Projets novateurs réalisés

Engaging stakeholders to evaluate alternatives in energy system planning through agentbased automated negotiation Year Two

The objective of this project is to improve long-term planning of Alberta’s electricity system infrastructure in collaboration with an industry sponsor, Alberta Electricity System Operator (AESO). The project aims at engaging stakeholders in a regional planning exercise in southern Alberta by a detailed exploration of their perspectives when evaluating energy system alternatives. This was identified by AESO as being a pressing gap in their current practice. The objective will be achieved through the development of an agent-based negotiation model that will act as a virtual laboratory in which computer agents, acting on behalf of stakeholders, will examine scenarios of energy system development and negotiate to find the alternative that satisfies them the most, considering economic, social and environmental aspects. The project will allow AESO to engage in a transformation in decision making and will deliver knowledge that will support them in achieving their mandate by improving their planning process.

AI For Real-Time Embedded Applications: Honeypot Learning and Predicting for OoD Attack Patterns

Today’s automobile is more than a mechanical tool; it contains a myriad of computers, sensors, IoT, and embedded nodes. The embedded system is the heart of a vehicle’s electronic system because of its versatility and flexibility. Furthermore, these systems are becoming increasingly sophisticated and interconnected, both to each other and to the Internet. However, with great convenience also comes great concerns about the security and privacy of our digital assets. Unfortunately, the security implications of this complexity and connectivity have mostly been overlooked, even though ignoring security could have disastrous consequences.

The attacks on embedded systems are evolving and becoming more complex and destructive. In this project, we develop a security incident response system for embedded systems designed to recover from attacks without significant interruption, dynamically selecting response actions while being lightweight in computational power, memory, and energy overhead. Furthermore, this project’s overcoming will help Thales identify the problem and associated cyber threat risks and pave the way for more efficient hardware/software solutions.

Survival of Indigenous Healing Systems in Colonial India

We will study the efforts of traditional physicians to preserve their Indigenous healing system against the oppressive forces of western colonialism. Ayurveda is one of the oldest holistic healing systems in the world and has been practiced in India for more than 2,000 years. However, under the British rule and the spread of colonial medicine Ayurveda was discredited and demoralized. Our hypothesis is that to safeguard their Indigenous knowledges and practices, traditional physicians turned into entrepreneurs and focused on industrializing the production of pharmaceutical products as a path to protecting Ayurvedic medicine. Their success was key to the development of the medical pluralism policy in India and for the World Health Organization recommendation for the integration of traditional medicine into national health care systems to achieve universal health coverage. Their experience can help us reflect on Indigenous healing systems in Canada and what can be done to ensure the survivance (survival + endurance) of traditional knowledges and their use for the benefit of Canadian citizens.

AI to increase statistical power in clinical neuroimaging

Many studies worldwide use neuroimaging to investigate whether there are abnormalities in the structure or function of the brain that underlie mental disorders. The sample sizes in these studies are limited because of the high cost of neuroimaging and difficulties in recruiting large numbers of patients if the disease is rare. This is a problem because clinical researchers need to investigate correlations between imaging metrics and a wide array of demographic and clinical variables, which traditionally requires large sample sizes to obtain good statistical power. This project will thus harness artificial intelligence (AI) to reduce the many variables under consideration in a real-world clinical neuroimaging study of bipolar disorder to just those that are most important. This will boost the statistical power of the study and inform future clinical neuroimaging studies of the best approach to analyze richly-characterized yet small datasets.

Polymer seed film coating mixed with a micronized natural mineral (zeolite) as management tools against pea root rot disease

Root rot disease especially Aphanomyces root rot has led to decrease pea acreage in the prairies due to yield losses of up to 70 percent in wet years. Current fungicides are few and have very limited efficacy on the target pathogen, but may negatively affect other living organisms in the environment. Therefore, there is the need to develop effective tools against root rots in a more effective and natural way. One graduate student will develop a polymer-based seed coating with antifungal properties to protect pea seedlings from root rot disease. The second graduate student will assess the survival of aphanomyces spores in the presence of new developed coatings and other gemination processes. This will be the first step in a collaborative research effort to tap into industry know-how and develop solutions that will benefit producers and the pulse industry.

Engaging stakeholders to evaluate alternatives in energy system planning through agentbased automated negotiation

The objective of this project is to improve long-term planning of Alberta’s electricity system infrastructure in collaboration with an industry sponsor, Alberta Electricity System Operator (AESO). The project aims at engaging stakeholders in a regional planning exercise in southern Alberta by a detailed exploration of their perspectives when evaluating energy system alternatives. This was identified by AESO as being a pressing gap in their current practice. The objective will be achieved through the development of an agent-based negotiation model that will act as a virtual laboratory in which computer agents, acting on behalf of stakeholders, will examine scenarios of energy system development and negotiate to find the alternative that satisfies them the most, considering economic, social and environmental aspects. The project will allow AESO to engage in a transformation in decision making and will deliver knowledge that will support them in achieving their mandate by improving their planning process.

