Innovative Projects Realized

Analyse de performance et potentiel des secteurs manufacturiers de l’Estrie

Le projet vise à identifier les secteurs porteurs pour l’économie estrienne. Ainsi, maximiser les retombées économiques d’investissements futurs dans la région sera facilité par la réalisation de ce projet. De plus, des composantes additionnelles permettront, d’abord, de quantifier les besoins de main-d’oeuvre régionaux ainsi que l’offre de main-d’oeuvre, ce qui permettra aux entreprises d’élaborer des stratégies de recrutement et de rétention de la main-d’oeuvre basées sur les estimations réalisées au cours de cette étude. Ensuite, la quantification de l’impact de l’université à l’innovation régionale offrira une mesure objective pouvant servir de point de comparaison avec d’autres villes universitaires de tailles similaires. Sur la base des indicateurs développés, il sera aussi possible de développer des stratégies visant à développer et à améliorer la synergie entre l’université et les entreprises de la région afin que ces dernières bénéficient de l’appui nécessaire pour innover dans leur domaine respectif.

Modeling atmospheric gas dispersion using computational fluid dynamics

Although rare, industrial facilities can suffer from minor to catastrophic failures, commonly referred to as loss of primary containment (LOPC), which can result in the release of hazardous gases and/or liquids. In order to protect the safety of the public, companies must provide a means of mitigating the potential damage to people and the environment. Since these measures are determined beforehand, the ability to develop and produce accurate modeling techniques is of the utmost importance.
The modeling of gas dispersion in the atmosphere following industrial releases (industrial stacks, containment breaches, etc.) relies on the ability to simulate accurate atmospheric flow close to the Earth’s surface. These flows are generally divided into three stability classes. Although neutral stability is well understood and applies to a number of real world scenarios, accurate prediction of dispersion under stable and unstable atmospheric flow would expand upon the current number of applicable cases. TO BE CONT’D

Constrained Kalman filtering for train position estimation

Just like for the automotive industry, there is growing interest in the development of fully autonomous trains. One of the key steps in the creation of a fully autonomous solution is optaining an accurate estimate of the train position and velocity. Accurate estimates are critical component of the train safety during operation and better estimates allow more trains to operate safely on the same track. The current project deals with trains operating in areas without GPS coverage, such as subways, and so accurate position measurements cannot be obtained as frequently. This means that the estimation algorithm used to calculate the position in between measurements must be as precise as possible to reduce any possible drift. The proposed method to improve the estimate is to ensure that the train states (position, velocity, train orientation) are explicitly constrained by the track the train is traveling on. TO BE CONT’D

Bridging Simulation-based Search and Model-based Reinforcement Learning with Entropy Regularization

Reinforcement learning (RL) provides a unified framework for sequential decision-making problem, where a computer agent interacts with an environment while trying to learn optimal decisions to maximize its long-term reward. This makes RL a suitable choice for many real-world applications, including finance. RL applications in finance have created a lot of in-depth innovation such as better execution of approving loans, managing investments, and most importantly measuring risk. The objective of this project is to advance RL approaches by combining them with powerful simulation-based search algorithms. In particular, we will investigate how simulation-based search can improve the sample efficiency of RL. The performance of our proposed algorithms will first be evaluated on well-known test domains, such as board and video games. We will then employ our algorithms in finance applications.

Guidance and Control of Hybrid Vertical Takeoff and Landing (VTOL) Unmanned Aerial Vehicles (UAVs) with Thrust Vectoring Capabilities

Quadrotors are one of the most popular choices for unmanned aerial vehicles (UAVs) in situations where fast disturbance rejection, vertical takeoff and landing (VTOL) capabilities, and maneuverability are required. However, the quadrotor is inherently underactuated, and as a result, it is impossible to independently control the orientation and position of the vehicle. One solution to this problem involves rotors that can rotate relative to the vehicle frame, allowing for the angle of each rotor relative to the main vehicle frame to be independently controlled. This type of thrust vectoring in a quadrotor allows it to track both attitude and position trajectories. One other disadvantage with quadcopters is that they often fly at slower speeds and have shorter flight ranges compared to traditional fixed wing UAVs. TO BE CONT’D

Investigating the role of Sugars in the Risk of Obesity

Obesity is a major public health concern and sugar intake has been put in the spotlight as a possible key driver of the obesity epidemic. Much of the evidence is confounded by increased energy intake and is mainly focused on sugar-sweetened beverages. However, other sugar-containing foods like fruit, yogurt and high fibre breakfast cereals may not have the harmful effects associated with sugars. Therefore, we would like to conduct analyses using published data to determine whether there is an effect of sugar intake on body weight regardless of the amount of energy consumed and whether the effect varies depending on different food sources of sugar.

