Innovative Projects Realized

Advancing Brain Tumor Segmentation through Deep Learning based Approaches

We propose a semi-automated brain lesions segmentation method utilizing deep learning techniques and point prompting such as foundation models (SAM).
This developed approach aims to assist physicians in the follow-up of multiple sclerosis disease at different stages, enhancing the likelihood of successful treatment for patients. The key contribution of this research lies in the advancement and implementation of a brain lesion segmentation method, ultimately improving the quality of life for individuals who suffer from multiple sclerosis.
Our project employs image processing techniques and Deep Neural Networks (DNN) to achieve this goal. Should the developed project prove as valuable as we hope, it has the potential to better assess the pathology evolution of patients, signifying its substantial impact on patient well-being which is beneficial for both participating institutions. Furthermore, we are proposing cutting-edge research, which has significant benefits for both participating institutions, enhancing their academic reputation and fostering innovation that can lead to practical applications.

Broker Factors as Predictors of Mortgage Deal Success

Home Trust is a mid-size bank that provides innovative solutions to its customers. Home Trust provides mortgages for different property purchases including single-family dwellings, condominiums, duplexes, triplexes, store and apartment and rental properties. The process of funding a mortgage involves several interactions between Home Trust, brokers, underwriters, and the customer. We are committed to make sure that the mortgage process is as stress-free as possible for our customers and stakeholders. We evaluate each application individually to determine the appropriate pricing.

This project would focus on exploring factors (broker and client) and how they contribute to mortgage outcomes. Different data points would be explored as part of this project (for example: demographics, loan to value ratio, broker tenure and activity levels, brokerage size, average customer bureau scores, etc.). The goal is to understand how these different factors impact mortgage funding and predict the likelihood of mortgage deal success, utilizing machine learning to create a predictive model. Home Trust would leverage this predictive model to better understand our broker base, find efficiencies in our broker base to optimize our marketing opportunities as well as optimize service.

Interns working on this project would leverage SQL and Python to prepare the data, conduct relevant analyses and develop predictive model(s), such as Logistic Regression, XGBoost, Neural Network, Random Forest, and/or other relevant algorithms. The model(s) would be fine-tuned, evaluated, and presented, along with relevant findings and conclusions to Home Trust.

Sherry Shu: Using Artificial Intelligence and Machine Learning to Innovate in the Canadian Fintech Landscape

This project aims to identify new technological approaches to personal finance to bring into the Canadian market. Managing personal finance is critically important for Canadians, especially in a post-pandemic era of economic difficulty and high prices. The project will use customer research related to fintech and artificial intelligence in Malaysia to investigate potential areas for innovation for fintech in Canada.

Comparative Insights of Cultural Influence on Classroom Management in Grades 4 to 8: Exploring Chinese and Canadian Educational Philosophies, Practices, and Intercultural Exchanges

The objectives of this Globalink research project are to study in China and compare it to that of Canada, more specifically the philosophy behind teachers, classrooms, and schools. One sub- objective includes comparing the difference between China and Canada’s teaching philosophies. For example, what specifically do these countries do differently in the grades 4 – 8 classroom and for assessment tools, and how does this affect the students, teachers, schools, parents, relationships between the forementioned, and student success etc. Elizabeth Dalla Bona will conduct research on this sub-objective primarily via observation and casual conversation with teachers in the placement schools in China. Another sub-objective will include comparing the difference between China and Canada’s morals and culture, and how it affects grades 4 – 8 classroom management. For example, how does Chinese culture, and morals affect classroom management? How does Canadian culture and morals affect classroom management? How can the classroom management strategies change or reinforce certain morals and culture? This sub-objective will be researched by Yuyang Hua via observation and casual conversation. Dalla Bona and Hua hope to gain insights on the nuanced interplay between cultural values, moral frameworks, and classroom management strategies in both countries, ultimately aiming to inform and enhance pedagogical practices that are both culturally responsive and effective in fostering positive learning environments for students. The benefit of broadened perspectives will help both Dalla Bona and Hua become more well-rounded, and empathetic educators, which will ultimately benefit their students.

Optimal data communications between a UAV and a network of ground control stations

(UAV) and a network of ground/aerial control stations for long range communications to connect various remote places of Northern Canada. The main goal of this project is to design, test and implement a robust communication subsystem for such a vehicle to maintain a long range communication with a required data throughput. Most of the civilian UAVs in use today have flight duration of about an hour. They UAVs use the IEEE 802.11 a/b/g/n standard Wi-Fi technology to communicate with portable control stations. However, the range of these communication links are very short (70m for indoors and 300m for outdoors), and are not suitable for long-range flights. Thus, implementing and maintaining a reliable long-range communications link is very important. The research objectives of this project are to (i) Design and implement a communication subsystem to support a long-range operation of the UAV by employing multiple ground/aerial control stations with high-gain directional antenna and omni directional antenna, (ii) Design and implement a communications protocol that can predict link quality and provide high data rates, (iii) Design and implement a fuzzy inference system to regulate the transmission power against predicted link quality and distance to GCS, (iv)

L2M-Market validation of the 3D organoid culture plates for making the human-mimicked tissue models

Currently, over 95% of new anti-cancer drugs fail during clinical trials (1). Despite significant technological advances, drug development has become slower and more expensive. The root cause is that current preclinical cancer models, such as 2D cell layers and animal models, fail to accurately recreate human biology. This makes it very difficult to predict how humans will respond to a drug before it is administered (2). Apricell is changing the way new anti-cancer drugs are developed. These drugs range from chemotherapies to newer approaches that leverage the immune system to combat cancer. Using Apricell’s proprietary 3D tissue modelling platform, researchers and drug developers can now test drugs on patient-mimicking tumor models in a way that is faster, cheaper, and more predictive than existing approaches. As the current technology serves both diagnostic and therapeutic purposes, the biggest obstacle to commercializing it is finding a target market with less regulation. Therefore, we need to conduct thorough market validation to confirm the overall feasibility of our business idea. The L2M program is an excellent opportunity to evaluate not only our product but also to gauge the market’s willingness to adopt our solution. It will also allow us to analyze our market in different customer segments and assess the broader business landscape.

