Dynamic Binary Instrumentation of Embedded Systems

The proposed research project focuses on the dynamic analysis of embedded systems. The project has a duration of six months and aims to achieve two objectives: (1) to evaluate the applicability and effectiveness of a newly proposed QoS-aware dynamic instrumentation framework on real-word time-sensitive applications, and (2) compare the outcome to that of an existing state-of-the-art framework. For this purpose, the intern will get access to real-world applications provided by the partner, Labforge, Inc.

Development of a Novel Marine Icing Prediction Model

All shipping and marine activity is subject to risks, such as flooding and capsize in extreme seas. Shipping in cold winter conditions is subject to additional risks, such as ice accretion on the topsides, which in extreme cases can cause capsize. The catastrophic capsize of smaller vessels due to icing is still taking place, with the subsequent loss of life (Arctic Operations Handbook 2013). The consequences of a capsize in a remote area has a large financial and regulatory impact as well as subsequent environmental damage to the ice prone areas.

Innovative Designs in Methane Sourcing

The purpose of this project is to change the way piplelines are sourced for potential leaks. Currently, gas sniffers that detect gas near the pipeline monitor subsea pipelines. However, these sniffers do not differentiate between gas types and are unable to determine the source of the detected gas. Therefore, sniffers are unable to confirm if the detected gas is thermogenic methane leaking from the pipeline or an alternative nearby gas. This can lead to costly false positives that make the process inefficient.

Evaluating offline functionality of progressive web applications in e-commerce business: A/B testing and causal models

The project is to understand the potential impact of enabling the offline functionalities on progressive web application utilized as e-commerce platforms. For instance, will enabling offline functionalities help increase revenue by providing a more engaging environment when the connection is poor? Traditional evaluation method is to run online controlled experiments by randomly assigning users into two groups: with and without the feature. However, to accurate assess the impact, one needs to identify appropriate key metrics to quantify the performance.

Machine Learning for the Telecommunication Industry

Ericsson is an industry leader in offering telecommunication solutions and products. As an important step on the path towards the automatic and autonomous management of next generation networks, Ericsson is developing technology in machine learning and artificial intelligence that will benefit operators around the world, including in Canada where Ericsson supplies technology to most of the major telecommunication network operators.

Data Analytics for Social Network Marketing

Influencer marketing is a new and innovative way for brands to target their customers on social media in a highly accurate and trusted way. Brand partners work with hundreds of influencers over a period of time, which is called a campaign, to create marketing material. This marketing material is shared by both the brand and influencer to the audience of the influencers, who are followers on social networking platforms such blogs, YouTube, Instagram, and Facebook. A key challenge in influencer marketing is to identify influencers with the greatest social networking reach.

Reversing the ‘brain drain’: Where is Canadian STEM talent going and why?

Human capital migration, or “brain drain” as it is more commonly known, is a long-debated subject in Canadian public policy. This process involves large-scale emigration of talented individuals, educated in one country, but who choose to work in other countries to seek out higher salaries, prestige or greater occupational mobility. While this phenomenon has been long debated and discussed – mostly in relation to doctors and other medical professionals - policymakers in Canada are still often left wondering why highly skilled Canadians opt to work abroad.

Multi-Perspective Text Analysis of Social Knowledge Networks

Knowledge workers (i.e., researchers, business consultants and analysts, research-program managers) produce documents (research publications, analysis reports, opinion pieces, calls-for-proposals, and blog posts) through which they express their knowledge and opinions. They also read and review similar documents, produced by individuals and organizations in their domain of interest and expertise, to keep current with their domain.

Interactive Mesh-based Volumetric Visualization

Our industrial partner, LlamaZOO Interactive Inc, publishes the first-of-its-kind digital anatomy study and reference app, EasyAnatomy. For this app, dissecting an animal model and see its internals are important facets of the learning experience. Through our research, we will enhance this experience by designing an interactive 3D visualization of an arbitrarily dissected model, and accelerate the graphics rendering for mobile devices; enabling personal, interactive learning experience anytime, anywhere.

Privacy Preserving Federated Learning

5G, cloud and IoT confederation vision is to revolutionize the internet by fostering billions of interconnected mobile and embedded devices, sensors, and services, exchanging information in order to build smart, self-conscious autonomous environments. Yet, the ubiquity and value of connected devices and their applications cannot hide their security and privacy challenges. The enormous amount of data sensed and communicated over a fusion of heterogeneous networks, became an increasingly attractive target for cybercriminals.