Innovative Projects Realized

Real-time fatigue detection by remote eye tracking

Fatigue is a significant risk factor for operating moving vehicles in work settings that involve long duty hours or shift work rotations. A critical objective in fatigue management is to develop technology to establish fitness for duty, monitor fatigue in real time and predict performance failure. Eye movements (eyelid closure, blink rate and duration) are sensitive indicators of fatigue. SIX Safety Systems has developed an eye tracking system that can monitor eye movements remotely. The objective of this Mitacs supported research internship is to validate this tool as a fatigue detection method in motor vehicles, by correlating eye movements with performance on attention and driving in a high fidelity driving simulator, and with electrophysiological and subjective measures of fatigue. The proposed project will directly benefit the partner organization in providing scientific validation crucial to bringing this tool to market. The technology has considerable potential to benefit the health and safety of Canadians and to generate economic activity

Ecosystem-based management research for Canada’s Sablefish fishery

The fishery for British Columbia’s Sablefish (Anoplopoma fimbria) is one of Canada’s most valuable marine fisheries. This project addresses the two primary strategic challenges currently facing this fishery: (1) lower harvest quotas aimed at rebuilding the spawning biomass to more productive levels risks the economic sustainability of the industry and (2) future access to fishing grounds could be in jeopardy without improved information about the ecological impacts of fishing on non-target species and seabed habitats. Our research will apply advanced statistical and modeling methods to identify and develop novel ways of utilizing existing fishery databases and fisheries sampling power to address these challenges. We will identify causes underlying Sablefish size-selectivity patterns inb multiple fisheries, as well as conditions leading to undesirable catch and at-sea discarding of juvenile Sablefish and non-target, bycatch species. These analyses will utilize large existing databases of Sablefish tag releases and recoveries, fishery-independent surveys, and detailed set-by-set fishery catch and species composition. We will also use machine learning and spatial modeling techniques to identify the locations, types, and sensitivity of deep sea habitats contacted by Sablefish trap fishing gear based on video, audio, and motion-sensing data obtained from autonomous, deep water camera systems, which we’ve developed previously.

GIS and AI for the recognition and mapping of power grid assets

(1) ESMIA offers expertise in modeling integrated 3E (energy-economy-environment) systems for strategic decision-making at the municipal, regional, national, and global levels. ESMIA’s expertise is recognized by numerous private sector clients and various levels of government in Quebec, Canada, and around the world. ESMIA’s goal is to provide solutions that enable the achievement of energy security and transition objectives while ensuring sustained economic growth.
(2) The energy transition and power system planning increasingly require accurate and up-to-date spatial information on existing infrastructures. Unfortunately, publicly available inventories of power grids, such as transmission lines, substations, and generation facilities, are often confidential, incomplete, heterogeneous, or limited in spatial resolution. The main challenge of this project is to leverage recent advances in artificial intelligence (AI), particularly in image recognition applied to satellite and aerial imagery, to develop and automated, scalable, and reproducible mapping of power grid assets.
(3) The resulting information will serve as valuable input for ESMIA’s strategic and operational optimization models. An accurate mapping will improve the representation of transmission constraints in NATEM (North American TIMES Energy Model), and by identifying the actual routes of transmission lines and the location of substations, the model will better capture regional transfer capacities, potential bottlenecks, and associated losses.

Reservoir Souring Work – Understanding the Cycling and Conversion of Sulfur in Offshore Petroleum Reservoirs

The chemistry, thermodynamics, and transport phenomena of sulfur compounds in upstream petroleum operations is important as it impacts materials used in the production and processing systems, health and safety plans, treatment processes, and transport of petroleum. In offshore operations these impacts are magnified due to the remoteness of the operations and infrastructure limitations on the platform. Sulfur is introduced into offshore reservoirs through the injection of seawater containing sulfate and/or existing organic sulfur compounds in the reservoir. During the production and processing, sulfate converts to other sulfur compounds such as hydrogen sulfide, thiosalts, and sulfides, among others. How the sulfur is transformed determines the scale of impact and treatment and mitigation processes. The objective of this cluster is to better understand the cycling of sulfur at upstream and downstream temperatures and pressures, and the adsorption/absorption behaviour of sulfur compounds. The research will involve the following sub-projects: Sampling protocol development; Sulfur Chemistry; Development of green based solvents for sulfur removal; and Studying and modeling of localized pitting corrosion using molecular modeling techniques for oil and gas industry in harsh environment.