Influence of chronic low back pain on aperture crossing behaviours during goal-directed locomotion

Low back pain (LBP) is one of the most prevalent musculoskeletal conditions globally; it has claimed the number one spot for
global burden, the number of years lived with disability, and health condition requiring the most rehabilitation services. Despite the
commonness of LBP, there is a lack of understanding on the deficits associated with chronic LBP (pain experienced for more than
three months), making diagnoses and treatment challenging. To better inform proper management of chronic LBP, the proposed
study will investigate how chronic LBP influences pathway selection while walking toward a goal. The aims of the study are to 1)
determine how those with chronic LBP differ in their navigational behaviours compared to back-healthy controls (i.e. do they show
protective mechanisms and avoid pathways that would require body rotation?) and 2) measure any altered motor control
behaviours (walking speed, step length, step width, stability). Results from the study will not only address a research gap, but they
can be used to better inform sub-type diagnoses, return to work protocols to avoid re-injury or poor performance, and treatment
practices.

Mutual avoidance behaviors of previously-concussed athletes passing through a doorway

The proposed study will extend the findings of the current literature through the following objectives: 1) to understand individual’s
ability to use visual information to accurately avoid an approaching person; 2) determine the role of environmental objects (i.e.,
doorway) in regulating avoidance behaviours; and 3) determine any concussion-related avoidance behaviour changes. To meet
these objectives, we will conduct an experiment involving previously concussed and non-concussed athletes, who will have to
avoid colliding with each other while walking on a head-on collision course. A doorway will be located along the path of the
walkers and the position of the theoretical collision point will be manipulated so that it occurs before, at, or after the doorway. We
will measure participants’ walking trajectories using kinematic data (via Qualysis camera system) in order to evaluate participants’
adaptations to avoid the collision in terms of speed and path changes.

Petroglyph Complexes of the Upper Indus in Northern Pakistan – Digital Annotation of Visual Cultural Heritage

Complex sites with concentrations of inscriptions and rock drawings (petroglyphs) in the Upper Indus region in northern Pakistan are threatened with inundation in a flood zone of Diamer-Basha dam. These invaluable cultural heritage resources comprising over 30,000 petroglyphs and approximately 4000 inscriptions abraded into the desert varnish on the surfaces of rocks at dozens of complexes are essential to understanding cross-cultural interactions along passageways through the Karakorum, Hindu Kush and western Himalaya mountain chains between South Asia and Central Asia. Irreplaceable records of local inhabitants, merchants, monks, and other itinerant communities require careful attention, all the more so because many sites are endangered not only by flooding, but also by human damage. We are using advances in methods of digital imaging including 3D scanning to point clouds, photogrammetry, and virtual panotours to preserve important evidence of written and visual cultures and to make this data accessible to various scholarly and non-scholarly communities in Canada and Pakistan. The objective of this internship is to apply advances in digital humanities to models of rocks with petroglyphs along the Upper Indus.

Improving the Onboarding Process for the Heardthat App

The use of artificial intelligence (AI) is ushering in a new era of technology for assistive hearing devices. One example is HeardThat, a smartphone app that uses AI to enhance speech comprehension. It helps people carry on conversations more easily in the presence of background noise. This is something that many struggle with even if they have hearing aids. New technology can only provide a solution if the people who need it are able to use it, and be able to get started with it in a self-serve manner. This project will help the company that makes HeardThat achieve those goals by having the intern work with users to identify and test the product changes that are required. It will be an experimental, iterative process between users and the product team.

Exploring the threshold of mental health impact on cognition

The objective of this project is to better understand the impact prevalent mental health challenges have on cognition. For this pilot study, neurophysiological electroencephalography (EEG) will be investigated in three different mental health population groups: those suffering from Generalised Anxiety Disorder (GAD), depression, and Post-Traumatic Stress Disorder (PTSD). Portable EEG will be used to assess attention and information processing in participants. Standard clinical evaluations of GAD, depression and PTSD will also be acquired. Clinical mental health testing will be compared with cognitive EEG data.

The study will focus on two key objectives: 1) determine whether mental health challenges correlate significantly with changes in cognitive EEG; and 2) explore potential threshold levels of cognitive impact by mental health severity. The approach uses advances in signal processing and artificial intelligence/machine learning (AI/ML) to explore the relationship between neurophysiological EEG and clinical mental health evaluation. The integrated work involves a strategic partnership with the not-for-profit Legion Veterans Village (LVV) to examine possible impacts of mental health challenges and cognition in first responders.

Personalization of Web Tasking

A web task is defined as the set of services, sessions, and sequence of interactions that are required to perform a certain user objective. The current Web tasking model does not consider user preferences and context when executing a Web task. The proposed research project aims to improve the experience of Web users through personalization of Web tasks. Personalization integrates the user’s personal context with the task execution plan to serve the user’s interest at best. We will develop a flexible task representation model that can accommodate the user’s context, mechanisms for context solicitation, interpretation and transfer, and efficient context aggregation and handling.