Human-in-the-loop artificial intelligence for identification of fish behavior with high-frequency periodic acoustic fish tags

Innovasea produces fish tags and receivers to track the presence and motion of fish and marine mammals while underwater. Fish tracking (acoustic telemetry) is used by researchers worldwide to determine the abundance and habits of marine life, make decisions about fishing seasons and allowed catches, and help protect marine mammals. Innovasea has developed a novel […]

Read More
Pre-trained graph-based medical language model

The partner organization’s proposed role in the project is to lead all the initiatives in this project and collaborate closely with the academic partner in choosing the right approach to tackle the information retrieval and question answering problems. The partner organization will benefit through improvements to its product and the outcome of this research will […]

Read More
Data-driven AI Approach for Union Data Analysis

LegacyX is a software development firm currently transitioning from a consulting focus to a software as a service vendor, specializing in Unions. LegacyX aims to give users the choice of a range of data science tools and generate statistical analytic outcome that will allow end users gain access to the insights provided around their Union […]

Read More
Les systèmes de recommandations pour une cuisine robotique

Le système automatisé développé par Jaspercooks vise à fournir une alternative pour la préparation de repas frais et sains dans des lieux tels que les hôpitaux, les résidences pour personnes âgées, les universités et les écoles, ainsi que dans les immeubles résidentiels de grande hauteur. Ce projet vise à développer des algorithmes de classification des […]

Read More
Development of a Document AI algorithm for large-scale data capture

To guarantee progress and adherence to the Dreven platform the company must solve a major issue to which no traditional solutions tested have provided reliable and efficient answers. This issue is linked to the complexity and diversity of information exchanges that Dreeven must use for different reasons. To be efficient, the Dreeven platform must be […]

Read More
Real time fuel classification from drone imagery for improved wildfire prediction

Wildfires are naturally occurring phenomena that are necessary for the health of boreal forests. However, fires can cause infrastructural damage and loss of life if they spread into places where people, towns, and other assets are at risk. Due to the impact of wildfires on society, attempts have been undertaken to assess wildfire potential, spread, […]

Read More
Speech Recognition for 9-1-1 Calls and Long Audio Clips

This research project has two goals. The first goal is to design and test software that will automatically transcribe 9-1-1 emergency calls and interpret their meaning with respect to the central facts of an emergency (who, where, and what occurred) as well as possibly when, why, and how the emergency occurred. The second goal is […]

Read More
Incorporating Pruning Methods in GAN and Diffusion-based Models

Due to the widespread use of credit cards as a payment method, numerous fraudulent credit card transactions occur, resulting in significant losses for financial institutions. At a high level, the fundamental objective of the project is to improve the performance of fraud detection systems by providing high-quality synthetic data generated by improved deep generative models. […]

Read More
Design and Evaluation of Techniques for Enhancing the Utilization of Pre-Trained Language Models (GPT-3) in Sales and Marketing through Prompt Engineering and Fine-Tuning

This research project is focused on using AI technology called Pre-trained Language Models (PLMs) to generate results that are more human-like and of higher quality. The team will utilize a technique called “prompt engineering” to work with a leading PLM in the market, GPT-3, to enhance productivity in reading and writing tasks for salespeople. By […]

Read More
Decision Making Using Multi-Criterion DecisionAnalysis

This project is to enable groups of people to better brainstorm decisions in which people can have divergent opinions. Building on ValueCharts that lets people input their utility, we will build a tool that lets decision makers explore the space of the expressed opinion to see where there are differences and whether they matter to […]

Read More