Implementation of Data Generated from Competitive Analysis into Investor Presentation

With increased scrutiny of early stage investment for biotech start-ups linked to economics downturn from its peak in 2020-2021, targeted investor engagement is key for a successful financing round. Despite possessing highly derisked and innovative technology, data presentation must be refined in a highly digestable manner to attract interest from notable investors and potential strategic […]

Read More
Review of best practices in measuring, monitoring, evaluating and reporting (MER) of climate resilience as relevant to the City of Toronto

Urban areas will be some of the most complex and important sites of resilience planning in the 21st century. Despite notable efforts, best practices for how local and municipal governments set goals and track progress toward resilience have yet to be established or widely agreed upon. The City of Toronto seeks input into the development […]

Read More
Machine Learning Associate Program || Collaborative Project with Knowd and Vector Institute

Knowd is an organization that provides codified building blocks for knowledge capture, discovery, and organization within the enterprises using retrieval-based language models. With a focus on the application of large language models (LLMs) for diverse knowledge-intensive tasks such as question answering, summarization, and reasoning. The company seeks to train and fine-tune LMs and retriever models […]

Read More
Economic Development through Sustainable Forest Management at Haliburton Forest and Wildlife Reserve, Ontario, Canada

Master of Forest Conservation Candidates from the Faculty of Forestry at the University of Toronto will partake in the research and development of biochar in Haliburton Forest and Wildlife Reserve Ltd. Studies will provide a greater basis for certification and standardization of the product for use in forest systems and operations in Haliburton Forest, as […]

Read More
Efficient Data Representation for Wildfire Predictions

Wildfires continue to pose severe threats to ecological systems, communities, and economies worldwide. Early and accurate prediction of wildfire occurrences is crucial for effective preparedness and response strategies. This study investigates the application of machine learning methods to predict global wildfire events, utilizing the SeasFire Cubes dataset — a scientific datacube designed explicitly for seasonal […]

Read More
Automated Data Analyzer

The objective of this project is to develop an automatic data analysis tool that allows users to query datasets using a natural language interface. The project aims to incorporate external knowledge sources via knowledge graph integration, thereby enhancing the accuracy of the analysis. The knowledge augmentation will be reference based using REALM or Toolformer inspired […]

Read More
Imaging Fibrosis in Peyronie’s Disease with Photoacoustic Ultrasound

Nearly 1 in 10 men are affected by Peyronie’s Disease (PD), a disorder that occurs when excessive scarring builds up in the penis leading to abnormal curvature, pain, and erectile dysfunction. Currently, a photograph of the patient’s erect penis is used to measure the curvature angle, which can be very inaccurate and can be both […]

Read More
AI-Driven Pneumothorax Detection in X-ray Imaging

This project aims to enhance the accuracy of identifying health issues in chest X-ray images. The team will develop a specialized tool, known as a “chest-tube detection model”, which will initially examine all X-rays to identify cases where patients have already received medical assistance, making it unnecessary to flag these cases. Subsequently, the remaining X-rays […]

Read More