Innovative Projects Realized

RECHERCHE ET DÉVELOPPEMENT DE SOLUTIONS INNOVANTES POUR LE CONTRÔLE NON-DESTRUCTIF DE PLANCHER RÉSERVOIRS PÉTROCHIMIQUES

Nucleom est une entreprise canadienne proposant des services de contrôle non destructif (CND) pour diverses applications telles que l’inspection de réacteurs nucléaires ou de pipelines. Ce projet de recherche fortement appliquée permettra un transfert de connaissance entre le laboratoire d’accueil et le partenaire industriel. Le projet principal aura pour objectif d’évaluer les possibilités d’inspection ultrasonore du fond d’un réservoir similaire à ceux généralement utilisés pour le stockage des liquides dans l’industrie pétrochimique. Actuellement, avec les outils de CND disponibles il est nécessaire de vider entièrement le contenant afin d’effectuer une inspection par perte de flux magnétique depuis l’intérieur du réservoir. Cette méthode couteuse en temps et en ressources permet de détecter les détériorations généralement introduites par la corrosion. Dans ce projet, plusieurs méthodes innovantes basées sur les ondes guidées seront comparées dans le but de développer un dispositif permettant d’inspecter le fond des réservoirs depuis la surface extérieure.

Couplage de la dénitrification autotrophe sur soufre aux systèmes de traitement biologiquedes eaux usées domestiques applicables au secteur de l’assainissement décentralisé

Au Canada, les petites installations d’assainissement autonome (non-raccordées aux réseaux

d’égout) contribuent à produire 20% de la quantité totale des eaux usées. Ces petites installations de

traitement des eaux résiduaires sont souvent caractérisées par une difficulté à atteindre les normes

de rejets, lesquelles sont de plus en plus sévères. La dénitrification autotrophe utilisant le soufre

élémentaire constitue une nouvelle biotechnologie efficace pour réduire les teneurs en nitrate dans

les effluents avant leur rejet dans le milieu récepteur. Le présent projet, d’une durée de trois ans et

comprenant quatre stages en entreprise, vise donc à évaluer, d’abord en laboratoire puis à l’échelle

pilote, le potentiel du couplage de la dénitrification autotrophe sur soufre élémentaire avec deux

procédés de traitement biologique de la compagnie Premier Tech Ltée, soient le procédé de

biofiltration Ecoflo® et le système Ecoprocess MBRTM, pour l’élimination des nutriments,

principalement l’azote, présents dans les eaux de petites et moyennes collectivités.

Adapting Human Performance Techniques, Illusion Aesthetics, and Specialized Apparatus from the World of Stage Conjuring to Contemporary Circus Disciplines

The vast majority of performance techniques, illusion aesthetics, and specialized apparatuses used by stage conjurors are still unknown and remain unexplored by the circus world. The tacit knowledge that magicians exchange amongst themselves is rarely transferred to members outside of their subculture, which leads to creative stagnation in their communities and beyond. The purpose of this project is to create an intensive and sustained collaboration between North American illusion experts and elite circus artists to produce new physical vocabulary for new equipment. The prototypes produced will be disciplinary hybrids. The specific magic/circus combinations proposed for this project are: 1) manipulation techniques for an optical illusion wheel apparatus, 2) movement vocabulary for a color-changing aerial rope apparatus, and 3) movement vocabulary for a color-changing silks apparatus. Cirque du Soleil, as industrial partner, and graduates of Montreal’s National Circus School will be the first to use and diffuse the physical vocabulary and special apparatuses developed. The collaboration of magic and circus specialists will be facilitated through the organization of an international academic and industry conference held in Montreal in the summer 2020.

L’évolution de la virulence des punaises ternes en réponse à la sélection exercée par les méthodes de lutte

En empêchant le développement normal des fruits, les punaises ternes occasionnent des pertes économiques majeures pour les agriculteurs de fraises. Ils utilisent donc des méthodes de luttes pour réduire la densité de ces insectes qui changent les paramètres déterminant la survie des individus. Ce projet permettra d’examiner comment ces méthodes de lutte occasionnent un changement dans le comportement des punaises et comment cet effet se répercute sur les dommages qu’elles occasionnent et leur susceptibilité aux méthodes de lutte. Ces données permettront d’optimiser l’utilisation des méthodes de lutte alternatives aux insecticides pour minimiser les pertes économiques tout en assurant un plan de gestion efficace à long terme.

