AI-driven detection of anomalous supplier profiles at web scale

Information gathered from internet sources has high variance and different types of noise. This causes out-of-distribution problems with downstream ML modules such as category classification and keyword extraction. The extremely large size of internet-scale datasets requires a solution that is efficient and scalable. The objective of this project is to develop a start-of-the-art anomaly detection […]

Read More
Evolutionary Housing Strategies for Canadian Cities

This project examines the feasibility of low-cost evolutionary housing strategies to accommodate changing uses in Canada. It is a partnership between the University of Waterloo school of Architecture and architect John van Nostrand who has developed numerous prototypes for evolutionary housing in Canada and internationally. The research will begin with an analysis of existing prototypes […]

Read More
Production Line Packaging Sensor Optimization

Automated production lines use in food, beverage and pharmaceutical manufacture can subject the product being produced and especially the product packaging to high levels of mechanical stress. These stresses can take many forms, be it impact, side pressure, vertical pressure, etc. Plant quality assurance engineers are constantly making adjustments to their automated systems to reduce […]

Read More
Participatory Cities Every One, Every Day: Toronto

This proposal details an approach for evaluating a planned project led by SII called Participatory Cities: a new inclusive, system-based approach to stimulating and supporting dense networks of practical ‘participation culture’ in cities around the world. With proof of concept developed and tested in London, UK, by the Participatory City Foundation, the model will now […]

Read More
Synthetic biology constructions toward bacteria-mediated cancer therapy

Development of selective drug delivery agents that target tumor cells with minimal toxicity to normal tissues is a major challenge in cancer therapy. Non-toxic bacteria can be used to target solid tumors because, within a patient’s body, they can only be active at a tumor site (where oxygen levels are pathologically low). Prior attempts at […]

Read More
Coveo : Algorithmes de recommandation

Ce projet s’inscrit dans la grande famille des projets de systèmes de recommandation, où un algorithme doit recommander aux utilisateurs des produits ou des documents qui seraient intéressants pour eux, basé sur ce que nous connaissons de l’utilisateur et sur sa session de recherche actuelle. Coveo a déjà des modèles de recommandation en place, dans […]

Read More
One-Shot Learning Based 3D Object Picking

Automation of processes is becoming more popular within logistics and material handling industries. As the amount of transferred objects grows there is a continuously increasing need for high efficiency, reduce cost, and of course reliability. With this project, we are utilizing the latest machine learning technology to improve the automation rate to a new level. […]

Read More
Development of a low-cost tool for skin cancer screening

The proposed research project is intended to develop an educational tool for the general public to be able to perform self-screening of their skin lesions. For this, a melanoma-detection mobile application will be developed to analyze lesion images acquired using a low-cost dermoscope attached to a smartphone. This product helps public or students to learn […]

Read More
Smart empathetic speaker based on real-time EEG-based music therapy

During COVID-19 outbreak, many people are suffering the negative emotions, causing anxiety, fear, and depression in daily life. To improve the individuals’ mental health, musical therapy will be employed due to its high value of treatment in the mental health field. In our project, a smart empathetic speaker based on real-time emotion recognition system will […]

Read More
Barcode Image Enhancement Using Deep Learning

The use of barcodes to store alphanumeric information has spread from supermarkets to department stores, the health industry and even on the back of our drivers’ license. Recent years have also seen demand to increase the density of information encoded in barcodes. A Drivers’ License has its personal data encoded in the barcode on the […]

Read More
Regeneration dynamics of white and red pine forests following surface fire: developing an ecosystem-based sustainable forest management strategy (PINEFIRE).

The cover and extent of pure and mixed pine forests in northeastern North America has significantly declined across their historic range, primarily as a result of changes in fire regime, unsustainable forest management practices, and increased tree mortality due to introduced pathogens. To address the decline of these ecologically, socially, and economically important ecosystems we […]

Read More