Innovative Projects Realized

AI Patient Intake and Screening

TxtSquad will develop an AI-driven intake and screening system that begins over SMS and continues in a secure web portal. Patients can upload documents and describe their symptoms, which are processed using OCR and AI to generate structured, FHIR-compatible records for EMR integration. The project will reduce administrative effort and improve intake quality for healthcare providers.

Mitigating Detrimental Effects of Vergence Accommodation Conflict in Stereo Displays

Modern augmented reality (AR) head-mounted displays (HMDs) display stereo images to the two eyes through a beam splitter and optical lenses that project the images onto a fixed focal plane. When 3D content is rendered at a depth different from this focal plane, users must accommodate to the display distance while converging their eyes to the perceived target depth, creating a mismatch known as the vergence–accommodation conflict (VAC). This mismatch, absent in natural viewing, has been shown to reduce depth judgment accuracy and impair pointing and selection performance in stereo systems.

To mitigate the VAC, researchers have proposed using varifocal stereo displays, which dynamically alter the focal distance based on real-time gaze tracking However, prior work has focused on evaluating visual perception improvements, such as depth realism or visual comfort, rather than interaction performance. Consequently, the implications of varifocal displays for interactive AR experiences remain largely unexplored.

In this project, we aim to investigate whether varifocal stereo displays can eliminate the interaction performance disadvantages introduced by the VAC in current AR systems. By systematically comparing user performance across varifocal and fixed-focus display conditions, our study will bridge the gap between perceptual display research and interaction-centric human–computer interaction studies.

Quantum functionality testing under dimensional assumptions

This research project aims to develop more practical and efficient methods to verify that quantum devices are working correctly, especially when we cannot fully trust the internal details of the hardware. By relaxing strong assumptions about the dimension of tested quantum devices and deriving clear robustness bounds, the project will help build scalable and robust quantum device testing method.

Data-Efficient Scan-to-BIM: A Weakly Supervised Learning Framework for 3D Point Cloud Analysis in Modular Construction

This research proposal aims to automate the Scan-to-BIM Quality Control (QC) process for Modular Off-site Construction (MOC).
MOC requires millimeter-level precision, but the 3D scan data (point clouds) consist of raw coordinates without semantic information like wall or floor. Using AI (3D Semantic Segmentation) to automate classification presents a Catch-22 dilemma: training the AI requires manually labeled 3D data, which is prohibitively expensive and time-consuming.
This study proposes a Semi-Supervised Learning (SSL) and Self-Supervised Learning (SSL) framework to overcome this problem by drastically reducing the dependency on labeled data.
The core idea is to pre-train the AI model on large-scale unlabeled data, allowing it to learn the grammar of 3D structures on its own. Subsequently, a high-performance segmentation model is built using only a minimal amount of labeled data (approx. 1-5%).
The ultimate goal is to automate the Scan-to-BIM post-processing workflow, prevent costly on-site rework, and contribute to enhancing the MOC industry’s competitiveness.

Acquiring novel molecular techniques to study the impact of climate change fuelled heat waves on insects at both the physiological and population level

The intensity and frequency of heat waves is increasing. The effects of this on agricultural pests is poorly understood. Insects have a remarkable ability to adapt to unfavourable conditions, and this resilience can be inherited. This study springboards a novel collaboration to study whether a newly discovered method of DNA transmission across generations, extra chromosomal DNA, may aid insects in evolving resistance to stressors. The Adamo lab has a long standing interest in the physiology of insect stress responses. The intern, Dr. Lee, brings both an interest and expertise in studying transgenerational events in insect pests. Working with Dr. Bruce Hay at Caltech, Dr. Lee will learn how to find, and work with, eccDNA. He will be able to bring this technique back to our lab, increasing my lab’s ability to study transgenerational events. We will be able to search for fitness costs of eccDNA in my lab, with support from Dr. Hay. Fitness costs are also critical for his research program on insect pests, which focuses on the genomic level.

Understanding Dengue Transmission Dynamics with Wolbachia-Mediated Vector Control

This project focuses on understanding dengue transmission and testing a promising mosquito-based intervention, called Wolbachia, to reduce its spread. The aim is to develop a computer model that simulates the life of individual Aedes aegypti mosquitoes and their role in transmitting dengue. This model will include mosquito behaviour, the effects of Wolbachia on mosquito reproduction, and virus transmission from mosquitoes to people. Using this model, we will study the spread of Wolbachia in mosquito populations and its impact on dengue under different environmental and intervention scenarios. The project will be carried out in partnership with York University’s Agent-Based Modelling Laboratory (ABM-Lab), which has strong expertise in creating realistic infectious disease models. By combining York University’s strengths in complex-systems modelling, we aim to create a simulation tool that provides deeper insight into the biological and environmental factors that drive dengue transmission. This knowledge will support researchers and public health decision-makers in designing more effective strategies to control mosquitoes and reduce dengue risk.

Unsupervised Learning–Based Scan-to-BIM for Modular Construction

This project aims to create a simple and reliable method to turn 3D scan data from modular construction factories into BIM models using unsupervised learning. By focusing on basic geometric patterns in point-cloud data, it reduces the need for manual labeling and helps build a semi-automated Scan-to-BIM workflow. The interns will develop a full pipeline that includes preprocessing, geometric feature extraction, clustering, and BIM integration. The project will benefit both participating institutions: Concordia University will gain new algorithms, datasets, and tools that support its research in digital construction, while Gyeongsang National University will strengthen its skills in AI-based point-cloud processing and expand international research collaboration.

