Department of Electrical and Computer Engineering
Browse by
Recent Submissions
-
EVALUATION OF RADIOMICS AND MACHINE LEARNING IN IDENTIFICATION OF AGGRESSIVE TUMOR FEATURES IN RENAL CELL CARCINOMA (RCC)
(2020)The purpose of this study was to evaluate the use of CT radiomics features and machine learning analysis to identify aggressive tumor features, including high nuclear grade (NG) and sarcomatoid (sarc) features, in large ... -
Computational Investigation of Starting Characteristics of An Induction Machine
(2020)An induction machine consumes a very high inrush current during start-up, which can be potentially damaging to the machine itself and to the appliances connected. In the past, various studies focused on analytical and ... -
Designing Efficient Barriers and Semaphores for Graphics Processing Units
(2020-05)General-purpose GPU applications that use fine-grained synchronization to enforce ordering between many threads accessing shared data have become increasingly popular. Thus, it is imperative to create more efficient GPU ... -
Understanding Siamese Networks for Visual Object Tracking
(2020-08)Visual tracking of an arbitrary object has drawn great attention in the computer vision community for years. Visual object tracking methods based on Siamese networks achieved state-of-the-art results with balanced accuracy ... -
Machine Learning Approach to Event Detection for Load Monitoring
(2019)Today’s Electricity market is highly interconnected. The actions of customers, transmission and distribution systems, generation systems, markets, and service providers are correlated. The dynamic stability of the grid ... -
A Simplified Approach to High Performance Computing in Power Flow Analysis
(2017)The power grid is a complex network interconnecting energy sources with loads. The power flow and state estimation problems model the power flows and voltages throughout the grid. They are currently solved using computer ... -
Robust Budget Allocation
(2019)We consider at the problem of optimal budget allocation, where we are given a fixed budget to distribute amongst sources in order to maximally influence targeted individuals. In practice, situations may arise where the ... -
Locational Effects of Variability of Power Generation and Loads on Total Cost of Power Systems
(2015)In this thesis locational prices associated with power injection variability are introduced. Using a probabilistic DC optimal power flow (DC-OPF), the sensitivity of uncertainty in injected power on system cost is calculated. ... -
New Frontiers for Blackout Prevention: A Study of the Vulnerability Frontier and its Use for Contingency Analysis and Reliability Assessment
(2019)From infrastructure to healthcare to national security, global dependence on bulk power systems has never been more critical-placing reliability at a premium. Disruptions to power are consequential, and data on the frequency ... -
Single Rotor, Dual Stator Axial Flux Permanent Magnet Motor Design, Analysis and Test
(2019)The Axial Flux Permanent Magnet (AFPM) motor is a unique machine topology which possesses advantages over Radial Field Permanent Magnet (RFPM) machines. Over the last several decades this uniqueness has garnered interest, ... -
Cooling design and thermal analysis for dual-stator 6-slot 4-pole flux-switching permanent magnet machine
(2017-09-26)This research report focusses on the thermal management of the electrical machine, which is another important aspect of the machine design. The machine components are often influenced by the variation of temperature, ... -
Implementation of a DC Microgrid
(2017-05-31)The first permanent electric grid powered only the homes and buildings in its immediate vicinity–much like microgrids, which are presently the focus of intense research and development. An area holding great promise for ... -
Improving Video Transportation over Dynamic Wireless Networks
(2017-05-22)This thesis explores video transfer over dynamic wireless communication links in an attempt to understand current limitations and propose new methods to push performance beyond the existing envelope. To this end, I spent ... -
One-shot Unsupervised Learning for Improved Human-Robot Collaboration
(2017-05-16)As robots become commonplace in human environments such as households and manufacturing facilities, they require new control methods for e↵ectively collaborating with their human partners in common pick-and-place tasks, ... -
Automated Feature Analysis in Biological Images
(2017-05-11)This thesis is comprised of three projects that I worked on during the period of my Master of Science degree. All three projects use computer vision and image processing techniques to improve microscopy image analysis ... -
Model of Two-Phase Motor and Compressor for FIDVR Analysis
(2017-05-10)The main focus of this research is dynamic load modeling for Fault Induced Delayed Voltage Recovery (FIDVR). FIDVR is the phenomenon whereby the system voltage remains at uncontrolled reduced levels for several seconds ... -
Some Applications of Machine Learning in Edge Computing, Wireless and Mobile Systems
(2017-02-27)Recent advancement in Deep Learning for Image Classification and Perception tasks have contributed to incredible advancements in consumer technology. Devices such as Google Home, projects such as self-driving cars are now ... -
Capacitive Power Transfer Through Rotational and Sliding Bearings
(2017-01-05)Throughout the history of electrification, applications have existed for the transmission of electrical energy from stationary sources to moving loads. Electrical equipment which is expected to move along tracks, or in ... -
Integrated Inductors and Capacitors with Co-Located Electric and Magnetic Fields
(2017-01-05)Passive components such as inductors and capacitors are fundamental components needed in all power electronics converters, and in many designs, they comprise a significant portion of the total weight and volume of the ... -
A Dynamic Tariff Market Design for Electrical Energy in a Distribution System
(2016-09-08)The work in this thesis is motivated by the need to design an energy marketplace for use in a Dynamic Distribution System. The Dynamic Distribution System is a proposed techno-economic approach to increased penetration of ...