This project investigates whether a user’s entered information in e-commerce sites is fake or real. In order to achieve the goal of understanding and identifying fake users, data are to be collected, managed, and analyzed. In addition to using existing data from the e-commerce partner organization and some third-party data if available, the two major […]

With the development of imaging technology, camera trapping becomes one of the best ways to record the presence and activities of large mammals in a given area. The approach to monitoring the animals can assist people in the community with decision making about preserving biodiversity. In the past, experts analyzed such images manually, which required […]

By combining the information contained in the visual, audio and text content of videos, it is possible to extract complex information about their content. It’s then possible to analyse a query from a search engine to find the video segments that best matches this query. During this project, the intern will be using state-of-the-art deep […]

People who experience mental wellness challenges or mental illness often struggle to obtain or maintain a position in the workplace. Furthermore, lack of employment means individuals lose out on a myriad of mental, emotional, and physiological benefits that are generated through work. This is extremely relevant given the current COVID crisis where personal distancing and […]

Korbit Technologies Inc. is developing an e-learning platform to teach artificial intelligence (AI), data science and coding skills. The student interacts with a virtual, personalized AI tutor, through a web-based chat interface. The main objective of this research project is to investigate how a personalized, data-driven learning experience based on the student’s profile, needs, and […]

In May 2021, the total market capitalization of digital assets such as cryptocurrencies and Non-Fungible Tokens (NFTs) exceeded $2.4 Trillion (USD), tripling in the past 3 years. Yet, digital assets are widely misunderstood even by experienced investors, primarily because the technologies empowering digital assets are new and are rapidly evolving. Hence, scientific approach to understanding […]

With the growing importance of ecommerce, automated warehousing has gained much interest. A crucial component of such system is a robotic arm or a similar device that allows to grasp, pick up and sort items with complex shapes and in cluttered conditions. We will be working on improving such system, so that online delivery can […]

Mineral exploration and natural disaster risk reduction involve reasoning with uncertainty about complex descriptions of parts of the Earth. Such complex reasoning is traditionally carried out by human experts who, through years of training and field experience, develop specific knowledge and are able to take the right decision at the right time. This project will […]

Increased energy consumption across the world for heating and cooling indoor living spaces has been a major contributor to global greenhouse gas production. As per 2015 statistics, buildings account for 76% of global electricity consumption and approx. 35% of that energy consumption is for air conditioning, heating, and ventilation. To combat climate change it is […]

Tribute Kiosk currently operates photo booths that are touch-based in terms of their operation. However, as a result of the Covid-19 pandemic, consumers are hesitant to interact directly with high-contact surfaces. Tribute Kiosk seeks to migrate the functionality of its photo booths to a touchless format while also adding new interactive augmented reality features to […]

In this project, we will explore the new ways to design and implement a Low-Code Software Development platform that is easy to use, requires minimum software knowledge, is business logic oriented, and robust to dependency change. Specifically, we provide functional templates with detailed configuration flexibility to cover the high frequency requirements from the expected business […]

Adversarial perturbation of all the image pixels is computationally intensive and may not be realized in practice. In contrast, an adversarial patch attack where an adversary can choose to perturb a specific subset of pixels in an image, is more practical in fooling a trained image classifier or hiding a person from an object-detection model. […]