Innovative Projects Realized

Automatically Evolving Machine Learning Codebases with Large Language Models

Machine learning (ML) is transforming industries like IT, finance, and healthcare, but the code that powers these systems is still mostly written and updated by hand. This project explores how Large Language Models (LLMs) can assist developers by predicting and suggesting code edits for ML projects.

By analyzing real-world code from public repositories, the research will develop and test an AI-driven approach to automate ML code modifications based on developer intent. The goal is to make software development faster and more efficient, helping businesses and researchers automate the process of updating codebases.

This project aims to build a benchmark dataset of ML code edits, develop an LLM-powered assistant that can suggest and apply modifications, and evaluate its effectiveness compared to human-made changes. By improving automation in software engineering, the research will help streamline ML development and reduce manual effort.

Asynchronous mesh networks for continuous methane leak monitoring

Spero Analytics is a research-driven IoT startup which builds mesh networks for automated, continuous surveillance of greenhouse gas emissions in landfills and energy facilities. As those networks are power efficient and operate using radio communication, they can be deployed in remote industrial areas with limited cellular/power infrastructure. The existing system architecture consists of a gateway connected to a number of downstream nodes arranged in a multi-hop mesh configuration and equipped with a high-accuracy methane sensor. Every hour, the nodes come online, transmit their sensor reading via their on-board antenna, then go into a “deep sleep” mode to conserve power. This existing arrangement allows us to deploy robust, scalable greenhouse gas surveillance networks that can operate for years with minimal operator intervention. The challenge, however, emerges when there is an anomalous methane reading (due to a leak) which occurs during the hour that the nodes are in deep sleep mode. In that case, the operator will not be alerted about the anomaly until the next reporting cycle, thereby introducing a delay in leak detection and repair. This project proposes the development of an algorithm which will allow the mesh network to react to those intra-duty-cycle anomalies without compromising power efficiency.

Biosignal Transformers for Advanced Blood Pressure Waveform Analysis

This project aims to develop advanced machine learning models to analyze arterial blood pressure (ABP) waveforms
from patients in intensive care units (ICUs). By using a large dataset and cutting-edge techniques like transformer
architectures and contrastive learning, the goal is to create models that can accurately predict patient outcomes, such
as ICU mortality and hospital stay lengths. This research will improve our understanding of how ABP data can be
used to support clinical decision-making and enhance patient care. The project will also benefit participating
institutions by advancing the application of machine learning in healthcare, providing valuable insights for both
academic research and real-world clinical practice.

Automated Digital Asset Wallet Tracking & Visualization

This project will create a dashboard for the automatic tracking of digital asset investments. By using data directly from the blockchain, this dashboard will be more accurate and comprehensive than existing solutions. Further, much of this work is currently being done manually and using spreadsheets by the partner, with this dashboard the expect to 3x their efficiency in this area.
A dashboard that assists with tracking digital asset investments is an important tool to bring greater transparency and risk management to the digital asset space, enabling the partner to not only be more productive but also more valuable to customers and partners in the digital asset landscape and beyond.

A needs assessment to identify gaps and opportunities for patient navigation programs for youth/young adults with mental health and/or addiction concerns in New Brunswick

The research team at the Centre for Research in Integrated Care (CRIC), at the University of New Brunswick, will be
partnering with the research team at New Brunswick Social Pediatrics (NBSP). The main objective of this project is to
inform the development and implementation of a patient navigation program in New Brunswick for youth/young adults
with mental health and addiction concerns, their informal caregivers, and members of the care team. It will also
provide stakeholders with evidence, information, and practical resources to adapt patient navigation for this
population.

Cross-Cultural wisdom: Mapping wise strategies for life’s major decisions

This project explores how people from different cultures make important life decisions, such as career choices or relationships. It focuses on understanding how cultural norms, social values, and religious beliefs influence decision-making. The research will use advanced text analysis (Natural Language Processing) and surveys to identify patterns in how people from different backgrounds approach decisions. The results will help create more culturally sensitive strategies for education, international relations, and policymaking. This collaboration benefits participating institutions by strengthening cross-cultural research, fostering international academic exchange, and advancing innovative research methods in decision-making studies.

