Multibeam echosounder noise classification using machine learning

Icebergs are large masses of ice drifting in ocean under influence of winds in currents. Icebergs are important indicators of climate, they provide nutrients to the ocean ecosystem, but they are also a threat to shipping and offshore industry. Collecting iceberg shapes helps to model climate, predict iceberg drift, and protect offshore facilities and flowlines […]

Read More
Esdilagh Development Corporation Business Action Plan Research and Development

Esdilagh Development Corporation(EDC) business Interns to perform business development research to inform the composition of business plans, ensuring we have professional business guidance tools to assist EDC in engaging in business sectors as identified in the Esdilagh Economic Development Plan and Investment Profile completed in 2011. Project goals are to produce professional quality Business Plans […]

Read More
Performance Based Design of Viscoelastic Coupling Dampers in Mass Timber Buildings

Viscoelastic Coupling Dampers (VCDs) have been developed over the past 15 years at the University of Toronto and by Kinetica for use in multi-storey buildings constructed with conventional construction techniques (steel and concrete). It has been shown the VCDs improve the wind and seismic performance of these buildings, leading to safer, higher performing and more […]

Read More
Crevettiers : enjeux de santé et sécurité au travail

Le milieu des pêches commerciales est reconnu comme l’un des secteurs de travail les plus dangereux au Canada (Grant, 2017). Le Comité permanent sur la sécurité des bateaux de pêche du Québec (CPSBPQ) est un organisme à but non lucratif qui œuvre dans ce milieu afin d’améliorer la culture de sécurité et diminuer les risques […]

Read More
High-frequency financial forecasting

Berkindale Analytics is a cloud-based company and wants to create a next-generation platform to provide both market data and packaged analytics to financial clients via direct download, interface, and dashboards accessible from a web portal. It is distinguished by its service arm that engages in data discovery, new analytics design, and ETL (“Extract, Transform, and […]

Read More
Federated Learning on Sensitive Mobile Data (Python/Java)

At Lerna IA, we are building a private federated learning platform for mobile applications. Our technology allows mobile-first companies to learn about their app users without violating their privacy. Our novel security architecture speeds up the federated learning process by at least 50x, rendering it practical for real-world mobile set-ups by running the whole ML […]

Read More
Arch-App

The intention of the Arch-App is to create a mobile app that utilizes geo-location and augmented reality technologies to access data (including imagery, videos, and text) on building projects throughout the city in real time. The infrastructure of the Arch-App effectively provides users a resources (ranging from historic imagery to notable interviews) and tour guides […]

Read More
ALT TEX Circular Textile-grade Polymer Synthesis

Generating 10% of global greenhouse gas emissions the fashion industry’s heavy reliance on synthetic, petroleum-derived, fabrics such as polyester, is projected to create over a quarter of the world’s carbon emissions by 2050, according to the Ellen MacArthur foundation. Unlike its bio-based counterparts, such as cotton, wool or silk, polyester does not biodegrade, and its […]

Read More
Test-based Fracture Criteria for Pipeline Steels

Steel pipelines as key Canadian infrastructure are often exposed to various geological and environmental conditions that cause defects such as cracks, dents, and gouges in the pipe wall, which can lead to pipe fracture in pipelines, compromising the entire pipeline’s functionality and resulting in significant economic losses, environmental issues or even fatalities. There are several […]

Read More
Estimation visuelle sécuritaire et explicable des conditions routières

Nous avons actuellement un prototype de systeme de vision artificielle base sur des reseau de neurones profonds entra1ne sur notre jeu de donnees proprietaire qui permet d’identifier les zones de construction et de detecter et lire les panneaux de limite de vitesse. Dans notre prochain de R&D, nous souhaitons tirer partie de notre reseau de […]

Read More
Sequential anomaly detection with labelingcosts

In a number of data analytics domains, there is a need for detecting the situations when something outside of the normal conditions is happening. The goal of this project is to develop novel algorithms that learn to distinguish these normal and anomalous patterns through minimal interaction with a human user, while allowing complex data patterns […]

Read More