Towards a safer and more efficient communication process in aircraft ground deicing

Deicing is a complex process involving many actors including pilots, air traffic controllers and the deicing crew. In this context, communication mistakes can easily happen but can also have terrible consequences. The goal of the research project is to identify high risk areas of communication for aircraft ground deicing. Analyze of the voice interaction between the different actors involved with conversation analysis will be the starting point. After identifying problems in the communication process, the research will propose an improved approach to communication. Through this research the partner organization will be able to anticipate potential communication errors and can use this knowledge to optimize their communication process.

Designing and Promoting a Balance & Mobility Program for Seniors: Strategic Growth for Physio and Co.

Physio & Co. provides multi – disciplinary care and rehabilitation to several communities in Newfoundland and Labrador (NL). We have operational clinics in St. John’s, Bay Bulls and Placentia with a large variety of age groups with a multitude of injuries and issues. Our therapies consist of Physiotherapy, Chiropractic, Occupational Therapy, Acupuncture, Massage Therapy, Reflexology, Counselling, Kinesiology and Yoga. We work tirelessly to improve our patients physical, mental and emotional well being in order to support a healthy, happy and active lifestyle.

Senior citizens make up a high percentage of our patient caseload in each of our 3 clinics. This age group seek our services for many reasons but falls, effects of inactivity and overall muscle weakness are most common. Adults aged 65 years and older are at increased risk for falls. This risk can be attributed to a number of factors, which can include decreased mobility and balance, muscle weakness and visual impairment among individuals (Government of British Columbia. What Contributes to Falls? 2023 October 11). Fall-related injuries among older adults can have serious health and social consequences, impacting the quality of lives and even causing deaths.

For these reasons, we are very enthusiastic to create a Balance and Mobility program for the focus of fall prevention for seniors.

Detection of Coalition Attacks for Online Advertising

As the Internet has become part of people’s daily life, online advertising has also been more and more popular for its instant global communications. Of a number of factors on the cost of the advertising, a major consideration is the number of views of the ads, clicks to the ads, and conversion generated by the ads. Publisher fraud is the action that generates invalid traffic to the ads by inflating the number of views, clicks and conversions. With the increasing popularity of online advertising, publisher frauds become more and more sophisticated nowadays, and more advanced techniques are required to detect them. Coalition attacks is a type of recently prevalent publisher frauds that classical detection techniques are insufficient to identify them. The objective of the project is to study and develop new algorithms to automatically detect the coalition fraud actions of the publishers and therefore reduce unnecessary cost of the advertisers. The results will directly benefit the partner organization by increasing the efficiency of their platform to advertisers.

Distribution feeder voltage control with a high penetration of distributed generation

In this project, a methodology for controlling the distributed generation resources connected to the distribution system level will be developed. This control strategy will improve the efficiency and reliability of the operation by decreasing the losses, managing the assets, and increasing the system reliability. There are currently several feeders in the BC Hydro distribution system with considerable amount of distributed generation installed. This has caused voltage problems at the feeder level and also control issues at the substation level. This project is supposed to overcome some of these challenges and increase the penetration level of distributed generation without jeopardizing the system operation limits.

Évaluation de la faisabilité d’utiliser et d’implanter le programme Jintronix à domicile dans le but de prévenir le déclin fonctionnel chez des aînés encore autonomes qui consultent les urgences

Chaque année, environ 10% des canadiens autonomes (65 ans et +) subissent des blessures mineures (fractures, entorses) conduisant à un déclin fonctionnel (pertes de mobilité et d’autonomie). 65% d’entre eux auront recours aux urgences après leurs blessures et 18% auront un déclin fonctionnel 3 à 6 mois après leurs consultations aux urgences et seront dans un état de fragilité. La fragilité est un état clinique de vulnérabilité correspondant à des pertes importantes des propriétés fonctionnelles du muscle et à l’utilisation accrue des services hospitaliers. Ces résultats confirment la nécessité d’améliorer la gestion de la population âgée suite à une visite aux urgences afin de prévenir cet état via la mise en place un programme d’activité physique adaptée de 12 semaines à domicile (via Jintronix). Et c’est ce que propose ce stage. À notre connaissance, cette étude sera la première à essayer d’implanter une intervention en activité physique adaptée directement en lien avec les services d’urgence et en utilisant des gérontotechnologies. Cette étude permettra de valider la faisabilité, l’efficacité (bénéfice) et d’adapter le système Jintronix vers une population spécifique soit les personnes âgées.