Person Re-identification in Cross-Domain Adaptive Network – Year two

Video analytics is an active fields of research, where state-of-the-art systems rely on a variety of computer vision and machine learning techniques for accurate modeling and recognition from large-scale video datasets. Person re-identification is a key problem found in numerous application areas, e.g., video surveillance, summarization, and sports analysis, and seeks to match people across non-overlapping views in a multi-camera system. However, this remains a challenging problem because the appearance of individuals varies considerably across cameras viewpoints (pose, illumination, etc.), and due to the non-rigid structure of individuals. This project will focus on developing accurate visual recognition models that allow for person re-identification in sports video analytics application of interest for SPORTLOGiQ Inc., leading to person tracking, activity recognition and group behavior understanding over a distributed network of cameras. Designing accurate recognition systems for these applications typically gives rise to several challenges because it involves learning complex models using large weakly-annotated data sets that incorporate domain shifts, subtle noise, variations and uncertainties embedded in real-world signals.TO BE CONT’D

Person Re-identification in Cross-Domain Adaptive Network

Video analytics is an active fields of research, where state-of-the-art systems rely on a variety of computer vision and machine learning techniques for accurate modeling and recognition from large-scale video datasets. Person re-identification is a key problem found in numerous application areas, e.g., video surveillance, summarization, and sports analysis, and seeks to match people across non-overlapping views in a multi-camera system. However, this remains a challenging problem because the appearance of individuals varies considerably across cameras viewpoints (pose, illumination, etc.), and due to the non-rigid structure of individuals. This project will focus on developing accurate visual recognition models that allow for person re-identification in sports video analytics application of interest for SPORTLOGiQ Inc., leading to person tracking, activity recognition and group behavior understanding over a distributed network of cameras. Designing accurate recognition systems for these applications typically gives rise to several challenges because it involves learning complex models using large weakly-annotated data sets that incorporate domain shifts, subtle noise, variations and uncertainties embedded in real-world signals.TO BE CONT’D

Feasibility of clustering road user trajectories in complex scenes for automatic identification of common traffic activities

Proactive road safety analysis allows for the pre-emptive diagnosis of road safety issues without direct observation of traffic accidents by observing accident precursor events instead (i.e. “traffic conflicts”). This approach to road safety diagnosis is made possible with the collection and analysis of large quantities of high-resolution road user trajectory data acquired from video data automatically. However, several practical challenges with implementing this automation remain, including the automatic recognition of activity types in congested and complex scenes, particularly if the trajectory data is noisy. This activity recognition provides contextual information when observing traffic conflicts necessary for understanding specific causes of road safety issues and provides a better understanding of potential collision mechanisms.
Although this task can be performed manually, automation is sought for large-scale application of this technology as the manual task of performing activity recognition becomes cost-prohibitive. This project aims to achieve automated traffic activity recognition with a combination of trajectory clustering techniques and lane usage-learning heuristics from previously available road user classification (itself obtained from image recognition). Feasibility of this approach will be studied, including a sensitivity analysis of trajectory clustering in highly complex urban environments (e.g. intersections) and with lane type identification (road, sidewalk, bike path, etc.).

Detection of Mental Health Conditions from Textual Device Communication – Year two

Research into child safety applications using Artificial Intelligence (AI) methods is a new area of investigation. SafeToNet is continuing to develop AI monitoring tools together with a team of researchers at the University of Ottawa. These tools, when used over time, will take advantage of outgoing text-based communications from devices to detect the early onset and progression of developmental and mental health issues in youth. The addition of a postdoctoral researcher in Natural Language Processing (NLP) will allow the project to run quality assessments of the text-based data sets that we are developing for the purposes of assessing these behavioural and mental health concerns in youth. This will allow SafeToNet to develop new deep-learning tools and assess their performance against current research in NLP. The technology will be used in real time detection of safety and childhood development issues, with the technology being immediately deployed in the monitoring tool.

