Optimizing High Performance Distributed Computing Framework in Heterogeneous Environment System at Lakehead University

Universities in Canada and around the world are adopting the DCP (Distributed Compute Protocol) as a method of obtaining free, abundant compute resources for research and innovation. In doing so, IT departments are deploying DCP workers on fleets of desktop computers in departments, libraries and administration offices on campuses. All of these computers, once connected to the distributed computer, consume network bandwidth, switching, and power resources. DCP is unique. Other utilities such as networks, cloud compute, and/or other mainframe systems have existed for years.

Optimizing return on investment using artificial intelligence: A recommendation system-based solution

The main goal of this project is to develop an artificial intelligence based approach for recommendation to improve Videotron marketing solutions. We aim to focus on improving Vidéotron return on investment (ROI), engaging more users and retaining subscribers using advanced artificial intelligence techniques. The proposed system will be based on a collaborative filtering technique that involves state of the art deep learning and reinforcement learning techniques.

Digital Twin for Proactive Maintenance of Data Centre

The data centre management is paramount to ensure the uptime operation. This research aims to develop a digital twin platform using the industrial Internet of Things, edge and cloud computing, and artificial intelligence for predictive maintenance of data centre. The facilitate maintenance scheduling and data centre energy consumption could be further optimized through the digital twin platform, which enables the prediction with a virtual representation of the physical asset or a process. The interns will have the chance to work with industry partner in a multi-disciplinary team.

Deep Learning for Automatic Melody Harmonization

Beginner music composers often face difficulty in harmonizing a melodic idea. Particularly, if they lack music theoretical knowledge. It is well-understood that chord successions follow patterns. With some limitations, artificial intelligence algorithms can capture those patterns. A melody “harmonizer” model proposes harmonizations for the user’s melodies. The suggestions are often based on learned patterns from existing musical compositions, for example, the chorales by J. S. Bach. A model may learn patterns found in Bach’s compositions, applying them in new music.

Design and Development of a Novel Web Application for Enhanced User Experience of Digital Books

The research project collaboration between APCI and WIMTACH will involve the identification of best technology methods and processes that will enable new modes of publishing to bridge the gap between the traditional paper and online methods. The focus will be on the efficiency of delivery so that cost models are minimized, opening new opportunities for authors, including those from disadvantaged communities, to publish novel material. The student intern will learn first hand experience on these new technologies and its applications to the current APCI platform.

Developing new drawing techniques to create believable Black hair in 2D Animation, and its role in increasing representation of African heritage in mainstream kids media.

Through iterative design and experimentation, this research aims to overcome the technical challenge of creating an authentic and respectful representation of African American hairstyles in mainstream 2D Animation.

AI-Enabled Satellite Communication Networks

Due to the fast mobility of LEO satellites, ground users need to switch between LEO satellites frequently to keep the connection with the satellite network. The process of switching between satellites is called the handover process. Every handover process is associated with signalling overhead, processing delays, and data packet losses. The optimization of the handover process is crucial for an efficient and resilient satellite network. In this regard, intelligent resource allocation can reduce the handover rate while maximizing the network utility and ensuring the satisfaction of users.

Parallel multibody solver coupling algorithms

This project concerns the efficient simulation of constrained-multi body systems with applications in training simulations. For instance, a crane on a construction site can be modeled and simulated as a collection of rigid bodies connected by rotational joints. Simulation of contact and friction is similar but a challenge because the force is bounded (i.e., forces are not allowed to act like glue and can only push objects apart). When there are large numbers of bodies in a simulation, with many frictional contacts, these systems can be challenging to

Assessing Regenerative Energy Technologies for Electric Vehicles

Electric vehicle (EV) is the future of sustainable transportation to phase out the reliance on petroleum fuels. Despite the multibillion-dollar market potential, wide deployment of EV is challenging due to limited energy storage. Regenerative energy generation can be implemented to compensate for the energy consumption in EV to provide the much-needed extra mileage. Apart from regenerative braking, other energy harvesting options such as solar panels, wind turbines, and vibration/shock energy harvesting have yet to be implemented at larger

Technological advancements for data collection in animal research

The proposed research project is to program artificial intelligence, as produced by technology company EAIGLE, to monitor animals’ behaviour at the Toronto Zoo. The program will be capable of distinguishing where animals are in their enclosures, between individual animals, and which behaviours they are producing under different contexts. This technology will allow zoos, conservation areas, and researchers to monitor how animals interact with their enclosures and throughout the day, allowing for improved habitats and improved data collection for future experiments. Dr.