Innovative Projects Realized

High Energy, RAnge extending battery for Electrical Vehicles (HERA-EV)

We can deal with the daunting challenges of depleting fossil fuels as-well-as the toxic and greenhouse gases emitted from the gasoline/diesel driven vehicles by replacing their internal combustion engine with rechargeable batteries. This project focuses on the development of an all-metal-free and biocompatible rechargeable battery system that will compete with the existing counterparts (Lithium-ion batteries, LIBs) in Electric Vehicles (EVs) currently under development. We herein propose to design and develop dendrite-free organic anode, porous air-cathode, and solid-biopolymer electrolyte based solid-state batteries, having high energy density, enhanced service-lifetime, lightweight, cheaper and much safer than LIBs. This new metal-free, low-cost and solid-state rechargeable battery system when equipped in Ford vehicles (Ford is the industrial partner in this project) will not only enhance their driving range between consecutive recharge but will also provide a sustainable and eco-friendly solution to deal with the environmental problems and rising energy demands in the automotive sector.

Using Rapid Eye Movement (REM) Sleep to Enable and Enhance Clinical Epilepsy Surgery

A seizure is a medical emergency. 1 in 10 people will be hit by at least one seizure in their lifetime. 1 in 26 people continue to be hit by seizures recurrently: this is epilepsy. When medications do not work, surgery is needed to cut out seizing brain tissue. Unfortunately, many people cannot presently benefit from epilepsy surgery. Our research will harness the power of dream sleep (rapid eye movement or REM sleep) to help locate where the seizures are coming from. Empowered with this information, we can help guide the surgeon on where to perform life-changing epilepsy surgery. Our research will partner with the HSC Foundation, affiliated with Manitoba’s flagship hospital for neuroscience (Health Sciences Centre), to further its goal of advancing research and cutting-edge health care for the benefit of all Manitobans.

Edge-Twin based Framework for Real-Time AI Applications for Vehicular Scenarios

Edge computing is expected to play a transformative role for future AI applications in 5G networks by bringing cloud-style resource provisioning closer to the devices that have the data. Instead of running resource-intensive AI applications at the end devices, we can consolidate their execution at the edge, which brings many benefits, such as eliminating the redundant task processing, running machine learning (ML) tasks with sizeable data sets and running ML tasks in a spatial context that is shared by many devices. The downside of using edge computing for AI is the latency of transporting the data from the end device (e.g., a vehicle) to the edge servers and processing it there and getting the results back to the end device. This project will focus on developing a novel edge twin concept that extends the digital twin idea to maintain computing state at edge computing systems. The objective of edge twin is to model and control a complex system of IoT in a highly responsive manner. To achieve this objective, we will investigate many ideas, and one of them is time shifting.

Development of a highly accurate machine learning algorithm constrained by well-log data and its application in Lithological classification

The drilling success rate is the most important goal for any oil/gas company. For a start-up company, any failure in drilling will be a disaster. To this end, the Petro-Lin Energy Corp. wishes that through the combination of mature hydrocarbon prediction techniques and new research results such as machine learning, the success rate of hydrocarbon prediction, the theoretical basis for well placement can be provided in Roncott oil-field, which will improve the success rate in drilling. The University of Calgary is one of Canada’s top research institutes, especially in the areas of exploration geophysics, seismic data processing and petroleum engineering. On the other hand, Petro-Lin Energy Corp. will collaborate with researchers from University of Calgary to access the most up-to-date research results and the most advanced technology available in precise well placement, so that the drilling success rate can be improved to reduced drilling cost and environment impact, and it can effectively save the partner’s research cost. In addition, through the two-year project, the intern will receive hands-on industry problem and other training activities.

Redefining Recreational River Waves

Wave surfing was traditionally restricted to oceans. Nowadays it is becoming more and more popular in rivers. Although there are some natural surfable waves in rivers, human constructions can provide waves even where they do not naturally exist. However, there is not enough academic support for design and construction of these waves. In this project, the research intern utilizes physical river models to simulate river surfing waves. The industrial partner defines the existing problems and ideas of wave construction which is a result of 10 years of construction experience around the world. The academic supervisor brings the theory of hydraulics and scientific approach to help solving the problem. The main purpose of the research is to optimize and develop an adjustable structure for wave forming. How to sculpt safe and more attractive waves with dynamic shapes is the question that will be answered.

Competency-Based Education for Airside Professionals

This project will analyze competencies (knowledge, skill, and attitude) of airside professionals conducting the taxi-ground run of an aircraft in an operational airport environment. Both cognitive task analysis and consensus modeling methodologies will be used to identify competencies and draft a competency framework of the task. Based on the competency framework, training implementations (including those using Virtual and/or Augmented Reality, Gamification and other immersive technologies) will be developed and evaluated to assess the effectiveness of these approaches.
This work is significant because airside worker human error can cause damage to aircraft, injury to persons, time loss causing costly flight delays and other significant operational costs (such as loss of luggage). Competency-based education is increasingly used within aviation to align training with the actual professional competence required to complete a task safely and efficiently. This project will evaluate several methodologies in the identification of competencies, the results of which can translate to other professional positions.

