Reducing Training Data Requirements with Cognitive Cues

The aim of this project is to allow for Deep Learning approaches utilized by Eye For Infrastructure to rely less heavily on labelled training data as well as to produce more human-understandable and actionable results. The improved system would allow for a seamless integration with municipalities for automated infrastructure assessment.

DEEP LEARNING (DL) BASED APPLICATION FOR FRESH PRODUCE YIELD AND PRICE FORECASTING BASED ON SATELLITE IMAGES AND STATION-BASED PARAMETERS

Loblaw Companies Limited (LCL) supplies all fresh produce (FP) to South Western Ontario stores from Waterloo Distribution Center (DC). DC decides prices and quantities to meet FP demand. Timed fair priced orders minimize waste, bring prosperity to growers, consumers and FP trades. Factors affecting prices are highly uncertain due to environmental and socio-economic effects such as income, labor, trade, globalization and climate change which makes price prediction challenging.

Advanced Building Performance Analysis Tools for Computation Design of Building Envelopes

An early-stage design analysis methodology will be investigated for evaluating preliminary building envelope design alternatives using advanced computation and analysis tools. Design alternatives will be generated based on different envelope materials, structure, insulation types and window-to-wall ratios and evaluated based on selected metrics including energy use, daylighting, life cycle analysis and life cycle costing. A master-planning project in Mississauga, Ontario, will be used as a test-bed for the methodologies explored in this research.

Developing an aptamer, graphene based electrochemical biosensor for early detection of Alzheimer disease.

At least 50 million people are living with Alzheimer disease (AD) worldwide and the number is estimated to grow to 150 million by 2050 making it a global epidemy. AD in the sixth cause of death in north America and its estimated cost of caring is $277 billion yearly, yet no cure is available for AD. This is partly because current diagnostic techniques are expensive- ranging from $1500 to $6000- or invasive- require lumbar punctures-, which makes early screening and disease monitoring difficult.

Evaluation & sensitivity study of behind-the-meter load disaggregation methods

Solar energy generation at commercial and industrial sites has been gaining popularity in recent years. The addition of batteries to existing solar installations can allow for solar to not only be used during the day when the sun is out, but also at night. There however, are various hurdles to this process specifically involving the transparency of the data coming from the solar unit. Several methods have addressed this issue at residential sites and offer promising results.

Vapor-phase metal additive manufacturing

Additive manufacturing (AM, or 3-D printing) with metals is a rapidly growing field catalyzing a revolution in modern manufacturing. The most common approach involves the use of metal powders as a feedstock material. The proposed research program will use metalorganic gaseous precursors such as Ni(CO)4 and Fe(CO)5 which facilitate low temperature (~200 C) deposition, forming solid metal deposits utilizing infrared light radiation-based heating.

Awechigewin: Developing a Virtual Approach to Community-Based Planning with Michipicoten First Nation

The proposed research project will use a combination of Participatory Action Research and Indigenous Research Methods to create an online engagement tool to gather Michipicoten First Nation (MFN) member’s perspectives on draft planning strategies and policies regarding six priority areas. Engagement is a challenge for MFN as a displaced and widely dispersed community, challenges which are heightened by the COVID-19 pandemic. Online engagement is an important tool for reaching Michipicoten citizens on- and off-reserve, particularly during the pandemic.

Development of Durable Ultra-low-Pt-loading Catalyst Layers for Polymer Electrolyte Membrane Fuel Cells

Catalyst layers (CLs) determine the performance, durability, and cost of PEM fuel cells. The proposed research will focus on developing durable ultra-low-Pt-loading CLs with high performance and durability. The novel CLs will be fabricated by sputtering Pt onto a thin layer of carbon particles, pre-deposited on the membrane. The CL structure will be investigated by SEM, TEM, and the method of standard porosimetry. Electrochemical and mass transport properties will be characterized by cyclic voltammetry, electrochemical impedance spectroscopy, and Loschmidt Cell.

Bioprocessing strategies for enhanced production of heme in Escherichia coli

Ardra Inc. has sustainably produced many high-purity chemicals that are used for various flavor, perfume, and cosmetic applications. Combining industrial/business expertise provided by Ardra with academic/research skills provided by Dr. C. Perry Chou’s lab, we are aiming to effectively produce high-value heme compound using engineered E. coli host organism. Major efforts will be dedicated toward engineering of this bacterium by adopting synthetic biology, metabolic engineering, and bioprocessing strategies to facilitate large-scale bio-based production of heme.

Solid state electrode development for Li-ion batteries

Reducing fossil fuel use in transportation and utility scale electricity sectors is required to meaningfully reduce anthropogenic carbon emissions and to improve air quality in urban and industrial centres. Lithium ion batteries are beginning replace combustion engines for transportation applications, and show promise as tools that allow power utilities to seamlessly integrate intermittent carbon-free energy sources (i.e. windmills and solar panels) into the electricity grid.

Pages