Machine Learning for Modeling Soil-Tool Interactions

When construction equipment digs, this generates a complex set of physical interactions between the machine and the soil. Being able to accurately simulate such interactions in real-time opens the door to improved operator training and even adaptively-tuned digging operation that optimize the energy-efficiency of construction equipment. With recent advanced in artificial intelligence (AI), this is now within reach.

Scaling up CO2 electrocatalysis

CERT has developed a technology to convert carbon dioxide into chemicals using water and renewable electricity in a system called a CO2 electrolyzer. They are scaling up this technology as part of the Carbon XPRIZE competition, a global race to find new technologies to make valuable products from CO2.

Automatic matching of service offers to calls for tenders

The process for responding to tenders is very long, arduous and involves many repetitive tasks. Among these, it is necessary to read the invitation to tender in order to find the different requirements, important dates, legal obligations, constraints of presentation of the response, etc. All of these factors are used for the prequalification of a tender and for the drafting of the tender. These requirements are generally expressed in the form of free text.

Novelty Detection in Lunar Analogue Terrains

Lunar and planetary rovers are faced with a high volume of data from their sensors and cameras, and yet decisions must be made rapidly to prioritize to which crater it should drive up to and of which rock it should take a closer look. In Canada’s intended upcoming exploration of the Lunar surface aboard short-timescale commercial missions, these considerations are of utmost importance.

Enhancement of Virtual Synchronous Machine Algorithms with Energy Storage

Modern electric power systems are rapidly adopting renewable energy resources. This positive movement, however, does bring with it major challenges to the way we operate power systems. In particular we may face drastic frequency changes and far-reaching transient phenomena. One way to remedy these is to deploy energy storage systems, such a s batteries, to assist the power system in maintaining its frequency and in releasing and absorbing bursts of power that are required to do so.

Computer Vision Algorithms for USV mounted Real-Time Marine Vessel Detection Systems

This is a feasibility study for designing an automatic marine vessel detection system that can be used by an Unmanned Surface Vehicle. Following a thorough exploration of the challenges related to the video date acquired on the boat by our partner, we will come up with recommendations for the best camera hardware setup and preprocessing techniques that improve video quality. Next, state-of-art machine learning techniques for target detection will be applied to spot the marine vessels.

Machine-learning-based posture identification from dynamic seat sensors

Sitting for long periods of time has negative health effects that could be solved by changing posture throughout the day. The solution lies in the use of sit-stand desks, active seats, and automated reminders to change position. For this purpose, this project focuses on developing software that can intelligently determine a person’s posture using sensors located in a dynamic seat. Data will be collected from people using the Formid Dynamic Seat, which will then be used to develop and test machine learning algorithms.

Respiratory Health System and Pandemic Early Warning System

The goal of this project is to develop a low-cost ventilation system which accurately detects and records both patient treatment data and environmental data is in great need. Further, such a system will allow to create a global health map. This research and resulting hardware and software will not only benefit the current research of COVID-19, but also assist in the long term identification and management of potential respiratory pandemics.

Accelerating database storage engines using Processing In Memory

A notorious phenomenon limiting general-purpose computing today is memory wall. Memory – the hardware used to store the data- is located relatively far from the central processing unit (CPU), so applications spend a lot of time waiting on data to travel from memory to the CPU. New memory hardware, such as the one addressed in this project, aims to address this problem at a fundamental level by adding processing units to the memory itself. This way, the data can be processed right where it lives, instead of being shuffled to and from the CPU. This idea is called Processing In Memory (PIM).

Real-time Transcription and Knowledge Extraction of Video Consults

Dialogue is Canada's leading telemedicine provider, founded to improve well-being by using technology to deliver excellent care. Dialogue is a pioneer of virtual health care dedicated exclusively to organizations that want to improve the health and well-being of their members and families.