Innovative Projects Realized

AI Based Video Assessment of Walking Speed (Gait)

Aging adults want to age in place in their homes to remain in their community of friends, family and activities. This independence for many depends on the support of family care givers such as spouses or adult children that may live separately or work outside the home. The use of ambient sensors in the home can provide an extra level of knowledge about well-being. Specifically, video cameras have the potential to provide a great wealth of information but do so at the expense of privacy. Project partner AltumView, makes a unique video camera with built in Artificial Intelligence (AI) that detects and automatically removes people replacing them with a stick figure. This camera has the potential for use in well-being assessment without intruding on privacy. This project will specifically explore the potential for the assessment of walking speed (gait speed) as one measure of physical well-being.

The World as Sacrament: the Eucharistic Ontology of Maximos Confessor

My proposed project consists in completing the final chapters of my doctoral dissertation: The World as Sacrament: The Eucharistic Ontology of Maximos Confessor. In essence, I argue that Maximos’ insistence that all things are created from God (ek theou) according to (kata) the Logos offers a powerful example of sacramental ontology – that is, a vision of creation as derived from, and thus imbued with, the creative and sustaining divine energy. Insofar as this ontology is rooted in Christ the Logos through whom all things were made and who is immanent in the world as its constitutive logoi, Maximos’ ontology is not merely sacramental, but specifically eucharistic. The World is a ‘cosmic liturgy’ – a reciprocal interplay between God’s free gift of His own supraessential Being to the world, and the world’s offering back of that gift in gratitude (eucharistia). My aim for this mitacs exchange is to complete the final chapters of my dissertation under the supervision of Dr Brandon Gallaher who, as an established Orthodox theologian, can oversee the final stages of my dissertation.

Neuroanatomical changes following chronic post-stroke therapy using novel assistive devices

Presently we do not know the extent to which different types of therapies can assist those who are in the chronic phase of stroke recovery. Technologically innovative rehabilitation devices are now becoming available to clinicians, and often employ video game-like scenarios to motivate the patient to move. However, there is a lack of evidence documenting a) the benefits of enhanced therapy using gaming-like devices, and b) the underlying neuroplastic changes promoted by the use of these devices. Here we will measure behavioural and neuroanatomical changes associated with an enhanced rehabilitation program (gaming-device plus standard therapy) in chronic upper-limb stroke patients. This study will provide important data concerning both the capacity for neuroplasticity in chronic stroke patients, and the effectiveness of enhanced, technology-assisted devices on functional recovery. The provision of evidence-based therapeutic practice represents important knowledge translation for those living with disability brought about by stroke.

Hierarchical Bayesian Optimization in Neurostimulation

Neuroprostheses interfacing with brain and spinal tissue are in rapid development and are being applied to clinical treatment of paralysis after spinal cord injury stroke and other neurological disorders.
We have developed a versatile intelligent neuroprosthetic agent, a Gaussian Process (GP)-based Bayesian Optimization (BO) approach. We have further laid the theoretical groundwork to cover larger input spaces with a hierarchical GP.

Within this project, Julien will design a fully-hierarchical GP-BO, whereby multi-dimensional GP (i.e., a space of complex, multi-electrode stimulation patterns) rely on models preliminarily fitted in lower dimension (single-electrode). Beyond our previous work, the additional concept proposed here is that knowledge learnt during searches performed in the high-dimensional space is propagated back to the base low-dimensional components to update the building blocks of the hierarchical structure.

Enzyme-like nanoparticles for preventing lipid oxidation: implications for increasing asphalt lifetime

In Ontario, 95% of its paved roads in the province are paved with asphalt or asphalt surface treated. Due to severe weather conditions, the lifetime of asphalt roads is relatively short and regular maintenance is required. The annual cost of maintenance is estimated to be around 2.14 billion dollars. This project aims to explore nanotechnology to increase the lifetime of asphalt roads by exploring nanomaterials with anti-oxidation activities. Liposomes will be used as a model system for the initial studies and asphalt doped liposomes and finally asphalt will be tested. The partner organization will benefit from this project by learning the effect of some representative nanomaterials for asphalt improvement, which has an enormous potential economic benefit.

Improving Monitoring and Decision-making with Uncertain Sensor Data

Terrestrial contaminated sites – such as abandoned oilfields, chemical spill sites, or former industrial zones – are a major environmental problem in Canada and around the world. Environmental Material Science has created new environmental monitoring equipment that generates high-resolution spatially and temporally explicit data on environmental quality. The data must be visualized and then used to make decisions regarding if site remediation needs to occur, or if occurring, if site remediation should stop. Such environmental management decisions need to explicitly and transparently community data uncertainty and variability in the decision-making process. Data visualization techniques in the environmental sciences that allow non-expert stakeholders to interpret complex data streams do not exist, with existing techniques designed to be used by experts, who then report to stakeholders. The intent of this research project is to develop data visualization approaches that can be used by non-expert stakeholders to aid in their decision making process on environmental site management.