Visual History for Scheduling Behaviour

Actenum produces scheduling software (Actenum DSO) that computes project schedules based on user defined criteria, constraints and desired KPIs (Key Performance Indicators). The software represents schedules using Gantt charts. A user of Actenum DSO enters activities and the constraints between them and then runs an optimization algorithm to produce a schedule. Actenum has found that their customers have challenges understanding what their schedule optimization algorithm is doing. This leads to a lack of trust in the algorithm and a tendency to control much of the schedule manually, often leading to less than ideal schedules. Actenum would like to provide tools that help the users to understand the optimizer. We propose to design a visualization history module for DSO that tracks and visually represents changes made to the schedule. Our history module will enable users to visually understand and compare the effects of changes made in a schedule.

Les communautés féministes et l’organisation du care dans les Manzanas del cuidado

Ce projet analyse les communautés de femmes qui se forment dans les Manzanas del cuidado qui sont des « espaces de concentration de services qui rassemblent et articulent des services, des programmes ou des activités dirigés au care, autant pour celles et ceux qui ont besoin de soin (cuidada.os) que celles et ceux qui le réalisent (cuidadora.es) ». Les MdC appartiennent au Système distrital de care qui rassemble des politiques visant à « prendre soin, assister et soutenir » les cuidada.os et les cuidadore.as. Ces initiatives sont intersectorielles et universelles et visent à poser les bases d’une société de care. Mon étude se fonde sur le concept de « féminisme communautaire » afin de comprendre si et comment les femmes participantes aux manzanas font communauté au sens de Cabnal. Compris comme un concept dynamique, le féminisme communautaire se définit par les relations sociales et spatiales que construisent les femmes qui forment des luttes communes. L’objectif de ce mémoire est donc d’analyserl’organisation du care au sein des communautés de femmes et de comprendre jusqu’à où les femmes étendent l’espace des Manzanas del cuidado pour faire communauté.

Machine Learning developer and technical business interns working within cross-functional teams to develop and commercialize AI-powered solutions in the Public Services sector – AltaML

The project comprises internships in a variety of technical and business roles within our organization and within our GovLab program. Within the organization, roles include associate machine learning developer, business development associate, communications associate and finance associate. Within GovLab specifically, roles include associate machine learning developer, associate business solutions consultant, and project delivery associate. The difference is mainly that in GovLab, there is a focus on public sector problems, whereas in AltaML overall, we work across sectors.
The intern listed (Marley Cheema) on this particular application will work alongside the Government of Alberta on the Smart Document Extraction Agent team. The goal of a Government of Alberta Redaction Assistant would be to empower the government to handle sensitive information and acc eresqsuests with greater efficiency and security.
? Focus: using the SDP application template to create an Automated PII Redaction Tool. The main reason for the project is to automate the identification and masking of Personally Identifiable Information (PII) in high-volume, unstructured public sector documents, such as those related to Freedom of Information and Protection of Privacy (FOIP) requests. This automation replaces the current manual, time-consuming, and error-prone redaction process, directly addressing the growing volume of digital data and the increasing regulatory burden under new privacy legislation.
? Value: The Value of the project is substantial in terms of financial savings, risk mitigation, and operational efficiency. The automation of redaction provides financial benefit by freeing up highly skilled FOIP analysts and records management officers from repetitive, manual tasks, allowing them to focus on complex policy interpretation and disclosure decisions. The solution brings value to citizens by ensuring the GoA is compliant with the Protection of Privacy Act (PPA), drastically reducing the risk of accidental PII disclosure (data breach risk).