Uncertainty Quantification for Deep Neural Networks

Deep neural networks are effective at image classification and other types of predictive tasks, achieving higher accuracy than conventional machine learning methods. However, unlike these other methods, the predictions are less interpretable. While accuracy may be enough for applications where errors are not costly, for real world applications, we want to also know when the […]

Read More
Advanced sensor control implementations for energy optimization in commercial buildings using machine learning and data visualisation applied to building automation systems

The objective of the research is to develop a system leveraging data captured for commercial building management systems (BMS) to take decisions in to reduce energy consumption without affecting comfort. The idea is to showcase how intelligent control can be implemented in existing BMS to optimize energy consumption. The project is divided in three parts: […]

Read More
Probiotics for improved carotenoid bioavailability: A double-blind, randomized, controlled trial

There is a simple way to have great skin, be more attractive, and improve one’s health, but most of the global population refuses to do it. Worldwide fruit and vegetable (FV) intake is below recommendations reducing the intake of yellow-red plant pigments that have antioxidant, anti-inflammatory, anti-cancer, and anti-obesity properties. These plant pigments are called […]

Read More
The Next Generation Agriculture: Botanical extracts and essential oils as the new antimicrobials against microbial contaminants and diseases of Cannabis

The majority of license producers (LP) Cannabis producers have witnessed evidence of powdery mildew and grey mold and bud rot diseases. Plant yields and ultimate profitability can be severely undermined by these diseases. Medicinal plants produce essential oils in the form of secondary metabolites. The essential oils have the potential to be used as antibacterial, […]

Read More
Advanced Nystagmus System (ANSTM) as objective diagnostic tool for mild traumatic brain injury (mTBI) and concussion: A validation study using structural and functional magnetic resonance imaging

Annually, 2 million individuals in North America suffer mild traumatic brain injury (mTBI) or concussion (cost: $75 billion), with 200,000 in Canada. An objective tool is required to distinguish concussed subjects acutely from ontrols, and to predict who will develop chronic symptoms. The frontal lobes, the corpus callosum, and the thalamus play key roles in […]

Read More
Detecting deception, disinformation, and crowd manipulation on social media through machine learning, natural language processing and artificial intelligence

Recently, due to the widespread effects of “fake news”, a form of propaganda that is intentionally designed to mislead the reader, there has been a significant research effort to automate the process of detection of misinformation in social media. Although existing methods for automatic fake news detection are promising, distinguishing between true and false news […]

Read More
Textual Analysis of Climate-Related Disclosures

When faced with difficult issues such as climate change, some organizations decide to disclose information on relevant risks, opportunities, and strategies. The language used in these disclosures can theoretically reflect how managers process information in complex and uncertain environments, and by extension, their abilities in creating value for the firm. This research collaboration examines linkages […]

Read More
Geometallurgical Simulation and Multicriteria Risk Evaluation

The evaluation of mining projects depends on modern computational techniques. There is a demand for increasingly sophisticated techniques, due to environmental considerations and the drive toward increasingly complex ores. Without these techniques, projects may be wrongfully held back or abandoned, leading to severe socioeconomic consequences in the surrounding communities. Conversely, mining projects may be wrongfully […]

Read More
CFD methodology for analysis of multiphase flow process

Oil that has passed through the bearings and gearboxes of aircraft engines is recycled by a specialized oil scavenging system that separates droplets dispersed from the shaft from air and particulate matter. This process helps to mitigate the emissions of aircraft engines, greatly improves oil consumption and Improves working life by improving the cooling capabilities […]

Read More
A generic microgrid controller with rule-based dispatch

In order to provide more reliable electricity, facilitate clean enery integration and supply energy to remote communitites, part of the power grid may be required to operate autonomously. Microgrids which can be islanded from teh main grid, are deployed for this purpose. However, the compositions and objectives of microgrids vary in different applications and operating […]

Read More
Uptime Energy Control Procedure Using Machine Learning

In a time where energy use awareness is more and more prevalent due to its significance in global warming, all sectors of society are putting effort to participate in finding new ways to reduce energy consumption. The industrial sector in Canada consumes nearly 1/3 of total energy. A challenge for industrial organizations is to define […]

Read More