Projets novateurs réalisés

Two machine learning problems related to fitness and relaxation – RES0054116

Project is intended to optimize health and wellness by analyzing the relationships between various forms of feedback while monitoring key indicators such as eye movement, or in other cases specified diet regimes.

Advancing an Intelligent Transportation Data Platform and Environmental Sensing to Promote Sustainable Cities

Transportation services, ranging from public buses to private logistic fleets, could benefit significantly from the introduction of Roger’s 5G wireless networks. This project has a primary objective to support UBC’s efforts to achieve its 2050 GHG emission reduction goals with emphasis on reduction of GHG and air pollutant emissions from transportation services.

Implementation and evaluation of a surface estimation algorithm to modify the control of ADAS features

Road departure is a critical factor in vehicle accidents, which could happen as a result of a driver’s impairment or lack of attention, or the road surface condition due to inclement weather. Therefore, it has been a high priority for the automotive industry to improve advanced systems for stability and path control. GM novel approach aims to use a control method to maintain a vehicle in the intended path during automated braking, while the deceleration and collision prevention is optimized. The proposed research will generate a simulation platform to verify the performance of such a control system for different road surface conditions and driving scenarios. The insight from this study helps to improve the safety of motor vehicles and all road users. The partnership of the academic researchers and GM engineers will facilitate knowledge transfer between academia and industry and assure smooth and rapid commercialization of the intellectual property.

Challenges of integrating machine learning in rock engineering design

There is an increasing interest in applications of machine learning to solve mining and geotechnical problems; this is made easier thanks to user-friendly and open source machine learning codes and improved computational power. The benefit of incorporating machine learning in rock engineering design are apparent, including the reduction in the time required to sort and characterize field data and the capability to find mathematical correlations between complex sets of input data. However, there are challenges to be investigated, including the use of qualitative data. This project investigates the readiness of the technical community to integrate machine learning in rock engineering design at this time. To fully realize the potential and benefits of machine learning tools, the technical community must be willing to accept a paradigm shift in the data collection process and, if required, abandon or improve on empirical systems that are considered ‘industry standards’ by virtue of being commonly accepted despite acknowledging their limitations.

On-board gaseous fuel compression for low greenhouse gas commercial vehicles

To reduce the greenhouse gas (GHG) emissions from goods transportation low-carbon fuels can be combined with high-efficiency engine systems. Gaseous fuels such renewable natural gas and hydrogen offer low net GHG emissions from efficient direct-injection engines. These engines use high fuel injection pressures that need to be supplied during operation by a compressor on the vehicle. This project will investigate the technical pathways that could provide the desired fuel pressures. The objectives of the work include identifying the best way to drive the compressor; preparation of models to guide the design of the compressor system; and development and evaluation of two prototype compressors that can operate on a range of gaseous fuels including NG and H2. A successful outcome from this project will allow high-efficient low-GHG engine technology to be applied to transport truck applications worldwide.

Challenge of detecting deep infrastructures

The raw materials that support and accompany the development of society will always be essential beyond the technological evolution. The challenge is to renew the reserve of natural resources at great depth. For new exploitation of these resources, the borrowing of old infrastructure of mining camps above and below the ground makes it possible to reduce investments by minimizing the new environmental impact, especially for mature and urbanized mining districts like the Abitibi greenstone belt. Knowledge of the condition of the soil before (accessibility), during (stability) and after (reusability) mining exploitation is therefore important. By carrying out a research project, we wish to advance our knowledge of the detection capacity of underground infrastructures in order to aid future operations in a more secure, profitable and sustainable manner.

Forex data gathering and analysis acceleration

A prototype Forex currency trading system has demonstrated a proof of concept on a static data set. The current project proposes to implement the trading system for real-time applications.

Foreign currency trading (Forex) is a high risk activity where low stakes multiply out to large gains and large losses.The trading activity is time dependent and very small time differences can result in gains or losses. By analyzing trading activity CTSForex aims to provide a strategy thatgives the trader an advantage over a sequence of trades.The strategy depends on an algorithm that requires data gathering and analysis in close to real time. The internship proposed therefore includes fast data gathering from the web, the rapid execution ofpredictive analysis of the data and the automatic execution of Forex trades on the basis of the CTSForex algorithmic analysis.