Viability of Superconducting Resonator Based Detectors

There is an abundance of evidence from astronomical and cosmological observations that suggests approximately 85% of the matter in the universe is dark matter, an unknown form of matter beyond the description of the standard model of particle physics. To date the effects of dark matter have only been observed through its interactions via gravity; experiments attempting to detect dark matter must use highly sensitive detectors and take extensive measures to reduce the background of non-signal events. It has been proposed that new detectors for dark matter may be produced by instrumenting superconducting resonators to the surface of an absorbing target to measure the energy of the particle interaction. This project aims to determine the most effective absorbing material for the superconducting sensors, and perform test with the detectors in a low-background, underground test facility.

Farrow Memory Training Study

The goal of this project is to assess the effectiveness of a novel memory training program

developed by Dave Farrow, 2 time Guinness World Record winner for best memory. The

cornerstone of this program is the concept of memory personalities which posits that 1) the

optimal way of processing and organizing information to be remembered differs between

individuals and 2) a strategy designed to encourage individuals to organize information in a

way that is most natural to them will result in optimal memory performance. By introducing a

more personalized approach to memory training, it is anticipated that this system will be able

to help a greater amount of people (particularly older adults, who have more difficulty learning

complicated strategies), with only a limited amount of training time.

Neuroimaging biomarkers of Parkinson’s disease identified through brain, brainstem and spinal cord imaging

In the current functional and structural neuroimaging project, we aim to identify functional and structural changes that correlate with disease presence and its severity (staging) and that can serve as a basis for future development of PD neuroimaging biomarkers. To achieve this objective we will use our expertise in functional neuroimaging of the cervical spinal cord (CSC), brainstem and brain (simultaneously), as well as in micro-structural neuroimaging of the spinal cord. The PDQ will play an essential role in subject recruitment, while also benefiting from the research outcomes and gained knowledge from the project. This work has great potential for future development of clinical applications as the novel PD biomarkers developed here can help diagnose the disease, assess its severity or prodromal identification of at-risk individuals.

A Study of Motor Learning in Children and Adults who Stutter

Stuttering is a speech disorder that not only affects a person’s ability to communicate fluently and confidently, but can also have a significant impact on their quality of life and mental health. Developmental stuttering typically emerges in early childhood; however, 20% of individuals will continue to be affected by this disorder into adulthood. After decades of research, the causes of this speech disorder and the reasons for its persistence are still not clear. We do know from the study of movement behaviour in this population that children who stutter are slower and more unstable in their speech movements. Adults who stutter have shown difficulties in planning and coordinating their movements, along with impairments in learning and combining multiple movements efficiently, in speech as well as in finger sequencing tasks.TO BE CONT’D

Translational Research in User Experience Design for Personalized Health

Personalized health is increasingly gaining public attention in the media as the future of healthcare. Personalized health is the idea that medical treatment will be tailored to the individual based on their predicted response or risks of disease. Omics analysis, defined as the universal detection of different classes of biological molecules, has the potential to direct personalized health delivery and enhance lifestyle changes, such as changes in diet and exercise habits, that may prevent disease development.
To improve on the accessibility of this rich Information and action plan for health seekers and platform users, we will use a user centred design approach to optimize the user interface and user experience design of the platform. Through an iterative process of research, design and user-testing, we will seek to Improve and simplify the user experience without compromising integrity of Information to support Improved decision making. TO BE CONT’D

Spatiotemporal travel behavior modeling and analysis for better public transport systems

The public transportation system is crucial in alleviating urban congestion. The widespread of smart card automated fare collection (AFC) system produces massive data recording passengers’ day-to-day transport dynamic, which provides unprecedented opportunities to researchers and practitioners to understand and improve transit services. This project aims to make full use of the transit operational data (mainly smart card data) to enhance transit services. The main body of the research project is spatiotemporal behavior patterns mining. The project collaborates with the transit operator exo and will be accomplished by a series of methodological and practical contributions. Data fusion technique will be used to make up incomplete data and contextualize trips’ and passengers’ attributes. We will construct features to profile passengers’ behavior at different time scales and utilize statistical learning methods to extract meaningful latent representations to help to understand passenger behavior patterns. TO BE CONT’D