Quantum Training of Neural Networks

We are witnessing an explosion in the use of machine learning (ML) algorithms with significant impacts on the world’s economic and social activities. The backbone of a machine learning algorithm is a deep neural network which is composed of hundreds to thousands of neurons. To make the neural networks (NNs) functional, they need to be trained using a training dataset. It is known that the training of the networks is computationally intensive and may take several weeks or even months to complete. In this research project, we aim to develop a quantum program to train classical neural networks. The core of a training algorithm is matrix multiplication which is a linear operation and can be implemented in a quantum computer. This research project opens up new avenues for further research in the area of quantum computing and enables deployment of more accurate ML algorithms for real world applications.

The effects of internal dialyzer hemodynamics on the development of microvascular dysfunction during hemodialysis in healthy and chronic renal failure rats

Patients with end-stage renal failure (ESRF) require hemodialysis (HD) to clear their blood from metabolic waste products. While generally considered mildly invasive, research shows that HD can induce severe side effects, often affecting microvascular blood flow in tissue.
We successfully developed a small animal model that allows us to successfully dialyze laboratory rats (approx. 250 grams) while simultaneously performing an intravital microscopic observation of the microcirculation. It will enable us to investigate how microvascular tissue perfusion is affected by HD directly. Moreover, since the microdialyzers are designed and produced in-house, the dialyzer’s design and functional aspects can be easily modified. As such, we can easily change the dialyzer setup, evaluate different membrane materials, modify the HD procedure, or evaluate the effect of any pharmacological treatment strategy.

Innovations in Municipal Bylaw Adjudication

This research will look at existing and possible innovations that would make municipal bylaw enforcement and adjudication in Saskatchewan more accessible, effective and efficient and would reduce the involvement of the formal court system. This may build on the example of regional co-operation offered by the Municipal Bylaw Court in Kindersley, and it may include ways to adjudicate bylaw prosecutions outside of the court system. Any proposed solutions will be suitable for the Saskatchewan context, and any necessary changes to Saskatchewan legislation will be specifically identified.

L’incubation au sein d’une structure coopérative : quels leviers et obstacles au développement de l’agriculture urbaine au Québec ?

L’agriculture urbaine est une expertise québécoise qui tend à se développer fortement ces dernières années, à travers le développement de nombreuses structures commerciales. La Centrale Agricole est l’une d’entre elles : c’est une structure coopérative d’incubation d’entreprises agricoles urbaines. À travers les services et les biens qu’elle offre à ses membres, ainsi que les conseils et soutiens à la recherche, la Centrale Agricole a pour objectif de participer au développement de cette industrie à Montréal. Toutefois, il pourrait être potentiellement intéressant de répliquer ce modèle coopératif d’incubation aux autres régions du Québec. C’est l’objectif de ce projet de recherche : évaluer le fonctionnement de cette structure coopérative pour identifier les leviers et les obstacles à sa transférabilité.

Fully Automated End to End Analysis of Non-small-cell Lung Carcinoma using Deep Learning Techniques.

Deep learning in medical imaging analysis has revolutionized the field in areas such as computer-aided detection and segmentation of clinical abnormalities. Several studies have been published on lung cancer screening using deep learning methodologies. Specific to lung cancer screening, algorithms have been trained to automatically detect and diagnose lesions in the lungs in low dose computed tomography (CT) by leveraging longitudinal imaging in combination with biopsy results. Perez et.al [3] proposed a three-dimensional (3D) CNN model to detect lung nodules and predict lung cancer using CT images. The lung is extracted from the entire volume in each patient and the extracted data is used to train the model. To increase the precision, both 2D and 3D convolutions were used. They were able to achieve best results using 3D convolutions suggesting there is information between slices that is relevant for lung cancer analysis.

YWCA Regina BSI Project

The overall objective of this project is to diversify the YWCA’s revenue stream in a strategic way that provides both sustainability and alignment with the organization’s values. Pursuing this project will raise questions such as; can the YWCA’s rental spaces compete with current rental space trends? What value will the project add to the downtown Regina community? And what level of upkeep can the YWCA staff expect from taking on this project. The student intern will be required to assess rental space needs, research current rental space norms or expectations, determine ways the YWCA will be able to differentiate themselves, and create a strategic plan that will lead to the actual implementation of the project.