Weakly Supervised Behavioral Modeling for Controllable AI Agents in Video Games

The project aims at developing a new type of Reinforcement Learning algorithm that would allow to retain more control over the artificial agent once its training is completed. This framework would combine modern unsupervised modeling techniques to capture the variability of a set of demonstrations and user-defined programmatic functions that can characterise particularly important factors of variations. Ultimately, the user would be able to specify to the learned agent what type of behavior should be executed at test-time. While this contribution could benefit many AI applications involving sequential decision making, it is particularly interesting for the video game industry as such a tool would allow game designers to make better use of machine learning approaches for in-house testing.

Opportunities for Sino-Canadian Collaboration in Global Health Governance and Multilateral Pandemic Response

The coronavirus pandemic has elevated global health governance from a “low politics” position in foreign policy practice to an economic and security priority of international importance. Conventional foreign policy approaches to pandemic management have proven ineffective in the time of Covid-19, as states struggle to fulfil public health obligations in an increasingly globalized world. Canada’s inability to contain and manage the coronavirus is further complicated by its challenge of navigating a global order shifting to multipolarity as a middle power with close ties to the United States. This project will review recent epidemics and pandemics to determine the limitations of conventional foreign policy approaches in managing highly contagious viruses following the 2008 Global Financial Crisis. It will suggest the advancement of global health as a non-traditional security (NTS) issue, and identify realistic opportunities for improved Sino-Canadian health diplomacy. The project will address political-economic factors un/favourable to effective health diplomacy as a sub-objective to strengthen its findings.
The partner organization, the Institute for Peace and Diplomacy, will benefit from the publication of a rigorous research report on a topic at the forefront of nearly all current foreign policy issues. Findings of this project will be publicly available to the Canadian foreign policy research community. IPD welcomes the opportunity to forge a relationship with the University of Waterloo and Balsillie School of International Affairs and enter more collaborative projects that benefit students.

The effects of a nature-based mindfulness-compassion intervention for older adults delivered using virtual reality

Mental health problems in older adults (>65 years old) are becoming increasingly prevalent in Canada, with high rates of depression, anxiety, and social isolation found in long-term care facility residents. These psychological challenges are being exacerbated by the COVID-19 pandemic. There is thus a need for effective and innovative health strategies to help support older adults’ psychological well-being. The proposed research project is a partnership between Dr. Khoury’s mindfulness research lab at McGill (PhD Intern: Isabel Sadowski) and Super Splendide. We seek to investigate the acceptability and effectiveness of a multi-user 360-HD video virtual reality (VR) application, Excursion VR, that aims to support older adult mental health and well-being through incorporating elements of nature, mindfulness, compassion and social connection. If successful, ExcursionVR has the potential to promote geriatric health utilizing a technology that is accessible and safe, given the current global context. This project will also support Super Splendide in the effective development, market validation, commercialization and scaling of ExcursionVR.

Post-harvesting biodiversity recovery curves for the boreal forest

Canada’s boreal forests are dynamic landscapes whose forest structure and biodiversity are altered by both natural and anthropogenic disturbance. Timber harvest is one of the dominant anthropogenic disturbances in these forests. We need to better understand how the biodiversity within these forests recovers after harvest. In this study we develop biodiversity recovery curves for harvested forests, considering various biotic groups (e.g., birds, mammals, vascular and non-vascular understory plants, invertebrates, fungi). We expect recovery trajectories to vary among forest types and natural regions, requiring both local understanding and broader landscape pattern discernment. We will use species richness and community composition to assess biodiversity recovery among taxa, following published methods and employing identified sources of relevant ground data to produce curves that generalize biodiversity recovery post-harvest. Our findings can be used, including by ABMI, to inform the Biodiversity Management Framework, sustainable resource development, land use planning, and cumulative effects management.

Intern

iGen Education is an innovative approach to education, which includes offering outdoor courses and integrating STEAM principles into curriculums. The vision behind iGen Education is “Learning beyond the walls of the classroom.” The intern will have the opportunity to promote how our programs can benefit students and their families as well as the greater community, and consider the different communication methods we can utilize to retain more clients and amplify the message of our company values. This will be done by creating a website and digital marketing plan, business development strategy, conducting online campaigns, and ongoing brand promotion.