Innovative Projects Realized

National Smart Vehicle Demonstration Project

Autonomous vehicle technologies and associated “smart” infrastructures are innovative technologies that can provide many benefits to transportation such as reducing traffic congestion and collisions, improving ridership experience by operating in a more on-demand application providing real-time updates to the rider, and reducing GHG emissions through integration of electric propulsion and route optimization technologies. This project will develop the technological certification standards and specification of the National Smart Vehicle Demonstration projects, in partnership with CUTRIC, which aims to test smart vehicles and smart infrastructure technologies within five to seven municipal jurisdictions across Canada in a closed or restricted laneway using low-speed shuttles. Additionally, this project aims to integrate some form of autonomous vehicle into First Nations communities across Canada where a lack of transportation services often leads to safety concerns for youth and women in particular. TO BE CONT’D

Evaluation of strategies in decreasing energy consumption at Irving Paper byfractionation

The thermo mechanical pulping (TMP) process uses large amounts of electrical Energy to

turn wood chips into separated pulp fibers suitable for papermaking Hecent advances being

developed by supplier-mill partnerships employ fiber fractionation processes between refining stages to achieve significant reductions in total energy consumption During this

internship these new processes will be investigated to understand how the discrete process

stages impact the resultant fiber fractions and overall pulp properties, and its implication to

[he operation at irving Paper These will be done by conducting bench and pilot-scale

fractionation and refining equipment. Pulp and fiber properties will be determined, thus

identifying the process configuration with the best potential for decreasing the energy

consumption while maintaining pulp properties

Modelling partial mortality wildfire dynamics in boreal and mountain landscapes

An emerging strategy for managing natural resources such as Canada’s forests more sustainably and responsibly is to use knowledge of how Mother Nature has done it to help guide our hand. This so-called ‘ecosystem-based” approach has gained favour with provincial and federal governments, as well as national and international certification agencies. One of the foundations of such an approach is a fundamental understanding of how natural forest ecosystems have worked for millennia over time and space: How has Mother Nature provided the rich array of goods and services such as timber, clean water, recreation, fishing, hunting, and critical species habitat that we enjoy today? Unfortunately, it is not possible to define historic reference conditions using actual data. The next best solution is to develop simulation models that can capture what we understand of landscape dynamics over time and space to re-create such reference points. TO BE CONT’D

Influence of base rigidity on the load-carrying capacity of loadbearing masonry walls

Design of loadbearing, out-of-plane (OOP), tall masonry walls tends to have stringent limits related to their buckling stability and the scarcity of research on their structural reliability. This currently puts the masonry industry at a disadvantage as a construction alternative compared to other structural options. The proposed research investigates the strength of tall masonry walls against lateral loads, considering the influence of base rigidity. Current design practice does not recognize the influence of actual support conditions in estimating the load capacity of slender masonry walls. Neglecting the rigidity of common foundation systems leads to an underestimation in load capacity that can be uneconomical. This indicate the need to determine the structural response of walls with realistic boundary conditions at the base, in terms of strength against lateral loads, and to develop numerical models that allow for the development of new design methods that account for base rigidity.

Machine Learning for the Telecommunication Industry – Year two

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. In the proposed project, through the exploration of concrete telecommunication industry use cases, the Ericsson researchers in Canada and their academic partners will evolve the start-of-the-art in machine learning and artificial intelligence for the analysis of telecommunication data and operation of telecommunication networks. This will allow Ericsson to develop new products and services, which will allow Canadian network operators to offer improved communication services to Canadian customers. The proposed project will lead to new methodologies for processing complex communication network data, addressing significant imbalances in data sets, and performing anomaly detection.

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. In the proposed project, through the exploration of concrete telecommunication industry use cases, the postdoctoral researcher will collaborate with the Ericsson researchers in Canada and the academic supervisor to evolve the start-of-the-art in machine learning and artificial intelligence for the analysis of telecommunication data and operation of telecommunication networks. This will allow Ericsson to develop new products and services, which will allow Canadian network operators to offer improved communication services to Canadian customers. TO BE CONT’D

Improving the use of evidence-informed health policy for individuals with brain-based disabilities – Year two

There has been an increasing focus in the health and disabilities research field on knowledge translation – that is, to ensure that emerging research can be effectively integrated into health and social service policies and into service delivery. Studies on the development of policy and services demonstrate that many factors apart from academic research evidence play significant roles in creating services and policies. In fact, evidence and/or best practices that some might argue is irrefutable, may never make its way into policy or practice. This project will create retrospective process maps of multiple pilot project initiatives of the Centre for Innovation in Autism and Intellectual Disabilities that aimed to change public sector health and social services and policy related to individuals with autism spectrum disorders and intellectual disabilities. TO BE CONT’D

Improving the use of evidence-informed health policy for individuals with brain-based disabilities

There has been an increasing focus in the health and disabilities research field on knowledge translation – that is, to ensure that emerging research can be effectively integrated into health and social service policies and into service delivery. Studies on the development of policy and services demonstrate that many factors apart from academic research evidence play significant roles in creating services and policies. In fact, evidence and/or best practices that some might argue is irrefutable, may never make its way into policy or practice. This project will create retrospective process maps of multiple pilot project initiatives of the Centre for Innovation in Autism and Intellectual Disabilities that aimed to change public sector health and social services and policy related to individuals with autism spectrum disorders and intellectual disabilities. TO BE CONT’D

Legal Question Answering with Machine Comprehension

ROSS Intelligence enables legal professionals to find analyze legal issues and find hidden information and cuts down on research time by using artificial intelligence specialized in legal research. Recent advances in neural networks applied to
natural language processing have brought results that are close to human performance in some tasks. However, this approach is still nascent in legal research and it has been identified as potentially fruitful. By reviewing and adding to the
most recent developments in natural language processing and machine learning available in academic literature, this project aims to increase the reliability and capability of this artificial intelligence.

Email Mining, Modeling, and Visualization

For this project, a data mining, visualization, and modeling technique will be developed and tested specifically for emails, using publicly available datasets. The mining will consist of gathering email and other potentially related datasets and cleaning those datasets. Cleaning will consist of removing duplicate or unnecessary information, as well as labeling data with basic information in order to ease training in the later steps. Next that data will be visualized in some form (graphs, charts, etc.) so that it may be more easily understood and a training model can be development. Lastly the data will be analyzed in order to obtain some statistically model which will provide new insight on the information, such as its general topics, the flows of conversations, and sentiment analysis; each using novel and modern algorithms and processes.

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. This project will develop machine learning and data analytics methods based on natural language processing to automatically and accurately match identify influencers for brands.

Développement d’un indice d’intégrité biotique pour le bassin versant de la rivière Saint-Charles

L’état de santé des rivières qui se déversent dans le lac Saint-Charles, est peu connu. Grâce à ce projet de recherche, l’Association pour la Protection du Lac Saint-Charles et des Marais-du-Nord (l’APEL), en lien avec l’Université Laval, développera un indice qui permettra de classer l’état de santé des rivièrescomme étant excellent, bon, assez bon, pauvre ou très pauvre. Pour ce faire, les espèces de poissons présentes ou absentes dans les rivières serviront d’indicateur pour coter les différents paramètres qui servent à calculer l’indice qui se nomme un indice d’intégrité biotique. Cet indice, calculé pour la première fois à l’été 2017, permettra à l’APEL de savoir si certaines rivières ne sont pas en santé. Ainsi, cette information pourra être transmise aux différents acteurs ayant un rôle à jouer dans la protection des cours d’eau. TO BE CONT’D