The ability to extract 3D models from 2D images, a process called Inverse Graphics, finds applications in the many applications of Virtual Reality. For the development of urban digital twins, we focus our research on Inverse Graphics of buildings, which would greatly simplify the reconstruction of entire city blocks in a virtual environment. We plan to investigate a Generative Adversarial Network (GAN) and Differentiable Renderer based approach. We first plan to train a building image GAN which would allow for the creation of a synthetic self-supervised dataset.
One of the primary challenges of creating robots that can complete useful real-world tasks is providing the robotwith the ability to navigate through its environment while avoiding collisions with objects. In order to do this,robotics relies on the use of collision checkers to determine which actions will result in a collision. The time takenfor a robot to come up with a collision-free path depends on how fast it can check for collisions and how often ithas to query the collision checker.
A multi-party live video communication, such as live tutorials and fitness classes, are an emerging application which involves a large number of users from different places with heterogeneous network conditions like 3G/4G/5G or Wi-Fi networks. Video Content/Service providers usually deploy their Content Delivery Networks (CDNs) over the public Internet to avoid expenses of dedicated connectivity. Thus, they often seek solutions to provide seamless services over the changing conditions of Internet that can introduce packet error, packet loss, or out-of-order packets.
COVID, remote work, remote learning and the accelerated adoption of technology globally has shifted the ways of how we live, learn, and our future lifestyles going forward. The 90% of society face challenges of how best to simplify their navigation and access to knowledge – those who may not have high value networks, and the means and resources to identify and access ways to upskill, reskill, or retrain to enter or re-enter the future workforce.
In this project, we are going to design blockchain networks and design an interaction between IoT devices. In this way, we can update the location of tokenized asset which is our food product in this project. Blockchain network can provide traceability and transparency, so we decided to use blockchain because of these features. The partner organization goal is to provide the seafood customers with a suitable source by which they can check whether the product is mislabeled.
This project aims to document the process that was undertaken to establish the first Indigenous Protected and Conserved Area (IPCA) Innovation Centre. This documentation will serve as a roadmap and assist in the establishment of future IPCA innovation centres across Canada and internationally. The establishment of IPCAs are essential if Canada hopes to protect biodiversity and ultimately achieve Target 1.
Today, there is an abundance of stakeholder engagement and data visualization platforms. However, they are overwhelming to use, and the data is not easy to interpret. To explore how new methods of visual design and data visualization, Veras Technologies Inc. will work with intern Divine Okonkwo to research, design, and test a comprehensive design language, adaptable visual components, and a interactive data visualization system. The intern will test the data visualization system with internally company data and publicly available population statistics.
Credit card payments are one of the most common transaction methods in our daily life, such as online shopping, e-commerce, and mobile payment. However, with the extensive usage of credit cards, numerous credit card fraud transactions occur every year and cause a huge economic loss. In order to improve the detection performance, this project proposes a transformer-based model to conduct fraud detection. The proposed transformer-based model omits convolutional or recurrent operations and relies solely on attention mechanisms to extract dependencies in the sequence dataset.
As the underlying networks transition into 5G and 6G infrastructure, the optimal task performance across different WIoT devices with different energy consumption and computing power require coordination at both the software and hardware levels to maximize accessibility and minimize latency to support emerging applications. The proposed research will explore the various parameter space to determine how federated learning should be optimally executed in real-time, in the edge and cloud, to maximize user experience supported by upcoming 6G networks.
Using machine learning, this project will seek to enhance customers’ online shopping experience by intelligently selecting product photos based on the user’s information and knowledge about the product. Computer vision will be used to label images and gain information automatically.
