Projets novateurs réalisés

Evaluating Gradients of Natural and Induced Stress on Fish Blood Parameters; Developing more accurate results from Point-of-Care Devices

The point-of-care i-STAT and VETSCAN units are easily portable blood-based assessment tools that can produce relevant blood parameters within minutes with only 2-3 drops of blood. The objective of this study is to examine both natural and investigator-applied stress gradients in fishes and compare blood chemistry of fishes from a range of environments (e.g., low to high stress). Investigations will occur in the lab and in the field at IISD- Experimental Lakes Area (ELA), where field data from devices will be compared to standard laboratory methods in the University of Manitoba in order to produce a point-of-care instrument better suited for fish. With the completion of this project, IIED-ELA will have greater knowledge about the current fish population within lakes, as well as access to devices that can be used in the field collect fish health data.

Manipulation de l’environnement lumineux pour optimiser le contrôle biologique des ravageurs sous serres ainsi que la croissance et la productivité des plantes

L’alimentation durable est une composante essentielle de l’économie durable visant à un développement économique apte à répondre aux besoins du présent sans compromettre la capacité des générations futures à répondre aux leurs. Pour ce faire, l’alimentation durable préconise la consommation de produits locaux et, en ce qui concerne les produits maraîchers, cultivés dans le respect de l’environnement. En milieu urbain, la culture en serre et plus particulièrement la culture verticale (rendue possible grâce à l’éclairage DEL), constitue une option des plus intéressantes.

L’objet de la présente étude sera la manipulation du spectre lumineux afin d’optimiser la saine croissance de végétaux sans l’utilisation de pesticides. Positionner le Canada en tant que leader de la culture biologique et durable en milieux contrôlés (serres et bâtiments : plant factory) aura un effet bénéfique tant sur l’économie que sur la santé de l’ensemble des Canadiens.

Reducing the carbon footprint at Hydro One

The purpose of the research project is to develop options for the reduction of the carbon footprint at

Hydro One Networks Inc. (HONI).The research will focus on helping HONI meet a reduction goal of

half of current emission levels over the next decade. The company has taken preliminary steps to

assess and plan for reduction of the company’s carbon footprint, including the collection of

preliminary data and the outlining of programs to reduce their impact on the environment. The research

project will further contribute to those efforts by focusing on providing three outputs: 1) process maps

whereby HONI may systematically identify its current carbon footprint, 2) scenario analyses to help

HONI project its future carbon emissions over varied timelines, and 3) a set of recommended actions

to reduce carbon emissions over the next decade. Completing the research will address an identifiedneed at HONI and will provide a tangible demonstration of the company’s commitment to reducing its

impact on…TOBECONTINUED

Assessing and Identifying Clinical Checklists in Intensive Care Settings

type of treatment they will provide to patients. With technological improvements and the availability of a significant volume of data, it is increasingly difficult for care providers to properly evaluate and analyze the options available to them. The current health condition of the patient–reflected in the monitored observations which are recorded in EMR–may depend on all the relevant information from all prior observations and selected treatments, not just those most immediate (e.g., the trend of various health measures). This project is focused on developing algorithms that disentangle this history, physician decisions and the outcome (patient survival or death) to assess and identify when actions may lead to irrecoverable negative outcomes. With the identification of these suboptimal actions, correctly associated with the time they are taken, the algorithm can actively discourage doctor’s from repeating such actions when they encounter similar patient histories in the future.

Caractérisation nutritionnelle et détermination des taux d’incorporation optimaux de farine de viande (pork meal) pour une utilisation efficace chez le poulet de chair

Dans une optique de durabilité, les filières animales sont à la recherche d’alternatives pouvant remplacer le maïs et le tourteau de soya très utilisés pour alimenter les animaux et qui entrent en compétition avec l’alimentation de l’homme. Dans ce cadre, les farines animales, riche en protéines, gras, phosphore et calcium, sont déjà utilisées pour substituer une partie du maïs, du tourteau de soya et des minéraux ajoutés chez le poulet de chair. En effet, celles ayant une teneur élevée en protéine (58-60%) et gras (12%) comme la farine de porc remplace avantageusement le tourteau de soya. Les taux d’incorporation demeurent cependant faibles (5-7%) compte tenu du peu d’informations de cet ingrédient sur les performances de croissance des oiseaux. L’objectif du projet est donc de caractériser la valeur nutritionnelle du produit en termes de composition et utilisation par les poulets et de mesurer l’impact de différents taux d’incorporation sur les performances de croissance, l’humidité des fientes et la composition corporelle en lipides et protéine et contenu minéral osseux, ainsi que l’efficacité d’utilisation de ces nutriments.

A Survey on Application of Visualization and AI Algorithm-Driven Technology for Healthcare

Healthcare facilities collect and produce vast amounts of clinical-relevant data. Various AI-related methods (like computer-aided detection for mammography and the learning and visualization of clinical pathways) are applied to healthcare these days, and visualization techniques are also used to support clinicians due to the complexities of clinical data. This self-contained survey focuses on the assessment of healthcare providers’ acceptance of and interaction with the AI algorithm-driven technology, along with the related visualization methods used in practice.
Historically, researchers have been concerned about the trust issue in computer-aided healthcare. For this reason,clinicians’ aversion and appreciation about algorithmic approaches in this field has been widely discussed. Some published studies have investigated physicians’ attitudes about technologies driven by AI algorithms, and generally, medical professionals seem to be somewhat skeptical about how well AI algorithms can perform in diagnostic tasks. Also, studies have been done on how healthcare providers indeed interact with algorithmic support systems in prognosis, diagnostics, and treatment recommendations, along with the visualization skills that are applied in practice.

