Using Machine Learning to Optimize a Workflow Management System.

Workflow management frameworks support the creation of task dependencies and make efficient use of resources while running those workloads. Typically, these tasks can be long running processes like machine learning algorithms or access data from databases. Workflow management consists of mapping tasks to suitable resources and the management of workflow execution in a cloud environment. The goal of this project is to optimize the job scheduling algorithm using machine learning techniques in a workflow orchestration framework that manage workloads across a heterogeneous system.

Development of a nanonewton force sensor for in-situ characterization of nanomaterials

Nanomaterials are the fundamental building blocks of nanotechnology. Despite the advances in nanomaterial synthesis, no reliable technique exists to characterize their physical properties. The key challenge lies with the lack of accurate force and displacement feedback. To tackle the problem, leading researchers from University of Toronto and from Toronto Nano Instrumentation (TNI) Inc. are working together to develop the next generation technology for nanomaterial testing.

Weibull modeling of part modification reliability for the use of return on investment (ROI) estimates

When Bombardier comes across reports from their customers regarding frequent part failures, they investigate reasons for the cause of these failures. If many reports are received, all due to similar faults on the same part, design changes are made to the part to make it more reliable. Once the newly designed parts are available for purchase, Bombardier informs their customers of the part and is often required to provide an expected return on their investment/purchase (ROI) of a new part.

Automated Integrated Model for Earned Value measure (AIM: EVm)

Earned Value Management (EVM) is a better way of managing project on the weekly or monthly basis. The EVM allows managers to be on top of their project budgets and deadlines. When managers complete projects on time, and within budget, the projects are said to have earned value.
With the increased number of information available concerning projects within a modern organization, the question is about how to develop a better means to calculate the value earned by completing a particular project.

Data Science Search Engine Optimization

Search is an important way people get the information they want. Whether we want to find more content about a specific topic, or get general information on a subject, search engines lie at the core of this process. At Flipp, search plays a crucial role in the overall user experience and drives relevant content to consumers. Consequently, improving search by assisting consumers in finding a larger volume of relevant products will be of growing importance to Flipp. The proposed project aims to improve Flipp’s search experience by achieving greater relevancy, volume and ease of use.

Visualization, understanding and engineering of machine learning models for entity recognition

Machine learning is a discipline of teaching computers repeatable tasks that humans do well but slowly. At Interdata we are on a mission to use Artificial intelligence to understand the data being stored by organizations and the relationships between those data assets. As such Darrell will be working on methodologies and tools to expand our understanding of the algorithms we develop in order to improve them. He will then use those methodologies and tools to engineer new algorithms to be used by the organization to categorize and tranform data.

Hydraulic Fracturing Process: Mechanics, Monitoring and Optimization

Hydraulic Fracturing or fracking has been extensively used in the extraction of hydrocarbon fuels in unconventional reservoirs. This process bears significant economic and environmental implications. The partner, ExGeo, has been providing professional services to the petroleum companies to monitor the fracking process using microseismic signals. To improve the precision of field monitoring and optimize the fracking process, this research will first try to understand the mechanics of fracking through highly controlled and fully instrumented laboratory experiments.

Speech recognition for older, pathological voices

Some diseases and brain injuries can seriously impair language. Patterns in an individual's speech can allow computers to describe these impairment with a high degree of accuracy. These techniques can be used to test large groups of people for drug trials and potentially replace pen-and-paper based testing methods. To fully automate this process, speech recognition systems can be used to automatically transcribe speech. Unfortunately, these technologies continue to perform relatively poorly for elderly speakers, or for individuals with speech disorders.

Multi-user Training Software Development and Otoscope Tracking for Otolaryngology Education

Simulation is being used increasingly to improve medical education by providing students and trainees with greater access and opportunity to learn critical skills without affecting actual patient care. To this end, OtoSim has developed a multi-user training platform and an otoscope tracking device. The multi-user training platform allows the trainee to self-learn while being electronically connected to a central database for monitoring and advice.

Optimization of the immune response against transferrin receptor based vaccines

The bacterial transferrin receptor is considered to be a potentially efficacious candidate vaccine antigen against pathogens important in human disease and in animal husbandry. Previous data suggests that transferrin receptor-based antigens can elicit protection from both invasive disease and potentially from asymptomatic colonization. One major consideration when developing vaccines is the choice of adjuvant, a component able to influence the intensity, quality and breadth of the immune response.