Bio Window Knowledge: Personalizing Most Relevant Content from Big Data

Peer publications in the healthcare are many and held in silos. For researchers, the accessibility and utility of such publications can be problematic for a variety of reasons. Open access publication has addressed some of the issues, but the silos remain an issue. Electric Effect will provide a technology platform that breaks down the silo barrier, truly opening efficient access for all researchers.

Machine Learning for Auto-Scaling Corda Node Containers

We are looking to drive the operational cost down for Corda R3 nodes. Corda R3 is a smart-contract Distributed Ledger technology. Our strategy is to do so by minimizing the cloud computing resources. Using machine learning and historic data we can proactively orchestrate a large number of nodes on behalf of our clients. The interaction between nodes is a type of social network lending itself to machine learning.

Saccade Concussion Diagnosis System

The underlying technology will leverage artificial intelligence (AI) to analyze oculomotor (eye movement) data to learn and extract human translatable features/symptoms of concussion. The software is computationally light-weight that is capable of running on portable hardware with minimal computational power. The intern will examine the system's commercialization by conducting interviews with potential customers and identifying the additional critical features needed by end-users.

Prevalence of moderate-to-severe Osteoarthritis pain of the hip and knee by Index Joints in Canadian Primary Care: A proof of concept study from the Canadian Primary Care Sentinel Surveillance Network

Osteoarthritis (OA) is a common disease in middle-aged and older Canadians attending primary care practitioners. As the Canadian population ages and with increasing obesity, OA will become an increasing burden for individuals and the health care system. Given the potential of Electronic Medical Record (EMR) data for surveillance of the population that is at high risk of or is diagnosed with OA, we will apply text mining method to investigate this problem further.

Exploring the Potential of Convalescent Plasma Therapy as an Intervention in the Pandemic Response

Convalescent plasma--used for over a century as the first treatment option in outbreaks caused by novel pathogens. The therapy involves transfusion of blood plasma from recovered donors, which contains antibodies, that can prevent or treat infection in recipients. Convalescent plasa therapy has been observed empirically or in small studies to confer passive immunity to susceptible or already infected recipients. Very little rigorous evidence has been available to confirm safety, effectiveness, appropriate target population and delivery strategies of this therapy for specific pathogens.

Dynamic Scheduling of NPC Behaviours in Modern Video Games

Persistent Non Player Characters (NPCs) in many modern video games follow schedules guiding their routines and behaviors over time as the player engages in play inside the game’s virtual world. In a game like Ubisoft’s recently released Watchdogs: Legion, where schedules are a player-facing game mechanic, a robust scheduling system is highly important and critical to the game’s financial and critical success.
Making good schedules for NPCs in this context, however, is surprisingly complex.

Utilizing Remote Sensing and Machine Learning to Improve Poultry Farm Productivity

Within the Canadian context, poultry farmers are constrained by regulations that predetermine chicken prices and market supply. As a result, they are limited in the approaches they can take to improve the profitability of their operations. Within this regulatory framework, farmers must rely on measures that can be applied on their farms to improve chicken’s growth performance while reducing production costs. In this project, we aim to find the effective approach to utilizing remote sensing and machine learning to improve poultry farm productivity.

Pairing Meteorological and Power Data for Marine Hybrid Electric Boats

Research will be conducted to determine the best way to visualize and operationalize electric and diesel engine performance data collected in real-time for vessel owners and operators. The boats involved in this research work are candidates for using hybrid electric/diesel drive. The methods of displaying data will be explored to determine the best way to visualize the interaction of the various data points in real time. The goal is to research the characteristics of a “fit-bit” for a vessel, tracking vessel performance and supplying feedback in real-time.

Evidence-driven strategies for successful schooling outcomes of learners of African descent in Nova Scotia

Research has identified that a gap exists in the academic achievement of Nova Scotian students of African descent as compared to their peers. Taking an Africentric approach, this research aims to understand how schools, families, and communities can collaborate to provide an enabling environment for learning so that Nova Scotian students of African descent succeed in school.

AI-based Platform for Population-level Social Isolation Detection and Prediction

Social isolation is a serious public health issue which has many negative effects on quality of life and well-being of individuals. This research project aims to develop and test a Minimally Viable technology platform (MVP) to tackle population-level social isolation. This platform is designed to collect and analyze surveys from the users and detect socially isolated people and identify individuals at risk of isolation in a community using AI and social network analysis techniques.

Pages