Auto-configuration of an autonomous farming vehicle using Machine Learning

Precision agriculture has many benefits especially for the developing world. Autonomous tractors and automatic planting systems have high accuracy, resulting in a substantially improved return on investment for growers, making food planting more economical. Moreover, the tractors can collect information on soil conditions, which can lead to improved maintenance of the crops, prevent blights, and achieve higher efficiency and higher plant food quality.

Advanced Signal Processing and Machine Learning for BLE-based Indoor Localization

The Internet of Things (IoT) is a new emerging paradigm and is rapidly gaining ground in different applications of significant engineering importance including but not limited to smart buildings, and smart public environments. The main enabling factor of this promising paradigm is integration of identification, localization, and navigation technologies with smart hand-held devices equipped with sensing, processing, and communication capabilities.

NLP Sales Assistant

The goal of this project that will be conducted in collaboration with Heyday is to create a technology that uses a given messaging platform (e.g. Facebook Messenger, web chat widget) that allows users to communicate easily and smoothly with their preferred brands or retailers. This technology should allow the automation of answers and interaction between users and retailers. The technology that we would like to develop will be based on advanced Natural Language Processing (NLP) and machine learning techniques.

An information-theoretic framework for understanding generalization in neural networks

Deep neural network (DNN) is a class of machine learning algorithms which is inspired by biological neural networks. DNNs are themselves general function approximations, which is the reason they can be applied to almost any machine learning problem. Their applications can be found in visual object recognition in computer vision, translating texts in unsupervised learning, etc. DNNs are prone to overfitting because DNNs usually have many more parameters than the available training data. However, they usually have a low error on the test data.

Research, development and testing of an instrument that can monitor and detect internal failure in liquids pipelines

The ubiquity of pipeline incidences have resulted in undesirable economic, environmental and social consequences. However, pipelines are a critical element of the transportation system of most countries, and are needed to convey goods and resources from one place to the other. In this research project, a technology that can be used to monitor operating pipelines is developed and extensively tested. This technology is projected to be able to identify the onset of pipeline failure earlier than existing technologies, and contribute towards improving the integrity of operating pipelines.

Improved pulse pressure approximation and pattern recognition algorithm for prediction of blood pressure-related health issues

Continuous blood pressure (BP) monitor is highly beneficial for detection and prevention of stroke and cardiovascular disease. The most common BP monitor technique still relies on using a cuff that slows the blood flow, which is both uncomfortable and makes continuous monitoring impossible. Furthermore, research has shown that due to the numerous artifacts, the existing cuff-less BP monitoring technologies such as pulse transit time (PTT) and tonometry are not effective.

Calibration-Free Continuous Pulse Oximeter Monitoring Using Deep Learning

Oxygen saturation, i.e. SpO2 is the fifth most important vital sign after heart rate (HR), body temperature (BT), blood pressure (BP), and breathing rate (BR). Oxygen saturation indicates if sufficient oxygen is being supplied to the body.
Continuous SpO2 monitoring is highly beneficial for detection and prevention of several diseases.

Transactive Electric Distribution System

Electric power distribution systems physically connect the newer active transactive energy (TE) elements such as energy storage, demand response, electric vehicles, and renewables to customer loads and electric supply from the transmission system. The proposal outlines a Transactive Electric Distribution System (TEDS) framework which enables the creation of a robust distribution system market in Canada and elsewhere.

Testing of a Collar-Mounted Airbag to Protect Against Neck Injuries and Concussions

Hockey parents are worried about rising concussion rates. Currently no sports equipment protects against concussions. Hockey players aged under 18, must wear a neck guard for protection against skate blade cuts. Recently, a redesigned hockey neck guard, using an impact sensor and airbag technology was conceptualized. We want to test whether airbag inflation upon direct or indirect hit to the head/face/neck/upper body, can simulate “neck bracing,” and reduce neck injuries and concussion risk caused by whiplash or rotational movement of the head/neck.

WP 2.1.2: Advanced, Intelligent, Analytics Driven Apps for Software Defined and Functionally Virtualized Networks

Networks are moving towards being adaptive. This means that automation will be used to replace processes which are today highly manual. This project proposes a development of knowledge in the area of algorithms required to enable adaptive networks. The project will train two PhD students to understand optical networks and devise optimization algorithms in the areas of interest. In particular, the algorithms will be devised to be fast and near-optimal to enable their implementation in the network in accordance with operator’s goals of making the network near-optimal and adaptive.