Projets novateurs réalisés

Summer Analyst – Impact Investing, Acceleration, and Advisory – Western University

The Social Innovation Academy will be working with a network of Mitacs interns to develop national-scale backend infrastructure resources for incubation and acceleration organizations across Canada. These resources may include (but are not limited to): initiatives for advancing equity, diversity, and inclusion; impact measurement frameworks; In addition, interns will provide marketing, research, and financial analysis for social purpose organizations over the duration of the 14-week internship.

Development of a Social Innovation Franchising Model

Create a Social Innovation Franchising (SIF) model for CMIM
CMIM would like to expand their operations regionally and nationally to provide programming to students across all of Canada through what is called social franchising. The social franchising model is defined as using entrepreneurial principles that make up traditional franchising to create, organize and manage a venture to solve a social problem — in this case, inequity within the education system, the employment sector, and entrepreneurial streams.

Digital Health Northwestern Ontario 1: Implementing a User Engagement Platform

Electronic Health Records (EHR) are the digital collection of a patient’s health information. EHRs can benefit clinicians, healthcare administrators and patients through the use of information technologies to manage various aspects of healthcare. These investments require sustained efforts to engage a multitude of stakeholders, and allow them to seek opportunities to automate, integrate and digitize healthcare processes. Thunder Bay Regional Health Sciences Centre (TBRHSC) is upgrading its EHR shared among 12 regional hospitals across a sparse geography. The success of the new system requires unprecedented levels of stakeholder engagement where traditional approach may not be effective.

This project seeks to 1) implement a crowdsourcing platform to continuously engage stakeholders of this project, 2) design and implement data visualizations and reports to monitor and report the usage, performance and results, and 3) document several types of end user engagement and provide instructions for future use in engagements.

Usability Testing will be employed in this project, where the intended users will perform specific tasks in this new system. This will help identify potential problems and improvement for the system, and also reveal insights as to the effectiveness of the platform.

Analyzing and reporting team dialogue to enhance psychological safety

The proposed project will be to examine Reticle Ventures Canada Incorporated’s (Reticle) current way of coding and reporting on team psychological safety and validating their end-to-end system against current validated psychological safety measures. The overarching goal is to establish content validity of their current system by assessing whether their current framework is measuring what it is supposed to be measuring in line with current research. This will consist of three primary activities. First, developing a rigorous and effective reporting and debriefing process for teams to better understand their current level of psychological safety. Second, creating one individual psychological safety measure using current validated measures that are aligned with the Reticle framework to establish content validity. Third, develop and plan the validation study to begin in Winter 2023. The expected benefits to the partner organization is an improved system that is evidence-based that encompasses all of the current standards for psychological safety and team functioning.

Using design thinking to Improve operational efficiency of a consumer health-tech product so it can scale and help Canadians avoid chronic disease

Molecular You is a health-tech start-up on a mission to help people live longer, healthier lives.

Using a new type of blood test, we’re able to give people unparalleled insight into their health and make precise diet, exercise and supplement recommendations to help them live longer healthier lives. The product consists of a mobile application and some powerful operational software systems that manage blood samples, ingest data, ensure data quality and allow us to derive new health insights from the data. The users of these systems are our operations team, quality management team, data science team and the user-facing app itself.

These operational software systems are too labour-intensive for us to scale. So we need to invest in creating more automated and efficient workflows. This project with MITAC will allow us to uncover the biggest pain points for our internal users and design better workflows that reduce errors and improve efficiency.

Reinforcement-GAN for Network Intrusion Detection

Network intrusion detection systems play a crucial role in computer networks defense. However, most of the existing solutions do not take into account the time-evolving component of the attacks. Attackers are constantly changing the intrusion methods which becomes a serious threat and requires the development of adaptive methods that can cope with these modifications. Moreover, the lack of labeled data or the delay in obtaining labels is also an important challenge.
We propose a system, Reinforcement-GAN, that is able to adapt to new network intrusion methods by incorporating reinforcement learning and generative adversarial networks (GANs). Our system takes advantage of reinforcement learning techniques for allowing the development of a more adaptive model building while utilizing GANs to improve its detection accuracy. Our system follows a semi-supervised method that integrates a self-learning approach while updating the model training with labeled data as it becomes available.

Scaling up a national program to improve hospital nutrition care in line with the new Canadian malnutrition standard

The Canadian Nutrition Society is Canada’s leading society for nutrition professionals. As a Fellow, I will work with the Canadian Malnutrition Taskforce—CNS’ flagship initiative—to support integration of a new malnutrition care standard in Canadian hospitals. Advancing Malnutrition Care (AMC) was designed to bring best practices from this standard to hospitals across the country. The aim of my project is to lead the spreading and scaling of the AMC program with focus on capacity-building within the Canadian health system. My roles include: 1) Building regional mentor and hospital champion capacity to support implementation of best practices in malnutrition care; 2) Understanding mentor and champion experiences to learn of barriers and opportunities they face; 3) Monitoring hospital-level progress and corresponding impacts of implementing best practices; 4) Planning knowledge mobilization and assessing sustainability. This work will be used to improve the AMC initiative and has the potential to improve hospital nutrition care across Canada.

