Analog ASIC Artificial Intelligence at the Edge

Enabling Analog Artificial Intelligence by the systematic generation of Analog Neural Networks from well-known Artificial Intelligence software tools. The circuits and methodologies developed here enable “AI at the Edge” meaning local, low power, analog AI that provides, for example, medical devices that analyse signals to asses the need for intervention; voice recognition devices that do […]

Read More
Certified Defense Framework against Patch Attacks on Images

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. […]

Read More
Discovering novel approaches to robust machine learning and visualization for banking applications

The overall objective of this project is to develop approaches to improve rating robustness that are distributionally robust. We will develop techniques to utilize ensemble learning machine learning models with categorical monotonic constraints. Lastly, we will develop novel data visualization tools for business intelligence tasks that will help decision makers at Scotia Bank.

Read More
Quantifying diaphragm perfusion in humans: A novel application of contrast-enhanced ultrasound

As oxygen demand increases (e.g., exercise), the availability of oxygen decreases (e.g., high altitude) or cardiopulmonary function is impaired (e.g., respiratory disease), our cardiopulmonary system works at a greater percentage of its maximal capacity to supply oxygenated blood to tissues. Currently, there is no reliable way of determining the blood flow to the respiratory muscles. […]

Read More
Towards the Commercialization of Perovskite Solar Cells

The project aims to design and fabricate high-performance perovskite solar cells for commercialization. Suitable fabrication methods will be employed for preparing perovskite solar cell samples in large-scale while characterizing both perovskite films and devices by utilizing a myriad of techniques. The characterization methods will provide better insight and invaluable date of the operation of perovskites […]

Read More
Designing a Full Duplex Transceiver to Improve the Detection of Low Cost Resonators Used in Electronic Article Surveillance

Electronic Article Surveillance systems, which are used to help retailers detect shoplifted items, suffer from two major problems. First, the systems often fail to detect EAS tags/labels that are present within the ‘detection zone’ of the gate. Secondly, false detection indications when EAS tags/label are not present within the ‘detection zone’ of the gate. As […]

Read More
Improving Conductivity and Waterproof Ability of Solar Tile Connectors

The project is to enhance the stability of the detachable solar tile panel connector in terms of conductivity and waterproof ability. The student will investigate other applications such as solar tiles for roof mounted applications and the current designs and prototypes developed by Square Solar. They will also develop a set of design requirements that […]

Read More
Techno-economic assessment of operating grid-scale super-capacitor energy storage for a wind power producer

Battery and energy storage units are one of the main sources of backup power in modern power systems to support the renewable power generation deficiencies in meeting the load demand. In recent years, the advancements in the charge/discharge efficiency, low cost, and long life of super-capacitor energy storage (SCES) technology have challenged conventional battery technologies. […]

Read More