Detection of Mental Health Conditions from Textual Device Communication

Research into child safety applications using Artificial Intelligence (AI) methods is a new area of investigation. SafeToNet is continuing to develop AI monitoring tools together with a team of researchers at the University of Ottawa. These tools, when used over time, will take advantage of outgoing text-based communications from devices to detect the early onset and progression of developmental and mental health issues in youth. The addition of a postdoctoral researcher in Natural Language Processing (NLP) will allow the project to run quality assessments of the text-based data sets that we are developing for the purposes of assessing these behavioural and mental health concerns in youth. This will allow SafeToNet to develop new deep-learning tools and assess their performance against current research in NLP. The technology will be used in real time detection of safety and childhood development issues, with the technology being immediately deployed in the monitoring tool.

Towards Understanding the Behaviour of FRP-Reinforced Structures under Changing Climate Trends – Year two

Fibre reinforced polymers (FRP) have become an attractive solution to make infrastructure corrosion- and disaster-resistant. Cities like Toronto have numerous structures and bridges already retrofitted with FRP and many more underway. However, FRPs effectiveness and and durability is sensitive to extreme thermal conditions, which can cause significant mechanical and durability issues. Climate change, one of the biggest challenges facing the planet today, is causing more frequent and severe weather events, such as rising service temperatures, heat waves and extreme temperature variation cycles, endangering the current infrastructure. Thus, the long-term impact of these unavoidable new temperature trends on FRP-reinforced structures needs to be better understood and evaluated. To that effect, in the proposed study, numerous FRP-reinforced specimens will be constructed and tested to investigate the effects of the rising temperatures and temperature cycles on bond performance, strength and ductility of FRP-reinforced members. The finding will not only help the industry partners to improve the quality of their FRP products to be durable against heat waves and temperature swings but will also provide the necessary data required to update Canada’s FRP codes to be more Climate-Resilient.

Towards Understanding the Behaviour of FRP-Reinforced Structures under Changing Climate Trends

Fibre reinforced polymers (FRP) have become an attractive solution to make infrastructure corrosion- and disaster-resistant. Cities like Toronto have numerous structures and bridges already retrofitted with FRP and many more underway. However, FRPs effectiveness and and durability is sensitive to extreme thermal conditions, which can cause significant mechanical and durability issues. Climate change, one of the biggest challenges facing the planet today, is causing more frequent and severe weather events, such as rising service temperatures, heat waves and extreme temperature variation cycles, endangering the current infrastructure. Thus, the long-term impact of these unavoidable new temperature trends on FRP-reinforced structures needs to be better understood and evaluated. To that effect, in the proposed study, numerous FRP-reinforced specimens will be constructed and tested to investigate the effects of the rising temperatures and temperature cycles on bond performance, strength and ductility of FRP-reinforced members. The finding will not only help the industry partners to improve the quality of their FRP products to be durable against heat waves and temperature swings but will also provide the necessary data required to update Canada’s FRP codes to be more Climate-Resilient.

Enzymatic nano-immobilisation facilitated by 2D materials for antifouling coatings – Year two

Enzyme immobilisation is crucial for preserving the enzyme activity while enabling the enzymes to be recovered and reused for multiple applications in biocatalysis. However, immobilisation can change the structure and functionality of enzymes. Therefore, immobilisation of enzymes needs to be carefully investigated and controlled at fundamental levels. The emerging two-dimensional (2D) materials, such as graphene and transition metal dichalcogenides exhibit unique physico-chemical properties which make them well suited for enzyme immobilisation. Considering this, our research will focus on the use of 2D nanomaterials as enzyme immobilisation materials to modify and control the stability, selectivity and activity of various enzymes. Through this project, we will design novel green routes for the production of biocompatible 2D materials to be used as immobilisation supports for various types of enzymes. This will assist in understanding the enzyme nano-immobilisation mechanism and will open new applications for the functionalized 2D materials in enzymatic nanobiotechnology. Specific enzyme-immobilised 2D materials developed with the partner company of Biosa Technologies, will possess bactericidal properties which will be applied for producing antifouling coatings for food preservation. This project will provide Biosa significant scientific and technological achievement and commercial success in improving enzymatic technology and enhancing antimicrobial coatings market in Canada.