Vibration inspection optimization for rotating assets in the Hinton Pulp mill

Inspections are carried out on machinery equipment to evaluate the equipment condition and to take necessary maintenance actions to prevent failures. Hinton Pulp, a Division of West Fraser mills have a 30-day inspection interval for vibration inspections on rotating assets. The fixed inspection interval adopted by the Hinton Pulp for vibration inspections are not effective enough to prevent the failures on critical and aging assets. Therefore, there is a definite need to study the vibration inspection intervals to better prevent the failures and achieve the desired reliability of equipment at Hinton Pulp. This study aims at developing optimal vibration inspection intervals for rotating assets at Hinton Pulp mill. Through this research project, an inspection interval optimization model will be developed. The inspection optimization model is expected to reduce the overall operation and maintenance costs of the assets at Hinton Pulp while maintaining the desired reliability.

Evaluating the efficacy of a 60-day emotion regulation self-care journal

How we manage our emotions, also known as emotion regulation, is important and helpful in dealing with everyday stressors, our professional and interpersonal relationships, and our relationship with ourselves. Poor emotion regulation can leave us feeling frustrated for longer periods of time than we need to or even cause angry outbursts at inappropriate times. There has been a recent surge in the popularity of health-promotive self-care products, or products aimed at providing individuals with “the knowledge, skills, and attitudes required to achieve and maintain good health”. However, there has not yet been a self-care journal aimed at improving emotion regulation. The purpose of this project is to evaluate the effectiveness of a 60-day emotion regulation journal for improving emotion regulation, mental health, and overall well-being. By the end of this project, Switch Research will receive a detailed report and academic manuscript prepared for peer-reviewed publication, both outlining the efficacy of their product.

Supporting cross-scalar environmental governance

Effective mechanisms for bridging global environmental governance institutions where decision-making and governance principles are established with the experiences, knowledge, and worldviews of local peoples, communities, and conservation practitioners are increasingly necessary. Large-scale planning initiatives for conservation and mitigating climate change are cross-scalar endeavors. Therefore there is a critical need for governance mechanisms that effectively decentralize decision-making and respect the diversity of experiences, worldviews, ontologies, and epistemologies. This project aims to support equitable and effective environmental and natural resource governance and generate knowledge about inclusive, impactful learning by supporting interdisciplinary academic research relating to a partnership of governance actors (i.e., individuals and/or organizations involved in governance). The research will involve reviews of current governance approaches at various scales (i.e., local, national, regional, international), will consider how such governance approaches affect communities, especially in the context of climate change and will work towards developing tools (i.e., online portal) to support learning and equity among governance actors involved in our work.

Artificial intelligence-powered approach for strategic pharmaceutical portfolio management based on a priori estimation of clinical trial success evolution

Drug development process is time consuming, expensive, complex and highly risky. The nature of risk in this industry is multidimensional. One important dimension involves clinical development since late-stage development failures are the costliest. If pharmacological efficacy and safety remain well-known failure factors, the literature abounds on a multitude of important failure risk factors of a strategic, operational and commercial nature. In addition to being difficult for humans to control, the decisions associated with these risk factors are major contributors to failure in late stages. Less than 10% of potential medicines that start a Phase I will eventually enter the market and not all marketed drugs will generate revenues that match or exceed R&D costs. Solving this problem requires the development of efficient portfolio management approaches. AI offers capability to streamline late-stages drug development by enabling intelligent control of the multitude of avoidable strategic, commercial and operational risk factors for failure.

Generative FlowNets for Material Physics Discovery

In many real world problems, the design process involves iterative steps with generation of candidates and evaluation of these generated candidates to evaluate their utility for the relevant task. This evaluation can be done with say expensive wet lab experiments or some computational oracles. We might want to make the best use of both of these evaluations. So ideally, during generation we would like to jointly generate the candidate as well as the fidelity of the oracle to evaluate the candidate with.
GFlowNets is a neural net that models distributions over data structures like graphs, to sample from them as well as to estimate all kinds of probabilistic quantities (like free energies, conditional probabilities on arbitrary subsets of variables, or partition functions) which otherwise look intractable.
Nikita’s project aims to extend the applications of GFlowNets in the context of material discovery, tparticularly new solid-state superionic conductors. The project focuses on exploring multi-fidelity active learning, in which at each step of an optimization algorithm, the model selects both a candidate and the precision level of the oracle from which obtaining the annotation of the candidate.