Innovative Projects Realized

Développement d’un système de désempêtrement autonome des baleines noires prises dans les cordages verticaux des casiers à crabe des neiges

Le projet consiste à concevoir des liens faibles intégrés dans les cordages des casiers à crabe des neiges pour permettre aux baleines noires qui s’y font piéger de se libérer d’elles-mêmes. Les liens faibles sont des maillons fragiles qui cèdent lorsque la baleine exerce une force quand il se sent pris dans les cordages. Ce système va prévenir les baleines noires des séquelles que peut engendrer un empêtrement qui affecte sa santé qui, dans certains cas, lui est fatal. Pour développer un tel système, la propriété fragile de certains matériaux est exploitée pour constituer un système de fusible mécanique lors qu’une force est appliquée soit la charge exercée par la baleine pour le cas de notre étude.

UV Mapping Assistance through Deep Learning

The goal is to create a conversation loop between 3D designers and artificial intelligence programs. This will help the AI provide suggestions to the designer, while the designer provides the AI with feedback. This can help make it easier for designing complicated objects as well as complicated textures that belong to the surface of 3D objects. Through this interaction, the hope that AI can extend the utility of design software.

Effect of chemical composition on machining of Inconel 625/718 components by machine learning and microstructural analysis

APN in Quebec City faces a high fluctuation of the lifespan of tools in machining operations such as milling and turning. This hampers production planning, since the number of necessary tools for a job as well as their lifetime cannot be well predicted. Previous investigation on this challenge could not determine a reason for this phenomenon. Therefore, the objective of this project is to identify a correlation between the available process data such as material properties and machining parameters with the length of tool life. A special focus lies in the chemical composition of the materials used for the machining of the parts, superalloys Inconel 625 and Inconel 718, and its effect on machinability. In addition, different Machine Learning algorithms will be trained on historic data to allow predictions on tool changing intervals in the future.

Southern Perspectives on Socio-Legal Education and Research

Internationalization is a key aspect in strategic planning of most of top universities across the globe. This proposal aims to collect documents and observe (institutional ethnography methodology) two winter courses promoted by the “Universidad Nacional del Litoral” (UNL, Argentina). Winter courses are a milestone in the internationalization process of the UNL and interestingly they are oriented towards South-South and South-North relations, a design rarely observable in Global North universities. The proposal will focus on the following research question: how far can those winter courses go in the production and circulation of knowledge from the South to an international set of attendants? This proposal is related to my PhD research, which explores the presence and circulation of knowledge from the South in PhD programs in Law at highly internationalized universities in Canada. I expect that the Argentinean data will provide an interesting contrast, helping me to nuance the results of my research in Canada.

Iron Removal In vivo Study (IRIS)

Infections and inflammation of the eyes are becoming increasingly prevalent problems for patients

with chronic diseases or for people who use implanted eye lenses. Serious ocular infectious and

inflammatory disease can lead to significant visual disability and requires aggressive treatment

intervention to mitigate disease pathology and prevent vision loss. Preliminary work suggests that ironchelating

agents developed by Chelation Partners Incorporated can effectively control microbes and

inflammation. These excipients can enhance the power of antibiotics, especially in clinically resistant

infections, dampen inflammation and reduce the need for harsh preservatives. Studies will be designed

to: (i) evaluate the safety of the excipients, (ii) determine the ability of these agents to control

inflammatory response in the eye (iii) examine the ability of these agents to limit eye infections or their

ability to enhance the anti-microbial activity of antibiotics. Results of these studies will be valuable in

assessing the safety and efficacy of these iron-chelating agents in vivo (in animals) prior to their TOBECONTINUED

Covalent and non-covalent interactions self-supervised representation of molecules for chemotherapeutic drug design

Most of the drugs used to treat cancer have been originally identified from natural sources. While Nature did a great job selecting those compounds, some of them have shown limitations in the treatment of cancer and others have shown to be insufficient on some cancer types. Furthermore, it exists a gigantic number (nearly infinite) of small molecules human can synthetize. The goal of this project is to use existing machine learning technics and novel input representation approaches in order to efficiently search in this gigantic chemical space, newly potential molecules that could be used as new chemotherapeutic drugs.

Synthesizing the State of Practice of On-Demand Transit in Canada

This project proposes a survey directed at transit agencies in Canada that have operated, operating, or planning to operate flexible transit, with special emphasis placed on app-based on-demand transit services. Personal interviews will be conducted with key personnel at the transit agencies, likely using phone communication. The results of the survey along with a more comprehensive review of industry reports will be summarized to highlight the key practices of flexible transit in Canada. With the increased interest in technology and automated operations, this study will also approach technology and software companies that usually provide the software for scheduling and dynamic routing application to support flexible transportation services.

Dynamic Credit Scoring

Banks use a myriad of methodologies to inform their officers on credit extension decisions. One of the most employed approach is to summarize borrower creditworthiness by credit scores, which in turn depend on loan default probabilities. The probability of default depends both on borrower characteristic and on the overall state of the economy. The goal of this project is to create credit scores that are responsive to the expected state of the economy. The core idea is to establish the link between default probabilities and borrower characteristics separated in good and bad-market state scenarios. These good/bad-market-states scores are then combined using forecasts of the probability of the economy falling in either scenarios. The output is dynamic credit scoring for borrowers characteristics.

Forecasting Ability of Non-consumer Scorecards and their Ability to Predict Probability of Default

International Financial Reporting Standards (IFRS) for loss allowances are changing, and financial institutions are proactively adapting existing methodologies and developing new ones to remain compliant. The main ingredient in the myriad of evaluations that banks are required to perform for compliance is risk assessment. The first goal of this research project is to review best practice risk models, with a special focus on modeling the evolution of default probabilities. In particular, the project evaluates the forecasting ability of internally credit ratings of borrowers in predicting probability of default. The linkage between internal scores and probability of default will be explored using a classical statistical approach (re-logit) and a methodology stemming from recent advances in machine learning (random forest with undersampling).

“Transit Gender Sunshine List”: Assessment of Representation of Women as CEOs and Directors of Canadian Transit Systems

CUTRIC, in partnership with the University of Windsor are seeking greater understanding of the barriers to participation which have resulted in the low representation of women within the leadership ranks of Canadian transit systems. To better understand this lack of representation, a literature review will be conducted to ascertain what knowledge exists in this field and will be used to provide a foundation for the next steps of the research. Following this, interviews and focus groups with members of transit system leadership will be conducted to discover which barriers exist within this industry. Comparative analyses with U.S. and relevant mobility sector cohorts will be conducted. This research will help CUTRIC to better understand and address systemic barriers within transit systems and increase the representation of women within this industry.

Gated and RGB Fusion for Robust Perception

Robust perception in all weather conditions is a critical requirement for autonomous vehicles. This project proposes fusing gated and conventional RGB camera images for robust scenes encoding, depth estimation and trajectory prediction. Conventional approaches using lidar and RGB camera fail to perform robustly in rain, fog and snow. By extending existing computer vision algorithms to Gated-RGB camera pair the fusion algorithms developed will utilize features that are robust in one sensor modality but not the other. The proposed projects will allow Algolux to evaluate different fusion algorithms and augment the existing captured dataset with simulated data that are useful for algorithm development and evaluation.

3D Visualization Pipeline and Methodology for Large-Scale Artifact Collections Management

This project will develop the protocols, standards and procedures to establish a digitized, virtual artifact repository, accessible online for research and public education, by establishing the processes for large scale digitization of the analyzable objects representing the full range of the compiled archaeological heritage from Ontario.