Using RTLS and Computer Vision to Extend Worksite Safety

The project aims to extend worksite safety of construction projects at Hydro-Quebec (HQ) using computer vision and a Real-Time Location System (RTLS). The case study is a substation construction project near Montreal. The main safety risks that will be targeted in the case study are related to equipment mobility (struck-by accidents) and not wearing Personal Protection Equipment. The concept of the method is to have a priori information about the types of expected risks in the planning phase, and then to monitor the site using video cameras and the RTLS.

Attribute-Driven Automatic Generation of Realistic Face Textures

When creating a video game, every digital character must be created by professional artists. Their work is very labor intensive because the number of created characters are in the thousands, each of which has multiple visual components that must be created for each one. “Scanning” real actors to create a digital version of themselves can help speed up this process, but each scan must be altered to preserve the actor’s anonymity.

Automating Configuration Management and Deployment in Large-scale Data Centers Augmented with Edge Data Centers - Year two

Data centers are now growing and expanding massively. They are large scale and heterogeneous. In addition, they rely more and more on emerging technologies such as Software Defined Networking (SDN) and Network Functions Virtualization (NFV) with “network softwarization” as their key feature. Moreover, they are now being augmented with edge data centers rooted in concepts such as cloudlets, ETSI Mobile Edge Computing (MEC), and fog computing. Such data centers bring a host of new challenges when it comes to the automation of configuration management and deployment.

Classifying Innovation Management Forms Using Ontology Reasoning

In this project, the goal is first to design a domain ontology that models the innovation management forms semantically. At this step, the ontology contains domain-specific background knowledge, which is expressed using terminological statements. Then every completed form and the value of its fields are asserted as instances of different concepts of the ontology. Afterwards, an ontology reasoning algorithm is deployed to classify every completed form into various categories defined in the ontology.

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

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.

Automating Configuration and Performance Management of Data Centers - Year two

Data centers (DCs) in network softwarization and 5G eras are significantly different from those operated nowadays by public cloud providers. They are massively distributed, closer to end-users, heterogeneous (e.g., multi-access edge, central office as a data center, etc.) and rely on much more complex technologies (e.g., Network Functions Virtualization [NFV] and Software-Defined Networking [SDN]). This makes their Operation and Management (O&M) much more challenging. Much more intelligence is required for automating the various tasks.

Just-In-Time Scaling of Cloud Based Video Games using Machine Learning

Ubisoft’s cloud-based video game ecosystems experience the workload up to 5+ millions players in a typical week. Workloads on game servers are of different scales, ranging from tens of clients per game server to thousands of clients for traditional workloads. To guarantee game player user experience, a pool of servers is launched to react to demands but servers are idles in most of the time. Scaling down servers is even more complex because of the persistent connections to maintain the states and records of players and games.

Fostering Indigenous Small-scale fisheries for Health, Economy and food Security in Cree communities of northern Quebec (FISHES)

Northern fisheries are facing major changes and reducing the negative impacts is crucial for communities tied to the fisheries for their food security and culture. The identification of regions important for subsistence, commercial and recreational harvesting and whether they comprise genetically distinct groups of populations is a key requirement for adaptive co?management of harvest. Our team is comprised of researchers and Indigenous collaborators that combine the expertise for implementing knowledge at the interface between genomics and fisheries management.

Detection and Prediction of Network Vulnerabilities with Machine Learning Models and Algorithms

The project investigates the development of artificial intelligence models and algorithms to analyze telecommunication networks, looking for signs that indicate the presence, or imminent arrival, of faults and outages on the network.
The project will use as its main input data (network topology and network health metrics) collected by EXFO in real-time and accumulated over extensive periods of time.

Improving the Reliability of AI Systems from a Software Engineering Perspective

Artificial Intelligence techniques have been widely applied to solve real-world challenges, from autonomous driving cars, to detecting diseases. With the popularity of 5G wireless network, more and more AI systems are being developed to provide convenient services to everyone. It is important to ensure the reliability and quality of AI systems from every phase in software development cycle, i.e., development, integration, deployment and monitoring. In this collaboration with Ericsson GAIA, we will propose techniques to systematically improve the quality and reliability of AI systems.