Innovative Projects Realized

Scalable Fault Detection, Diagnosis, and Situational Awareness for Modern High-volume Data Pipelines

Globally, industries are seeking to develop new products and services from the large-scale data sets they hold. As these systems move from prototypes into fully operational 24/7/265 commercial solutions additional services must be provided to detect and address system faults and failure as they arise. Within classical engineering plants, e.g., those of the telecommunications, petrochemical, transportation, etc. industries, these tasks are performed by fault detection and diagnosis (FDD) and situation awareness solutions. This Accelerate project will design and implement a prototype FDD and situation awareness solution for this emerging high-volume data pipeline industry. The solution will be tested and operationally assessed for two industry-held high-volume data pipelines, one in the telecommunications industry and one in the cyber-security industry.

Application of artificial intelligence for modeling driving behavior supported with real time trajectory development

The proposed research work is aimed at developing trajectory data on a real-time basis. On successful completion of the project, a real-time image processing framework will be available for developing innumerable trajectory datasets over the study sections. These datasets can enormously boost current driving behavior studies and facilitate Connected Autonomous Vehicles (CAV) research. Along with this, the trajectory database can be a potent source in understanding different traffic stream aspects, such as stability, safety, and attention. Later, the research work will also test AI concepts in modeling driving behavior. In addition, the potential of AI in simulating driving behavior will be assessed. Such driving behavior simulation has a huge potential in addressing the limitations of conventional behavioral models, like expressing stochastic driving behavior, assuming non-uniformity, finally improving the precision in modeling. Besides, in the present project, it is planned to carry the traffic flow modeling using Artificial Intelligence (AI), on successful modeling this can act as frame work in understanding traffic flow characteristics with AI.

Conceptual Design for Aircraft with Complex Aerodynamics

The proposed project is part of a larger effort to develop more suitable conceptual design methodologies for aircraft that account for the complex aerodynamic interactions of novel concepts, for example as present with distributed propulsion concepts. For the project an advanced aerodynamic code will be integrated in an existing larger design methodology. The advantages will be improved quality in the predictions with fewer computational required resources. The benefit will be new aircraft design that can better address our aviation needs while having reduced environmental impacts.

Characterization of the lateral hypothalamic neural outputs using camera-based multi-fiber photometry

Understanding how brain processes information is the one of the most intriguing questions that modern neuroscience faces. This project is aimed to characterize how the lateral hypothalamus process information to downstream brain targets to guide proper behavioral responses. This brain area is well-known to regulate key aspects of the behavior. But how does it process information to control behavior? To answer this question, we use and develop a state-of-the-art technique called fiber photometry. This approach allows to measure neuronal activity of specific neural pathways deep in the brain of a free-moving animal performing different behavioral tasks. In this program, in collaboration with the partner organization, we will use the Doric Lenses fiber photometry system, and improved it to democratize its uses for the needs of researches studying brain functionality.

Active Learning for Fish School Recognition in Echograms in the Bay of Fundy

OERA use hydroacoustic echosounder surveys to evaluate the impact on marine life of tidal turbines in the Bay of Fundy. OERA use Echoview software to read in the raw sensor data (e.g. voltages) and convert it to a visual representation. Echoview contains some algorithms to detect the bottom of the ocean. However, the Fundy data is very noisy from several sources including air bubbles, “entrained air” pushed below the surface of the water, and irregular surfaces on the bottom of the ocean. In order to analyze the survey data, manual pre-processing is currently required to annotate the data. This manual process delays the turnaround, potential consistency and provides opportunity for inconsistency.
This project will train a machine learning model to detect and filter noise in the hydroacoustic sensor data, allowing OERA to improve the accuracy, consistency and manual effort required to pre-process its data. By identifying “bad regions” in hydroacoustic data collected near underwater turbines in the Bay of Fundy with a model to automatically extract these regions from future survey data, OERA will be able to apply greater speed, consistency and accuracy to data processing to prepare for rigorous analysis.

