continuous Wave millimetre-wave Automotive Radar
This thesis presents the discovery, methodology, and experimental validation of a path planning algorithm developed to only use Frequency Modulated Continuous Wave (FMCW) radar. Radar has shown to be semi-invariant to ... -
Efficient Process Arrival Pattern Aware Collective Communication for HPC and Deep Learning
High-Performance Computing (HPC) is the key to tackle computationally intensive problems such as Deep Learning (DL) and scientific applications. Message Passing Interface (MPI) is the de facto parallel programming standard ... -
High-Performance Interconnect-AwareMPI communication for Deep Learning Workloads
High-Performance Computing (HPC) refers to using aggregate compute power of many small compute nodes to solve large complex problems which cannot be computed in a reasonable time on a single computer. In recent ... -
Impact of Reinforcement Learning Enabled Smart Homes on Humans
Smart homes are becoming increasingly popular as a result of advances in machine learning and cloud computing. Devices such as smart thermostats and speakers are now capable of learning from user feedback and adaptively ... -
Wireless Sensing for Ground Engaging Tools
A long-standing industrial problem is tackled with an industrial internet of things (IIoT) application. This thesis presents the hardware design and development of a wireless sensor network for monitoring ground engaging ... -
Analytical and Experimental Study of Perturbed Abrupt Fiber Tapers and Their Sensing Applications
Optical-fiber sensors are vastly employed in sensing applications due to their immunity to electromagnetic interference, high sensitivity, environmental ruggedness, and compactness. The development of fiber-optics technology ... -
Fluidic Antenna Reconfiguration Methods and Multi-Antenna Systems for Next Generation Wireless Networks
This thesis explores the design of planar reconfigurable antennas (RAs) using novel fluidic methods and further builds upon them to realize multi-antenna systems. Distilled water is utilized as the dielectric fluid (DF). ...
RSS 1.0