EQU’EAU : Études qualitatives pour améliorer la résilience des infrastructures de transport face aux pluies extrêmes

Il existe actuellement un consensus scientifique disant que dans le contexte de changements climatiques actuel, les épisodes de « pluies extrêmes », apportant un volume conséquent de précipitations dans un temps réduit, vont augmenter en fréquence et en intensité. Ces épisodes impactent d’ores et déjà le déroulement des activités socio-économiques, notamment les réseaux de transport, dont ils peuvent interrompre la livraison de service. À Montréal, le réseau de transport fait aussi régulièrement face à des épisodes de pluies extrêmes. Or, l’intégration de la gestion du risque est une question plutôt récente pour l’exploitant de transport qui est à la recherche d’une meilleure connaissance de sa vulnérabilité et l’amélioration de ses capacités de résilience. Ce projet vient ainsi répondre à un besoin local, celui d’une meilleure compréhension de la vulnérabilité du réseau de transport de la Ville de Montréal face aux pluies extrêmes (notamment estivales), soit une étude qui permettrait d’adapter et ajuster des méthodologies principalement développées en Europe et d’en formuler une mouture adaptée au cas québécois / montréalais.

Energy Policies and Regulations for Deep Electrification with Distributed Energy Resources

Electricity systems face unprecedented pressure to accommodate extraordinarily rapid growth within a short period. Achieving net-zero emissions requires deep electrification, extending electricity use to activities that currently rely on fossil fuels. This shift could dramatically increase current consumption levels, making it essential to harness the potential of distributed energy resources (DERs) to meet the growing demand sustainably and efficiently. However, doing so depends on the large-scale integration of DERs into existing power systems, a process that brings not only technical challenges but also significant economic and regulatory complexities. Addressing these issues requires a fundamental rethinking of traditional frameworks to ensure their effectiveness under deep electrification, along with a redesigned energy system and a new market paradigm.
The proposed research will be part of the Deep Electrification with Distributed Energy Resources project, which aims to develop a scientific, evidence-based plan to comprehensively address the technical, economic, and policy challenges of deep electrification through DERs. Specifically, this research will contribute from market, public policy, and regulatory perspectives by developing and evaluating economic frameworks and solutions that support the project’s objectives. Expected outcomes include recommendations for energy policies and regulatory changes, providing policymakers, regulators, and industry stakeholders with guidance toward net-zero through deep electrification.

Cryogenic Integration of Quantum Dot Single-Photon Light Sources

This project aims to improve how quantum light sources—specifically semiconductor quantum dots—are connected to optical fibers using a cutting-edge 3D printing technique called photonic wire bonding. Quantum dots can emit single photons on demand, which is essential for secure communication and future quantum computers, but getting those photons efficiently into standard optical fibers has been a major challenge, especially at the ultra-cold temperatures these devices require. By redesigning the 3D-printed connectors and developing cryogenically stable packaging, this work will create a reliable, plug-and-play interface that works with existing telecom infrastructure. The collaboration between the University of British Columbia (Canada) and the University of Würzburg (Germany) combines world-leading expertise in photonic integration and quantum emitter technology, strengthening long-term research ties and enabling both institutions to advance scalable quantum hardware—bringing practical quantum communication closer to reality.

A High-fidelity Digital Twin Platform with An Engineering Mechanism Inference through Vision Systems

While mass production systems have successfully implemented automation processes, job-shop manufacturers face a critical challenge: experienced workers are retiring, taking decades of specialized knowledge with them, while finding skilled replacements becomes increasingly difficult. This project addresses this problem by creating a “digital twin” – essentially a highly accurate virtual copy of a real manufacturing workspace that can see and understand what’s happening on the factory floor. Think of it as creating a knowledgeable digital assistant that learns from expert workers and can guide less experienced operators through complex tasks. The system uses artificial intelligence that learns the best ways to set up equipment from thousands of manufacturing scenarios and predicts potential problems before they occur. It can visually recognize tools and fixtures, answer questions about processes, and even coordinate robotic arms to automate setup tasks. For the manufacturing partner, this technology means preserving valuable expertise that would otherwise be lost, training new workers more quickly and effectively, reducing setup errors, and significantly cutting down the time needed to prepare machines for production – all while maintaining the precision and quality that customers expect.

Validation of the tissue regenerative properties of a novel peptide using a cellular co-culture model

This project addresses untreated dental caries, the world’s most prevalent disease affecting over 2 billion people, particularly underserved populations. The research will validate a novel peptide therapeutic that simultaneously promotes dental tissue regeneration and controls inflammation in infected tooth pulp. Using advanced cellular co-culture systems that mimic the inflammatory environment of dental infections, the study will investigate how this peptide activates regenerative pathways while modulating immune responses. This work represents a critical step toward developing a first-in-class biological treatment that could preserve inflamed dental tissues currently requiring removal, offering a transformative alternative to conventional interventions. Successful validation could establish a new paradigm for regenerative treatments in dentistry with broader applications across multiple inflammatory conditions affecting stem cell-rich tissues.