Adaptive multi-horizon models for probabilistic demand forecasting

This project aims to develop an itinerary demand forecasting model that can handle long-term and short-term forecasting and adjust its parameters under changing situations. General long-term prediction models are relatively precise because the context often remains stationary over time, but can not quickly adapt to unforeseen events, like the global pandemics. It is necessary to develop an adaptive model with multi-horizon perspectives. The model will integrate external data sources to output a plausible range of future booking status.

Multi-modal learning of human pose representation for conditional motion synthesis

The goal of the project is to generate realistic human movement in 3D animations. This is important to make movement animations in games and movies appear real. Typically, creating high quality animations is a resource and time consuming process that requires the participation of human actors in motion capture sessions. In this work, we present a data-driven approach that aims to generate novel animations based on a library of past motion capture recordings that can make generating high quality animations low cost and fast by eliminating the need to record human actors.

Effect of agro?climatic conditions on the cannabinoid quantities in hemp crops

We want to determine the relationship between weather such as rainfall and temperature on outdoor grown hemp. Specifically what these variables do in terms of changing the content of THC and CBD in certain varieties of hemp. Our goal is to give farmers the knowledge so that they can determine when is optimal time to harvest their crop based on that years weather if they want to be below a .3 thc content, and have a high CBD content. However, the research we do will lend itself to farmers seeking other CBD and THC outcomes in their crops.

Experimental and numerical evaluation of the electromagnetic ,mechanical and thermal behaviour of Kimberlite under microwave irradiation

In an environment of high risk and competitive, the mining industry needs continuous innovation and productivity enhancement. One of the major issues with present hard rock deposits is the cyclic mining operation associated with the drill and blast method. Another major obstacle in the extraction and processing of such rocks is the relatively high wear rate on the cutting tools which leads to low rate of penetration and low performance in conventional mechanical hard rock excavation machines.

Agricultural Multi-Layer Data Fusion to Support Cloud-Based Agricultural Advisory Services

The wor and there is a need to improve food production. Precision Agriculture is known for its use of technology in agriculture with a focus on improving farm productivity while increasing profits and environmental protection. However, as the use of technology in people's daily lives has increased, the same phenomena has been occurring in agriculture. Thus, with more technology, more information can be obtained, and a better understanding of the food production environment is the result.

High-Precision Imitation Learning for Real-Time Robotic Control

In recent years, an increase in industrial robots in manufacturing has emerged. However, there are still possible safety issues and difficulty in specifying tasks for the robots to perform. The objective of this research project is to make a path planning system that uses demonstrations of how to perform a task to learn how to perform the task using techniques from the field of machine learning. These demonstrations will also show the robot how to move in the workspace safely and without entering collision with items in its surroundings.

Exploring the effectiveness of a pilot parasport coach mentorship program.

Informal learning involves acquiring knowledge outside of a structured setting in which
learning is self-directed and developed from experience, exposure, and interactions with their
environments (Nelson et al., 2006).

Integration sound considerations into the Montreal nightlife policy

Noise affects everyone, and our cities try to limit noise impacts through effective policy. We focus on the issue of night noise, where the needs of different people can vary widely between wanting quiet for sleeping and for the great nightlife that cities are known for. This collaboration between the City of Montreal and the Sounds in the City research team uses Montreal as a living laboratory to develop new tools and methods to take sound into account when developing and evaluating a new nightlife policy.


BACKGROUND: Viral respiratory tract infection (VRTI) is the most common illness in humans, resulting in a total economic impact of $40 billion annually in the United States. Taking into consideration the current novel coronavirus pandemic - impacting billions of people around the world, compromising the global economy, and putting extreme pressure on healthcare systems - it is imperative to identify novel ways to both detect and prevent VRTIs such as COVID-19.

Modulating HMGB1 in COVID-19-associated inflammatory response

The project addresses urgent and clinically-relevant questions related to COVID-19, which causes in some patients life-threatening respiratory distress, septic shock and organ failures. Patients in intensive care units were found to have significantly higher levels of high mobility group box 1 (HMGB1) than patients with milder symptoms. HMGB1 is a protein normally found in the cell nucleus that is released outside the cell under inflammatory conditions such as viral infections.