Engineering Commons^™

Generating Energy Data For Machine Learning With Recurrent Generative Adversarial Networks, Mohammad Navid Fekri, Ananda M. Ghosh, Katarina Grolinger

Electrical and Computer Engineering Publications

The smart grid employs computing and communication technologies to embed intelligence into the power grid and, consequently, make the grid more efficient. Machine learning (ML) has been applied for tasks that are important for smart grid operation including energy consumption and generation forecasting, anomaly detection, and state estimation. These ML solutions commonly require sufficient historical data; however, this data is often not readily available because of reasons such as data collection costs and concerns regarding security and privacy. This paper introduces a recurrent generative adversarial network (R-GAN) for generating realistic energy consumption data by learning from real data. Generativea adversarial …

High-Pressure Studies On The Transition From Red Phosphorus To Black Phosphorus, Heng Xiang

Electronic Thesis and Dissertation Repository

Black phosphorus (BP) is a promising material in many research fields. However, the transition process from amorphous red phosphorus (ARP) is elusive and hence hinders large scale synthesis and applications. This work describes the application of the high-pressure method to study the transition process from ARP to BP.

In this thesis, the following three objectives were achieved: (1) to understand the mechanism of the transition, (2) to facilitate the synthesis of BP by taking the advantage of less pure ARP, (3) to propose new methods of synthesizing BP-based materials, such as the moderately oxidized BP and the black phosphorus/ amorphous …

Numerical And Semi-Analytical Estimation Of Convective Heat Transfer Coefficient For Buildings In An Urban-Like Setting, Anwar Demsis Awol

Electronic Thesis and Dissertation Repository

Urban building arrangements such as packing density, orientation and size are known to influence the microclimate surrounding each building. Studies on the impact of urban microclimatic changes on convective heat transfer coefficient (CHTC) from a stock of buildings, however, have been rare in surveyed literature. The present study focuses on numerical and analytical investigation of CHTC from building-like models with homogeneous set of equal and unequal planar and frontal densities. Consequently, the study discusses the CHTC response in relation to broader changes in the urban surface form. Part of the process involves the development of a simplified one-dimensional semi-analytical CHTC …

Characterization And Computational Modelling For The Garnet Oxide Solid State Electrolyte Ta-Llzo, Colin A. Versnick

Electronic Thesis and Dissertation Repository

The all-solid-state-battery (ASSB) serves as a promising candidate for next generation lithium ion batteries for significant improvements in battery safety, capacity, and longevity. Of the material candidates researched to replace the conventionally used liquid electrolyte, the garnet oxide Ta-LLZO (Li_6.4La₃Zr_1.4Ta_0.6O₁₂) has received much attention thanks to its high chemical and electrochemical stability, and ionic conductivity which rivals that of liquid electrolytes. While much investigation has taken place regarding the electrochemical performance of Ta-LLZO, much less is known about the micromechanics, including microstructural characterization, stress and strain development, and material failure …

High Strain Dynamic Test On Helical Piles: Analytical And Numerical Investigations, Mohammed Fahad Alwalan

Electronic Thesis and Dissertation Repository

Helical piles are currently considered a preferred foundation option in a wide range of engineering projects to provide high compressive and uplift resistance to static and dynamic loads. In view of the large capacity of large diameter helical piles, there is a need to determine their capacity using accurate and economically feasible testing techniques. The capacity of piles is usually determined by conducting a Static Load Test (SLT). However, the SLT can be costly and time consuming, especially for large capacity piles. The High Strain Dynamic Load Test (HSDT) evaluates the pile capacity using dynamic measurements generated through subjecting the …

Comparative Assessment Of Downscaling Methods And Application Towards Analysis Of Climate Change Impact On Urban Regions, Markus Eichenbaum

Electronic Thesis and Dissertation Repository

Global climate models (GCM) are sophisticated numerical models used to make long term climate projections. However, the resolution of their output is too coarse for climate change related local impact studies on urban regional scales. Downscaling efforts are taken to address this and increase GCM projection resolution. Physical Scaling (SP) downscaling methodology attempts to incorporate the physical basis of dynamical downscaling efforts with the computational efficiency of statistical methods. In this study, North American Regional Reanalysis surface skin temperature and precipitation data for a 1°x1° region centered on Houston, TX are downscaled to a resolution of 500m via SP and …

