Innovative Projects Realized

Statistical aspects of Optimal Transport

This proposal explores the use of optimal transport in statistics and machine learning as well as develop one simple application in chemistry. Optimal transport is a well established mathematical field whose actors have gone to receive the most prestigious recognitions. Its inventor, Leonid Kantorovich, received the Nobel Prize in Economics. Cedric Villani, who wrote the two most notable books on the topic, received the Fields Medal in 2010 and, more recently, another Fields Medal was awarded to Alessio Figalli for his work on optimal transport.

Beyond its mathematical depth, optimal transport has become a preponderant tool in many applications where data can be represented as probability distributions (images, point clouds, curves, word counts, etc). This useful feature translates into powerful tools ranging from clustering to dimension reduction.

A central goal of this MITACS project is to train the students to work on Statistical and Computational aspects of optimal transport by facing problems at the interface of Mathematics, Statistics and Data Sciences.

Méthode robuste d’estimation de la capacité d’effacement local des charges résidentielles

La gestion de la demande de puissance électrique (GDP) est un outil émergent pour les opérateurs de réseaux électriques. À l’heure actuelle, au Québec sous la bannière d’Hilo, on l’utilise principalement pour diminuer la pression sur le réseau lors des périodes de grande consommation comme les pointes hivernales. Dans ce projet, on cherche à développer les outils nécessaires pour utiliser la GDP à des fins plus sensibles, comme la coordination d’activités de maintenance dans un poste de distribution, où on a besoin de garantir, avec une certaine précision, la quantité de puissance qui sera effacée à un mo-ment précis et pour un lieu défini. Ces avancées permettront à Hilo d’à la fois diversifier son soutien au réseau en offrant un service sur mesure à Hydro-Québec, mais aussi d’augmenter les opportunités de récompense pour ses utilisateurs.

Cross-functional teams to develop and commercialize AI-powered solutions – Part C

AltaML is an innovative company capitalizing on a major technological trend: artificial intelligence (AI) technologies, enabled by big data, are driving a fourth industrial revolution. AI will transform all industries, but traditional industries face challenges in implementing AI. AltaML has a unique business model to overcome barriers to adoption of AI solutions by industry, which is to bring the innovating startup together with the large organization, thereby bringing together rich datasets, AI talent with a playbook for industry application and the close collaboration of subject matter experts and AI experts–with a mindset for change. In addition to AI expertise, we bring agility that our large, corporate partners often lack, and which is so essential for innovation. With a strategic focus on AI adoption and product, AltaML works across industries as well as with the public sector using a co-development approach to create applied AI solutions as well as joint AI ventures. This rich, complex multisectoral environment provides the breadth that enables insights in one area to be applied in new areas, leading to ever increasing opportunities for innovation.

The project comprises internships in a variety of technical and business roles, which are: associate machine learning developer, business development associate, communications associate, finance associate, associate business solutions consultant, and project delivery associate. Outcomes will include algorithm creation and deployment, data visualizations, market research reports, sales collateral, competitive landscape analysis, feasibility analysis; key messages and content writing such as case studies and feature articles, financial model development, data analysis, financial reports and variance analysis, customer workflow mapping, business case reports, resource allocation plans, project update reports, and project plans.

Pattern matching for definite summation in Maple

The proposed project is to design and implement a pattern matching based method for definite symbolic summation in. To remain competitive, Maple’s symbolic computation capabilities, which are one of its strengths, need to be improved constantly. This includes the ability to symbolically evaluate definite sums. Closed forms for definite sums are important in many applications, e.g., special functions, combinatorics, as well as first- and second-year university analysis courses, and even particle physics. Since new algorithms for symbolic summation that target more general classes of inputs are high effort to implement, and the benefits of doing so are not so clear, a pattern matching based approach seems like the quickest way to extend Maple’s symbolic summation capabilities, closing the gap between Maple’s integration capabilities (which already uses pattern matching) and summation capabilities (that are mostly pure algorithmic).

Forestry Co Op Student

The intern will assist on a range of planning & operations projects in the office and field. They will scout and evaluate sites in the field for timber volumes for utility, & forestry clients, conduct hazard tree assessments and salvage planning on utility lines, review stakeholder agreements & obtain landowner access consents, and prepare reports and GIS maps with resulting data for regulatory and client approval.

Occupational; Health and Safety

The SDI Group was founded by Mr. David A. Williamson in 2006 focusing on providing “Safety Design and Innovation”, exceptional service through partnership and innovation. SDI Group has 10 Divisions and more recently, in seeing the need for more innovative ways to service the clients opened up SDI Mobile Company with majority owner, Rosalie Gray who is a First Nation member of Enoch Cree Nation. Moreover, in partnership with our clients SDI strives to find solutions that meet non-traditional needs. We build and manage customized systems for clients in many sectors that enhance their current business model. Together our staff serve over 150 partnerships across North America. We are CRSP’s (Canadian Registered Safety Professionals) along with our team of Audiometric and Substance Screening technicians. Whether it is certified COR Auditors, Trainers or Occupational Hygiene, the SDI Group supports all organizations to meet their goals.

During their four month intern they will be engaged in several objectives both within SDI and for our client base. Our challenge and opportunity are to review key clients health and safety management systems and provide solutions on where we can improve performance. This is through training and procedural updates.