Self-Adaptive Penetration Tests with Deep-Reinforced Intelligent Agents

Penetration testing is a key security tactic, where defenders thinks like an attacker to predict the latter’s actions and develop effective defense. However, for large-scale cyber-physical infrastructures like the smart grid, traditional penetration tests on individual devices or networks are insufficient to exhaust all potential exploits or to reveal infrastructure-level vulnerabilities invisible to the local system. The project aims to close the gap by developing collaborative autonomous agents that can inspect a large-scale infrastructure to identify critical vulnerabilities that would be otherwise invisible to the operators and defenders. To this end, the project will develop innovative deep reinforcement learning agents that will automatically conduct penetration tests in complex dynamic environments and adaptively update their strategies to identify the most impactful exploits. The project will deliver a systematic methodology that enables proactive search for critical vulnerabilities in 5G-connected smart critical infrastructures and promote early defense actions to mitigate the potential risks.

Design and Refinement of a Colour-based Metabolomic Biosensor System

This project involves designing a portable device for measuring concentrations of certain metabolites in a person’s blood or urine. This is an easy-to-use device that connects to a smartphone to display a final result based on measurements of multiple components to generate a specific health diagnosis. Different tests can be run on the same device. The device works by loading custom-made fluidic chips into the device which contains dried chemical reactions. The chip moves the urine or blood to the reaction sites, where a reaction occurs causing a colour change proportional to the amount of the specific metabolite in that blood or urine. The device can measure this colour change and relate that to a concentration automatically, and interpret the results.

Machine Learning and Data Mining Approaches for Smart Buildings

The goal of this project is to develop machine learning and data mining algorithms relying on non-intrusive common sensor data to estimate and predict smart buildings’ occupancy and activities. Efficient feedbacks are automatically supplied to the end user to involve occupants and increase their awareness about energy systems. This consists of generating reports helping the occupant to understand his/her energy management system and thus to be involved in the decision-making process. The project directly aligns with Ericsson’s IoT mission and expands its operator potential opportunities by exploring a dimensionality in real-time automation, monitoring and tracking, and smart surveillance. It also further strengthens Ericsson’s position in the IoT market which has a projected additional revenue potential of up to 36% (USD 619 billion) by 2026. Moreover, the machine learning techniques to be developed can be easily adapted to other problems of interest to Ericsson.

Stable isotope measurements of vanadium and molybdenum as tracers for treated oil-sands process affected water

Petroleum coke (PC) is a by-product of the extraction of crude oil from the Oil Sands in northern Alberta and has been shown to effectively remove total acid-extractable organics from oil sands process-affected water. This treatment may also lead to an increase in some heavy metals in the treated water and it is important to distinguish between coke-derived elements and those found naturally. The objective of the project is to develop an understanding of the sources and sinks of vanadium and molybdenum in the petroleum coke treated water in the Athabasca Oil Sands Region. This knowledge can be used to identify and potential environmental concerns.

Side-Stream Nitrogen Treatment using a Membrane Aerated Biofilm Bioreactor (MABR) System: A Pilot Scale Demonstration

Municipal wastewater contains excessive nutrients, which when discharged without sufficient treatment can cause eutrophication in the receiving water bodies. Digested sludge liquor, the produce water generated from the treatment of sludge that is produced from municipal wastewater treatment plant contains high concentrations of ammonia that is toxic to aquatic biota and requires further treatment. Newer and less energy-intensive processes, such as the nitritation/anammox (anaerobic ammonium oxidation) processes are emerging, but information on the implementation of these processes at the full-scale is limited, especially for operations under cold Canadian conditions.

In this study, we propose to employ the nitritation/anammox processes at the pilot-scale in a membrane aerate biofilm reactor (MABR) to estimate the operation strategies for ammonia-rich sludge liquor treatment. This objective will be achieved through multidisciplinary studies combining expertise in wastewater treatment, biofilm microbiology, and bioreactor development from the University of Alberta, and full-scale bioreactor design and operation from EPCOR.

Enhancing data collection procedures for non-destructive chicken egg fertility determination using NIR hyperspectral imaging

The hatchery industries are faced with huge economic losses in millions of dollars, resulting from incubating nonfertile eggs that will never become chickens. There is therefore an urgent need for non-destructive techniques to predict the fertility chicken eggs early enough (especially prior to incubation). The project seeks to solve the identified problem via optimizing modelling parameters and performances of new and existing egg models using state-of-the-art hyperspectral imaging technology in conjunction with pattern recognition and multivariate analyses. This study will eventually come out with deployable chicken egg fertility classification models using adequate amount of light source illumination, optimised egg orientation position and appropriate targeted modelling features. Modelling results will eventually be ready for deployment in an industrial online multispectral imaging classification system for chicken eggs.