EMR Clinical Decision-Making Application for Hamilton Health Sciences ChronicPain Centres

The proposed internship will provide an opportunity to observe and evaluate the implementation

process of an Electronic Medical Record (EMR) application. It is an opportunity for an eHealth

student to evaluate from many different viewpoints: programming and software development in

response to requests for clinical and academic deliverables; training and introduction process for

business support personnel and clinical personnel; melding of the EMR in to the clinical flow of

patients, utility as a pre-screening tool to facilitate clinical decision-making for triage and scheduling;

performance of the EMR clinically and from an academic standpoint

Conception d’un nouveau système prototype de pultrusion pour l’élaboration et la fabrication de matériaux composites de pointe à base de résines thermoplastiques

Dans les domaines de la fabrication industrielle, la tendance est au remplacement progressif des matériaux classiques (plastique, acier, aluminium, etc.) par des matériaux composites ou polymères renforcés de fibres (PRF) à cause de leur excellente résistance, poids léger, faible densité, excellent module d’élasticité et forte résistance à la corrosion. Aujourd’hui, pour la fabrication de matériaux composites pultrudés, l’industrie utilise surtout des résines TD qui ne sont pas recyclables. De plus, ils sont considérés comme substances dangereuses. L’utilisation de résines TP pour la production de matériaux composites pultrudés détient un avantage sur celle des résines TD puisqu’elle permet de modifier la forme du composite après sa fabrication. De plus les TP sont réutilisables et recyclables. L’objectif du projet est le sélectionner de nouvelles résines TP liquides qui permettront de fabriquer des pièces composites par polymérisation in situ du polymère lors du procédé de pultrusion. Simultanément, nous allons développer et fabriquer un système prototype de pultrusion TP, compatible avec les nouvelles résines TP et se basant exclusivement sur une polymérisation contrôlée in situ.

Blood flow within microfluidic conduits

A current area of focus at SMT Americas is to develop injection-moulding methods for medical lab-on-chip (LOC) devices, particularly to transport and process blood and plasma while eliminating conduits clogging and reducing sample loss. This project will evaluate the effect of flow conditions on viscosity of samples, and the adequacy of conduit structures achieved with SMT Americas’ technology for cell separation. The resulting data and analysis will aid the intern to support particular segments of her project in developing a point of care microfluidic chip that separates blood plasma from its cells for sample sizes less than 100?L. SMT Americas will understand and resolve their current limitations in developing conduits for cell separation, with further objectives to increase the blood and plasma flow rates within their micro-conduits, while reducing sample loss.

Private conservation in a changing landscape: a perspective on Land Trust Organizations in Canada

Land Trust Organizations acquire and protect private land for conservation purposes. They have become the fastest growing tool for biodiversity conservation of private land in Canada. Despite their growth and the recognized importance of private protected areas; there is little information about them. This research aims to understand who the Land Trust Organizations are (e.g. size, level of protection, funding, governance structure, ecological monitoring) and the important opportunities and challenges they face. This baseline information on Land Trusts will contribute to making an informed decision of a nation-wide collaboration model of the organizations. This will support the changing of their political systems, to help humans live within Earth’s carrying capacity.

Extraction and identification of potential active ingredient from expired pharmaceutical drugs

Every year billions of doses of medications go unused by patients in North America. Some of these are returned to pharmacies for appropriate disposal, but the majority of these are discarded in landfills or flushed into municipal wastewater streams. Our goal for this initiative is to collect unused and expired pharmaceuticals and develop a sustainable method to extract the active compounds, and to establi

Comparaison des effets d’une stratégie d’apprentissage par problème avec les rétroactions vidéo sur la prise de décisions de jeunes hockeyeurs de 12 ans

Les meilleurs joueurs prennent la bonne décision, au bon moment et peu importe le contexte. Les habiletés de prise de décisions sont essentielles au développement du jeune joueur rêvant d’atteindre les sommets de son sport. En partenariat avec l’Académie Ulysse, le présent projet vise, pour commencer, à élaborer une approche par problème pour améliorer la prise de décisions de joueurs de hockey Pee-Wee. Ensuite, le projet prévoit comparer les effets de l’approche avec ceux des rétroactions vidéo traditionnellement utilisées par les entraîneurs. Puisque l’approche par problème place les joueurs dans des situations collaboratives où ils construisent eux-mêmes leur connaissances tactiques, l’hypothèse est l’apparition d’une meilleure rétention des habiletés de prise décisions suite à la participation à une approche par problème.

Evidence based delivery of effective packages of health services in humanitarian, fragile and conflict affected settings

Maternal, and childhood mortality and morbidity rates continue to rise in conflict affected areas. The Canadian Red Cross (CRC) is collaborating with the International Committee of Red Cross (ICRC) to implement Advanced Health Partnership (AHP) framework to provide health care to populations directly in war zones and conflict settings, without access to healthcare as a result of conflict. In delivering these services with a focus on providing services to women an, children, there is an opportunity to ensure that delivery of these services is based on best available practices and good quality data for evaluation of these services is generated. Through this internship, I will work with the Global Health Unit of the CRC and collaborate with the ICRC in the implementation of the AHP framework. I will analyze existing frameworks for providing health services design study to evaluate the delivery of AHP pilot project in South Sudan.