Asset Vision: Extracting Metadata from Engineering Drawing Images

Organizations have traditionally struggled with asset management as a result of not having a complete picture of the location and state of their physical assets. This is largely because critical information such as how an asset was built and should operate is locked in highly technical diagrams and unstructured documents. Asset Vision is a new […]

Read More
Persuasive technology – Guidance to Virtual Relationship Manager (VRM) for effective sales effort basis voice data mining

Voice of the Customer (VoC) is how companies hear and listen to customer feedback about their brand, products, and services. Voice of the Customer solutions convert gathered feedback into valuable data and insights at scale. Data-driven VoC analytics programs are proven to increase customer lifecycle value and lower customer churn. Companies in various industries including […]

Read More
SOTI Snap Analytics

Currently, data analytics services are not only expensive, but also often require days of delay for the data analytics report to be generated. The project focuses on making use of a user’s voice query as an input to create a data analytics response by aggregating data from a database. The successful implementation of the project […]

Read More
Diverging from the GPUs: The case for alternative architectures for training ML algorithms

Machine learning has ushered many breakthroughs in areas such as computer vision, natural language processing, speech recognition, and recommendation systems. The models used in these applications contain many parameters that need to be learned and training often requires massive amounts of computation. As such in recent years graphics processor units (GPUs) have seen wide adoption […]

Read More
Federated Learning for Language Models

The existing approach to building Machine Learning models includes gathering all the data from customers in one place and then running the training procedure using it. However, there are no guarantees personal data won’t be leaked by the one training the model. So, the customers face a difficult decision of either allowing companies to gather […]

Read More
Hydrologic regulating services of non-woody grassed and meadow urban landscapes

Due to urbanization in the GTA, many green areas are replaced by impervious infrastructure, preventing runoff infiltration and increasing flood risks. The Meadoway project proposed by the Toronto and Region Conservation Authority (TRCA) aims to restore meadow habitats with native plants along a hydro-corridor over 16 km across Scarborough, which can potentially improve the runoff […]

Read More
Personalized relevance content recommendation

PC Optimum was originally built as a rewards platform. As we are moving in the path to engage more meaningfully with our customers by way of personalized & interactive experiences (content), we are building a targeting engine as a solution to surface personalized content tailored for each individual customer. The problem we are solving then […]

Read More
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
Automatic Model Risk Management

Regulatory bodies, such as the Office of the Superintendent of Financial Institutions (OSFI) require that financial institutions properly assess and manage risk. Regulatory bodies aim to ensure the stability of financial markets, and the economy at large, and they do so by imposing guidelines on a firm’s risk management practices. Risk management models in general, […]

Read More
Modeling Ekona’s H2 production and carbon capture process: Phase 2

Ekona Power Inc is developing a technology to convert natural gas into H2, electricity, and a solid carbon stream. The solid carbon stream will then be sequestered. Their approach involves two reactors. The first reactor combusts natural gas and oxygen to provide the process heat to the second reactor. The second reactor heats natural gas […]

Read More
In-vitro evaluation of hypervalent antimicrobial agents on epidermal cell susceptibility, proliferation, and migration

Inorganic elements, such as silver and copper, have long been used as effective antimicrobial and antifungal agents. Although the introduction of antibiotics in the early 20th century diminished the use of inorganic antimicrobials, increasing incidence and prevalence of antibiotic resistance has led to a resurgence of interest in alternative antimicrobial technologies. However, valid concern over […]

Read More