First and Last Smiles: Consumer Experiences of Fun in E-Scooter Adoption

This research project aims to understand what factors are driving the increased usage of shared micromobility vehicles – e-scooters – in city centres. In particular, this research seeks to understand the notion of fun as it influences how people chose to get around within a city. The findings of this inquiry will help cities understand and in turn be better prepared in planning for and in incorporating new modes into transportation strategies. Ultimately, this research intends to help cities become more integrated and better equipped to meet demands around sustainability, congestion, affordability and increased population density. In partnering with Candler Chase Inc. to complete the research project, the results will provide new avenues of revenue and relevance among their client group.

The Impact of Ether Ring Formation via Mechanochemistry

Mechanochemistry uses physical, mechanical mixing in order to break and forms bonds in solvent-free conditions, which can yield different mechanistic outcomes compared to the traditional solution-based method. The highly concentrated mixing of reagents would be typically the last method thought to synthesize medium-sized ether rings, as the molecules require high dilution to promote ring closure and prevent unintended polymerization. However, solid mixing can orientate selectively based on weak interactions that may be negligible in a stirring solution. This project hopes to explore the viability of preparing small to medium ether rings by ball-milling. Ring closing is a common strategy in drug development and if this proves possible, a new branch of organic synthetic mechanochemically will emerge. Investigating alternative and environmentally-friendly methods of standard reactions is crucial as the global pandemic has highlighted the instability and huge price spike in the supply of solvents that Canada currently relies on to continue the production of medicine and research.

Cross-functional teams to develop and commercialize AI-powered solutions – Part A

AltaML is an innovative company capitalizing on a major technological trend: artificial intelligence (AI) technologies, enabled by big data, are driving a fourth industrial revolution. AI will transform all industries, but traditional industries face challenges in implementing AI. AltaML has a unique business model to overcome barriers to adoption of AI solutions by industry, which is to bring the innovating startup together with the large organization, thereby bringing together rich datasets, AI talent with a playbook for industry application and the close collaboration of subject matter experts and AI experts–with a mindset for change. In addition to AI expertise, we bring agility that our large, corporate partners often lack, and which is so essential for innovation. With a strategic focus on AI adoption and product, AltaML works across industries as well as with the public sector using a co-development approach to create applied AI solutions as well as joint AI ventures. This rich, complex multisectoral environment provides the breadth that enables insights in one area to be applied in new areas, leading to ever increasing opportunities for innovation.

The project comprises internships in a variety of technical and business roles, which are: associate machine learning developer, business development associate, communications associate, finance associate, associate business solutions consultant, and project delivery associate. Outcomes will include algorithm creation and deployment, data visualizations, market research reports, sales collateral, competitive landscape analysis, feasibility analysis; key messages and content writing such as case studies and feature articles, financial model development, data analysis, financial reports and variance analysis, customer workflow mapping, business case reports, resource allocation plans, project update reports, and project plans.

Signals of Opportunity-based Positioning Techniques for Challenging GNSS Environments Year Two

The availability and accuracy of GPS in some environments, such as indoors, is limited. Positioning utilizing radio frequency (RF) signals intended for communication, broadcasting, or networking is an attractive alternative or complement to GPS in such environments. The proposed research will develop novel methods to use RF signals of opportunity (SoO), such as WiFi signals and cellular telephone signals, for accurate and robust positioning in GPS challenged environments. This necessitates an investigation of the effects of RF signal characteristics on positioning performance. Detailed mathematical models will be developed to compensate for the negative impacts of such characteristics on positioning performance. The sponsoring company (RxNetworks Inc.) is deeply involved in utilizing SoO for positioning. This research will directly contribute to algorithmic improvements required by the company to enhance the accuracy and robustness of its SoO based positioning products. The development of such algorithms is of utmost importance to the company.

Machine Learning Developer intern within cross-functional teams to develop and commercialize AI-powered solutions – Part 4

AltaML is an innovative company capitalizing on a major technological trend: artificial intelligence (AI) technologies, enabled by big data, are driving a fourth industrial revolution. AI will transform all industries, but traditional industries face challenges in implementing AI. AltaML has a unique business model to overcome barriers to adoption of AI solutions by industry, which is to bring the innovating startup together with the large organization, thereby bringing together rich datasets, AI talent with a playbook for industry application and the close collaboration of subject matter experts and AI experts–with a mindset for change. In addition to AI expertise, we bring agility that our large, corporate partners often lack, and which is so essential for innovation. With a strategic focus on AI adoption and product, AltaML works across industries as well as with the public sector using a co-development approach to create applied AI solutions as well as joint AI ventures. This rich, complex multisectoral environment provides the breadth that enables insights in one area to be applied in new areas, leading to ever increasing opportunities for innovation.

The project comprises internships in a variety of technical and business roles, which are: associate machine learning developer, business development associate, communications associate, finance associate, associate business solutions consultant, and project delivery associate. Outcomes will include algorithm creation and deployment, data visualizations, market research reports, sales collateral, competitive landscape analysis, feasibility analysis; key messages and content writing such as case studies and feature articles, financial model development, data analysis, financial reports and variance analysis, customer workflow mapping, business case reports, resource allocation plans, project update reports, and project plans.

Going Beyond Thin Credit, the use of Account Data

The business partner is interested in finding ways to further automate small business lending and annual renewals. In recent years, with the improvement in efficient computing and data storage and movement, the use of deposit data in lending has become more prevalent in the industry. Within industry risk managers, it is widely accepted that deposit account information has a strong predictive ability for predicting borrower risk level. However, there are no widespread industry tools similar to credit scores making use of deposit data. This project aims to employ machines techniques to develop credit scores based on deposit lending data.