Risk aggregation beyond the normal limits

Risk aggregation is omnipresent in insurance applications. A recent example, borrowed from the modern regulatory accords, is the determination of the aggregate economic capital and its consequent allocation to risk drivers. A more traditional illustration of the importance of risk aggregation in insurance is the celebrated collective risk theory that dates back to the early […]

Read More
Automation of Event Detection for ISA Cybersecurity Inc.

The purpose of this initiative is to design and develop a highly advanced data analysis platform. This platform would address the need for a much higher degree of threat event detection efficacy by conducting big data analytics and determining relationships between a large number of fields. The goal being to identify patterns of data that […]

Read More
Build Data Pipeline for ML Applications with Kubeflow

In order to create value for the users, Dataraction needs to be able to provide insights and foster knowledge sharing and production from peer-learn activities. To do that, the ability to deploying effective machine learning applications is critical. Kubeflow will give the company the advantage with a well-structured data pipeline that can connect with many […]

Read More
Weakly supervised representation learning for sequential and composite actions.

Camera enabled AI-based personal assistants will need to recognize human actions in order to be safe and effective. Current machine learning approaches for action recognition require extensive datasets of annotated videos that depicting the actions to be recognized. Such datasets are expensive to acquire. The goal of this project is to decrease the annotation required […]

Read More
Advanced Text Clustering Algorithm for Aircraft Applications

CaseBank provides a service called ChronicX™ to the airline industry for the purpose of detecting and managing repeat defects, i.e. faults that have eluded resolution repeatedly. Each night, airlines upload their raw maintenance records to the CaseBank server. ChronicX applies text mining methods to eliminate irrelevant records, and search for defects that are repeat occurrences […]

Read More
Developing a watershed approach to manage anthropogenic and environmental stressors in an eastern Lake Ontario watershed

Water quality in the watersheds of the Great Lakes are under ever-increasing pressures from population growth, urban expansion, economic development, nutrient enrichment, and climate change. We aim to develop a statistical model to understand the relative influence of anthropogenic stressors on water quality for the central Lake Ontario watershed surrounding the cities of Oshawa, Whitby, […]

Read More
Deep learning-based illuminant estimation for mobile devices

Humans possess the ability to see objects as having the same color even when viewed under different illuminations. Cameras inherently lack this capability. A process called auto white balance (AWB) has to be applied by the camera to mimic this behavior of the human visual system. AWB is one of the first steps in a […]

Read More
Assessment of Diclofenac and its impact on some selected aquatic fauna of India (Western Himalayan Region) and Canada

The proposed project aims to assess the impact of Diclofenac on freshwater fauna. Current research work in this area will be beneficial to characterize potential risks from long term low-level exposure to pharmaceuticals like Diclofenac, particularly for sensitive aquatic organisms and hence, this project will attempt to evolve various measures for sustaining and safeguarding the […]

Read More
Indigenous peoples’ representation in the Greater Toronto Area construction industry

This research project seeks to identify and draw attention to the historical factors leading to the underrepresentation of Indigenous workers in unionized sectors of the construction industry; the problematic relationship between Indigenous workers and their non-Indigenous counterparts, employers and trade unionists; and past and present efforts to address these problems. This work will aid in […]

Read More
Physiological Data Analysis and Credibility Assessment

The subject of assessing credibility is not new. What we are proposing in this project, on the other hand, is novel. It has been shown in various context that assessing credibility is extremely difficulty. In this project, we take a data-driven approach, relying on fundamental knowledge of neural physiology and data collected by NuraLogix, our […]

Read More
Student

The proposed project will involve reviewing the current processes involved in recruitment and selection at the organization. The objective would be to find out what knowledge, traits and experiences the right candidates should have, and how the organization can go about recruiting, hiring and motivating them. The recent move to remote work has presented s2h […]

Read More
Wild bee pollinator habitat restoration through dietary breadth, nutrition and microbiome characterization across Canada

Wild bees are vital to our parks, gardens, greenspaces and ecosystem services, but we know surprisingly little about their habitat requirements and dietary breadth. In this proposal, we will characterize wild bee nutrition including their health and microbiomes across Canada. The postdoc will learn skills in bioinformatics, science writing and science communication. The W. Garfield […]

Read More