Prosaris Partial Discharge Ultrasonic Detector Design

Development of an ultrasonic detector for detecting partial discharges (PD) across high voltage insulators or electrical connections

Identification des efforts injectés par un instrumentiste sur une percussion par le couplage d’une méthode d’identification et de mesures vibratoires de plein champ

Les mesures par contact des vibrations structurelles sont effectuées traditionnellement à l’aide d’accéléromètres. Les mesures de vibrations sans contact ont été initiées avec la vibrométrie laser Doppler, mais le nombre d’applications à des excitation transitoires reste limité car la vibrométrie nécessite une opération de scan. Les techniques photographiques, comme la déflectométrie ou la corrélation d’images digitales, permettent d’effectuer des mesures de plein champ sous excitations stationnaires et non stationnaires. L’objectif général du projet vise à étendre les champs d’applications de la déflectométrie (installation de plusieurs caméras en réseau pour imager des surfaces étendues, utilisation de téléphones cellulaires de dernière génération, cas test d’utilisation dans des contextes multidisciplinaires). C’est dans ce dernier volet que se situe l’objectif spécifique de cette proposition Mitacs. En partant d’un cas documenté en laboratoire de reconstruction temps / espace d’un chargement acoustique sur une membrane circulaire, il est proposé de reconstruire un chargement mécanique en temps et en espace sur une membrane. Le volet multidisciplinaire provient du fait que la membrane considérée sera celle d’un instrument à percussion. Il deviendrait alors possible de reconstruire le chargement mécanique correspondant au jeu de l’instrumentiste, ce qui est actuellement impossible via des méthodes traditionnelles utilisant des capteurs de force.

Youth and Early Career Ocean Professionals Perceptions and Intentions in the Sustainable Ocean Economy

The Ocean Super Cluster is interested in gaining more insight into the perceptions and attitudes of young talent, that influence their interest in participating in Ocean careers. Research has been conducted in the past that shed light on the perceptions and intentions of youth (grades 6-9) living in maritime regions, and this previous research will provide a point of comparison for current findings. A broader pan Canadian study that extends to post-secondary youth (and available potential workforce from industries in transition) will help to identify gaps and opportunities in building awareness and engagement. This research is critical to understanding ongoing barriers to participation from underrepresented groups and top talent, and will help to inform PSI curricula, industry programming, and employer support for workforce development.

Program development and evaluation for the RBC Patient and Family Learning Space at CAMH

The RBC Patient and Family Learning Space (PFLS) at the Centre for Addiction and Mental Health (CAMH) is a new non-clinical program that provides a comprehensive range of educational workshops and events, patient education resources, and navigational support to patients, families, and the wider community. The PFLS launched in November 2021 with 3 staff and limited resources. As awareness of the PFLS grows both within CAMH and throughout the community, so does the number of people entering the space and accessing our programming, adding more demands on staff and highlighting the need for more program development and evalution support. To evaluate progress and enhance the PFLS program capacity, we are looking to support three Dalla Lana School of Public Health Masters practicum students to help us further develop our programming, evaluate the current activities and assess future needs of the PFLS.

Software Engineering Coop

Our comprehensive real estate project is structured into two innovative subprojects, each spanning four months, with the overarching aim of revolutionizing communication and decision-making in the real estate market for buyers, sellers, and agents.

Sub Project 1: The Smart Open House introduces a groundbreaking approach to open houses. This system features a digital sign-in for attendees, offering immediate access to detailed property information and establishing a direct communication link with their real estate agents. Utilizing advanced AI, it facilitates real-time feedback and analyzes this data to aid agents in identifying properties that match client preferences. This addresses the key challenges of enhancing client-agent communication and personalizing property matching, thus streamlining the property buying experience and aligning with the goals of technological innovation and client-centric solutions.

Sub Project 2: BASL Smart Analyzer is a state-of-the-art Competitive Market Analysis (CMA) tool that transforms the way real estate agents and clients make decisions. Leveraging data analytics and AI, it provides in-depth insights into the real estate market, enhancing the efficiency and accuracy of property valuations. This tool tackles the historical issue of transparency in the industry, fostering trust among clients and agents and ultimately promoting a more active and confident engagement in the real estate market. Together, these subprojects not only address specific challenges in the real estate sector but also significantly contribute to its overall innovation and technological advancement.

Marketing Coop Student

Cantiro is an award winning real estate company with projects across Alberta, BC and Ontario. We are working with Mitacs to continue to drive innovation in how we adapt the latest retail strategies, trends and emerging technologies to some of individuals’ largest purchases including:
• capturing insights to design/refine our developments, products and services for emerging buyer groups,
• merchandising and engaging prospects in new ways, and
• targeting and anticipating the needs of leads and clients over their lifetime.