Novel Avenues Toward Controlling The Photophysical Properties Of Ultra-Small Silicon Quantum Dots, Mohammed Abdelhameed

Electronic Thesis and Dissertation Repository

Quantum dots (QDs) have attracted an increasing attention in the last decade over many conventional organic dyes. This is due to their unique optical properties including broad absorption spectra, high photostability, and size-tunable photoluminescence (PL). However, some toxicity concerns associated with traditional quantum dots have hindered their wide applicability. Interestingly, silicon quantum dots (SQDs) have been shown to be more advantageous than most of QDs thanks to their excellent biocompatibility and biodegradability, low cytotoxicity, and versatile surface functionalization capability. Thus, SQDs are promising candidates for various biological and biomedical applications such as bioimaging, biosensing, and photodynamic therapy. Unfortunately, only a …

Progress Toward Durable Icephobic Materials, Matthew J. Coady

Electronic Thesis and Dissertation Repository

Ice accumulation is a major engineering challenge in many fields including aerospace, power generation, transportation, and infrastructure. A variety of solutions are being researched to address this challenge. Perhaps the most promising method of combating ice accumulation is by applying coatings with low values of interfacial ice adhesion strength, τ_ice. Icephobic materials are those with ice adhesion below 100 kPa, and it has been shown that passive delamination can occur on surfaces with τ_ice below 20 kPa. While various low adhesion surfaces have been prepared, durability concerns pervade applications where surfaces experience repeated icing or freeze-thaw cycles, …

Similarity-Based Chained Transfer Learning For Energy Forecasting With Big Data, Yifang Tian, Ljubisa Sehovac, Katarina Grolinger

Electrical and Computer Engineering Publications

Smart meter popularity has resulted in the ability to collect big energy data and has created opportunities for large-scale energy forecasting. Machine Learning (ML) techniques commonly used for forecasting, such as neural networks, involve computationally intensive training typically with data from a single building or a single aggregated load to predict future consumption for that same building or aggregated load. With hundreds of thousands of meters, it becomes impractical or even infeasible to individually train a model for each meter. Consequently, this paper proposes Similarity-Based Chained Transfer Learning (SBCTL), an approach for building neural network-based models for many meters by …

Shape-Controlled Nanoparticles As Effective Catalysts For Proton Exchange Membrane (Pem) Fuel Cells, Ali Feizabadi

Electronic Thesis and Dissertation Repository

Polymer electrolyte membrane fuel cell (PEMFC), is considered a promising candidate for the next generation power sources in transportation, stationary and portable applications. However, oxygen reduction reaction (ORR), one of the key reactions occurring on PEMFC is kinetically slow; this has limited performance and further advancement in this kind of fuel cells. Thus, improving the PEMFC efficiency requires a thorough understanding of the ORR mechanism on the desired catalyst. To address the above-mentioned demands, the scope of this thesis is focused on the fundamental understanding of facet-controlled nanoparticles, metal-support interactions, and bimetallic platinum catalysts, utilizing synchrotron-based X-ray absorption, X-ray photoelectron …

The Effect Of Stiffness Anisotropy Of A Glacial Clay On The Behaviour Of A Shallow Wind Turbine Foundation, Jesús A. González-Hurtado

Electronic Thesis and Dissertation Repository

Shallow wind turbine foundations are designed based on investigations of the ultimate, serviceability and fatigue limit states. The serviceability limit state design approaches in particular are based on simple isotropic elastic half-space analyses that ignore coupling between loading directions, and soil non-linearity and elastic anisotropy. Many of the wind farms in Ontario are constructed around the Great Lakes basin and a number of these areas are characterized as stiff clayey glacial tills. It is recognized that many of these glacial materials exhibit some degree of strength, stiffness and fabric anisotropy. This research aimed to characterize the anisotropic geotechnical properties of …

Forecasting Building Energy Consumption With Deep Learning: A Sequence To Sequence Approach, Ljubisa Sehovac, Cornelius Nesen, Katarina Grolinger