A needs assessment to identify gaps and opportunities for patient navigation programs for youth/young adults with mental health and/or addiction concerns in New Brunswick

The research team at the Centre for Research in Integrated Care (CRIC), at the University of New Brunswick, will be partnering with the research team at New Brunswick Social Pediatrics (NBSP). The main objective of this project is to inform the development and implementation of a patient navigation program in New Brunswick for youth/young adults with mental health and addiction concerns, their informal caregivers, and members of the care team. It will also provide stakeholders with evidence, information, and practical resources to adapt patient navigation for this population.

Valoriser les connaissances récoltées dans le cadre de la production d’une émission médiatique à grande écoute

HINT est spécialisée dans la création de contenu pertinent. Nous supportons les organisations en leur permettant d’exploiter le plein potentiel de leurs données et de leurs expertises pour créer du contenu personnalisé, pertinent et approfondi. Elle développe des outils de gestion de connaissances et de création de contenu dans le but de permettre aux organisations de créer du contenu pertinent et adapté à leurs besoins.

Grâce à son expertise en traitement du langage naturel (NLP), avec des outils comme NLTK, SpaCy, ou des frameworks comme transformers, le stagiaire sera au cœur de l’avancement de notre mission en travaillant sur l’analyse des besoins d’un client stratégique et en contribuant au développement de notre moteur de recherche intelligent dans le cadre d’un projet avec un média d’envergure.

Le travail réalisé permettra à HINT d’acquérir de l’intelligence de données et de l’intelligence d’affaires lui donnant un avantage concurrentiel notable pour le développement de son moteur de recherche. Plus précisément, le stagiaire travaillera sur la cartographie et l’analyse des processus de création des données compris dans des dossiers de recherche journalistique, la mise en place d’un processus optimisé de création des données et de leur dissémination responsable ainsi que de fournir des recommandations pour la création ultérieure d’un moteur de recherche d’information performant rendu performant grâce à l’IA.

Revolutionizing Real Estate Advertising with AI: An Automated Ad Creation System for Realtors

Our project aims to revolutionize real estate marketing with an innovative AI-driven advertising system that automates the creation and optimization of digital campaigns for realtors. Tailored for real estate teams and brokerages, the system leverages BASL’s extensive market insights and performance data to generate personalized ad content. With a user-friendly interface, team leads can prompt the AI to develop targeted ad copy and creative assets that resonate with local market demands. The platform continuously learns from campaign outcomes to refine future advertising strategies, ensuring higher engagement and conversion rates.

BSI – Ultra-Resolution Multi-Projection Image Processing & Calibration Development Project

To research, develop and innovative upon existing and new image processing & calibration software for an ultra-resolution (up to 100MPx) multi-projection digital display. The solution is to be made to be distributable for embedding into custom in-line FPGA hardware to further enable high-speed parallel processing and eliminate bottlenecks in data communication.

Immunization Barriers Among Newcomers

The Hospital for Sick Children (SickKids) is the largest paediatric hospital in Canada, and partners both locally and globally to improve the health of children through the integration of care, education, community advocacy, and patient/family partnerships. As a cornerstone of the work of the Division of Infectious Diseases, immunization is one of the most important tools used by healthcare professionals to support healthy childhood. However, there are populations of children that face barriers to immunization access, education, and awareness. For example, newcomers to Canada face systemic barriers that make immunization and engagement with the healthcare system difficult. This project seeks to understand the extent of these barriers as they relate to requirements for international vaccine records to be translated and assessed in order to allow children in Ontario to attend school. The intern will co-lead focus groups and/or interviews with newcomer families to identify how these issues can be addressed effectively and appropriately within SickKids hospital and external health care settings. In addition to understanding barriers, this project also seeks to increase awareness and use of the SickKids Immunization InfoLine, a free phone consultation service run by SickKids to provide high-quality information and guidance on immunizations directly to the Ontario public to increase immunization confidence and knowledge.

L2M_Business Strategy for CELLECT’s Research and Commercialization

Despite advancements in women’s health diagnostics, cervical cancer screening rates remain critically low due to the invasive nature of traditional collection methods like Pap smears and self-swabs. CELLECT is pioneering a non-invasive, nanotechnology-enabled collection device—the CELLECTPad—that passively captures high-quality cervical and epithelial cells during menstruation. By removing the discomfort and accessibility barriers of existing methods, CELLECT aims to transform the landscape of gynecological screening and reproductive health research.