Development, optimization and production of fiber-based strain sensors for aerospace, automotive and health

The project will employ three undergraduate coop students and one post-doctoral fellow to work with the MesoMat team to improve the sensing capabilities of the fiber technology that has been developed at MesoMat and develop robust production methods. MesoMat has developed a fiber-based sensor manufactured from plastics and nanoparticles. These materials change their resistance when stretched and for this reason can be used as a sensor. Measuring the change in resistance as a function of strain is the operating principle of the sensors. The strain range over which the sensors are effective can be adjusted through the concentration of nanoparticle additives. The fibers are as thin as 10 micrometers in diameter. For this reason, they can be embedded within composites, bonded to the surface of materials that experience strain, placed within adhesive joints, or used to monitor biomechanical changes on the human body, amongst many other uses. The interns will determine optimal parameters for the nanoparticles, the concentration of nanoparticles, the various polymer materials that can be used for a range of applications and develop the required electronic data acquisition units required to read the signal. An ambitious aspect of the project is to develop fully scalable solutions for the

Mesurer les paléopressions des systèmes hydrothermaux aurifères le long de la faille Cadillac, Abitibi

Certains gisements riches en or de l’Abitibi sont associés à des veines de quartz formées à partir de fluides hydrothermaux à différentes profondeurs dans la croûte terrestre. La mesure des anciennes pressions enregistrées par ces veines, donc de la profondeur originelle des dépôts minéralisés est particulièrement importante en exploration minière. Elle permet notamment de déterminer la profondeur de formation des gîtes minéraux et éventuellement de prédire leur position régionalement. Les sites sélectionnés pour cette étude, situés en Abitibi, constituent des exemples bien connus de systèmes filoniens. Le projet comporte une première phase d’échantillonnage et d’étude des quartz au microscope optique, et une seconde d’analyse par imagerie des d’électrons rétrodiffusés (EBSD). Cette méthodologie permettra de remonter aux pressions de formation ou de recristallisation des filons. Elle permettra au partenaire de mieux comprendre la distribution et la formation des veines aurifères sur ses propriétés, contribuant ainsi à raffiner leurs stratégies d’exploration.

Effectiveness of Cognitive Behavioural Therapy in patients suffering fromdepression and in receipt of disability benefits

Depression is expected to become the second leading cause of disease burden

worldwide by the year 2020. Cognitive Behavioural Therapy (CBT) is one of the most

effective methods of treatment for depression. CBT may be less effective, or

ineffective, in the setting of patients in receipt of disability benefits who are likely to, on

average, suffer worse outcomes than patients not receiving benefits. Currently, there

is no review that has systematically assessed the effectiveness of CBT in patients

suffering from depression and in receipt of disability benefits. We will examine the

effectiveness of CBT in patients suffering from depression and in receipt of disability

benefits by performing a systematic review of studies that evaluate CBT and by

analyzing the administrative database of Sun Life Financial, a Canadian private

insurance company. This would have large implications in establishing if the current

treatment funds directed to CBT represent a good investment.

Application of Machine Learning to Vision-Based Pose Data for Exercise Classification

The research will be using visual information from the phone’s camera as well as demographic information from participants and implement various machine learning algorithms such as random forests, support vector machines, etc. to provide feedback regarding different exercises to the participant. Specifically, the algorithms will classify the exercise types. Furthermore, these algorithms will be optimized for use on smart phones. The partner organization intends to incorporate the algorithms in their mobile app for mass use. Such research methods allow for a more health-conscious use of smart phones and would give the partner organization a significant edge in technological development in the health-related sector.

Predicting Treatment Sensitivity in Hypotensive Patients

Anticoagulation with Warfarin is indicated and required for post-operative cardiovascular patients. However, it is a high-risk medication with a narrow therapeutic range where sub-optimal dosing can lead to complications and even death. While multiple risk factors have been associated to Warfarin sensitivity, the prediction of optimal Warfarin dosing strategies remains ineffective and requires trial and error and close patient monitoring. This work proposes the use of machine learning and reinforcement learning algorithms to more accurately predict Warfarin requirements in post-operative cardiovascular patients, leading to decreased hospital stay and re-admission rates and increasing cost savings at cardiovascular surgery centers globally.

Multi-institute domain adaptation by adversarial constrained medical time series representation learning

Hospitals strive to perform cutting edge medical treatment, treat all patients fairly, and reduce operating costs, while also enabling caregivers to spend more time interacting with patients. Artificial intelligence and machine learning promise these things. However, medical data provides unique challenges for machine learning. Currently, if a hospital wants to include an algorithm for automated decision making, they must either secure approval to collect additional patient data or change their care practices to replicate those at other institutions. This work proposes a novel application of artificial intelligence in medicine that creates a numeric representation of patients’ electronic medical records which is constrained to be similar across all hospitals despite each hospital having different underlying operating procedures. As a result, we can directly transfer algorithms which have proven to improve care at one hospital to another, without the need for additional data collection. This research has the potential to save lives of patients who otherwise might have been overlooked, improve patient quality of life, and set a precedent for quality healthcare globally within the next three years.