Electrical and Computer Engineering Publications

Energy Consumption has been continuously increasing due to the rapid expansion of high-density cities, and growth in the industrial and commercial sectors. To reduce the negative impact on the environment and improve sustainability, it is crucial to efficiently manage energy consumption. Internet of Things (IoT) devices, including widely used smart meters, have created possibilities for energy monitoring as well as for sensor based energy forecasting. Machine learning algorithms commonly used for energy forecasting such as feedforward neural networks are not well-suited for interpreting the time dimensionality of a signal. Consequently, this paper uses Recurrent Neural Networks (RNN) to capture time …

Future Changes Of Hydroclimatic Extremes In Western North America Using A Large Ensemble: The Role Of Internal Variability, Mohammad Hasan Mahmoudi

Electronic Thesis and Dissertation Repository

Increases in the intensity and frequency of extreme events in Western North America (WNA) can cause significant socioeconomic problems and threaten existing infrastructure. In this study we analyze the impacts of climate change on hydroclimatic extremes and assess the role of internal variability over WNA, which collectively drain an area of about 1 million km². We used gridded observations and downscaled precipitation, maximum and minimum temperature from seven General Circulation Models (GCMs) that participated in the Coupled Model Intercomparison Project Phase 5 (CMIP5) and a large ensemble of CanESM2 model simulations (CanESM2-LE; 50 members) for this analysis. Spatial …

Seismic Landslide Hazard Mapping For Greater Vancouver, British Columbia, Ali Fallah Yeznabad, Sheri E. Molnar, Hesham M. El Naggar

Western Research Forum

The lower Mainland of southwest British Columbia (BC) hosts about 3.5 million people and significant infrastructures of national importance. Southwestern BC has the highest seismic risk in Canada with significant potential to cause earthquake-induced hazards including tsunamis, liquefaction and landslides. A Cascadia mega-thrust (M_W 9) earthquake is predicted to generate $75 billion Canadian dollars in losses. This damage can be resulted from ground shaking or its secondary phenomena like landslides; ground shaking during earthquakes may trigger landslides that can damage or destroy buildings, bury roads and highways and kill and injure people. In Canada, during the past century and …

Development Of In Situ Forming Hydrogels For Intra-Articular Drug Delivery, Andy Prince

Electronic Thesis and Dissertation Repository

Hydrogels are 3-dimensional crosslinked polymer networks that can absorb significant amounts of water. The physical properties associated with hydrogels affords them resemblance to biological tissues making them good candidates for biomedical applications. Many pharmaceuticals, specifically non-steroidal anti-inflammatory drugs (NSAIDs), have poor aqueous solubility, which limits their bioavailability and efficacy. People suffering from chronic osteoarthritis (OA) are required to frequently take large doses to mitigate pain, which can lead to serious side effects. Hydrogels are good strategies to deliver NSAIDs via articular injection because they can form solid gels in situ. This thesis describes the synthesis, formulation, mechanical testing, in …

Dynamic Light Scattering Optical Coherence Tomography To Probe Motion Of Subcellular Scatterers., Nico J J Arezza, Marjan Razani, Michael C Kolios

Medical Biophysics Publications

Optical coherence tomography (OCT) is used to provide anatomical information of biological systems but can also provide functional information by characterizing the motion of intracellular structures. Dynamic light scattering OCT was performed on intact, control MCF-7 breast cancer cells and cells either treated with paclitaxel to induce apoptosis or deprived of nutrients to induce oncosis. Autocorrelations (ACs) of the temporal fluctuations of OCT intensity signals demonstrate a significant decrease in decorrelation time after 24 h in both the paclitaxel-treated and nutrient-deprived cell groups but no significant differences between the two groups. The acquired ACs were then used as input for …

Deep Learning: Edge-Cloud Data Analytics For Iot, Katarina Grolinger, Ananda M. Ghosh

Electrical and Computer Engineering Publications

Sensors, wearables, mobile and other Internet of Thing (IoT) devices are becoming increasingly integrated in all aspects of our lives. They are capable of collecting massive quantities of data that are typically transmitted to the cloud for processing. However, this results in increased network traffic and latencies. Edge computing has a potential to remedy these challenges by moving computation physically closer to the network edge where data are generated. However, edge computing does not have sufficient resources for complex data analytics tasks. Consequently, this paper investigates merging cloud and edge computing for IoT data analytics and presents a deep learning-based …