Adaptive techniques to predict the N2O emission in a corn field under different fertilizer management practices and external factors.

Global warming is one of the largest environmental issues these days and the increasing greenhouse gases(GHGs) emission such as CO2, CH4 and N2O is the leading reason for global warming. The main sources of CH4 emission are rice cultivating systems and cattle rearing, meanwhile, N2O mainly come from the application of fertilizers. Many factors in the fertilizer management practices, as well as environmental factors, could affect the N2O emission therefore the carbon foot print. In this research, external factors such as temperature, irrigation, soil texture, etc.

Data Driven Intrusion Detection in Autonomous/Connected Vehicles

Securing autonomous vehicle environments has recently become a hot topic for both industry and academia due to the significant safety and monetary costs associated with security breaches of such environments. This requires different approaches to address the challenges and propose potential solutions at multiple levels of these environments. To that end, machine learning (ML) and blockchain (BC) techniques can play a vital role in ensuring that the safety and security standards are satisfied to protect vehicles from failures that may cause an accident and/or possible attacks.

Machine Learning Aided Self-Estimation of Device Position in Cellular IoT Networks

The research program in this project aims at advancing the use of cellular communications for Internet-of-Things applications. The academic researchers and the partner organization have identified three work items that revolve around the self-estimation of cellular IoT devices (1) to improve energy and spectrum efficient transmission of short and intermittent data packets, (2) to enable cellular non-terrestrial communication with low-cost devices, and (3) to help realize tracking applications that can benefit from device-to-device communication.

Technology Innovations to Improve Patient Outcomes After Spinal Cord Injury

Spinal cord injury (SCI) results in severe paralysis, for which there are no effective treatments. Advanced technologies, however, can play an important role in assisting in the diagnosis, monitoring, and treatment of SCI patients who suffer many impairments beyond the loss of voluntary muscle control. In this proposal, we will develop and apply innovative technologies for SCI. We will develop a novel biosensor for the injured cord to inform doctors how to best support its healing in the early stages of injury.

Indoor Virtual Tour and Virtual Object Display in 360 Degrees

The proposed project implements the applications of virtual view of indoor environments and objects in 360 degrees, thereby encouraging people to check the information of rooms and products online during the COVID-19 pandemic. Specifically, six objectives are proposed, each undertaken by two interns, to build a virtual view system satisfying different scenarios.

Model-Based Security Compliance-By-Design for Low-Earth Orbit Satellite Operations Segments

Low-earth orbit (LEO) satellite constellations require high levels of security and resilience to provide high quality, reliable and trustworthy global connectivity services to customers. For these systems to develop customer trust and find widespread use, developers must demonstrate compliance to a variety of security standards, policies, and regulations. However, because these systems are very large and complex, it is difficult to clearly and effectively show how the system satisfies all of its compliance requirements throughout its development lifetime.


Loblaw Companies Limited (LCL) supplies all fresh produce (FP) to South Western Ontario stores from Waterloo Distribution Center (DC). DC decides prices and quantities to meet FP demand. Timed fair priced orders minimize waste, bring prosperity to growers, consumers and FP trades. Factors affecting prices are highly uncertain due to environmental and socio-economic effects such as income, labor, trade, globalization and climate change which makes price prediction challenging.

Multi-modal learning of human pose representation for conditional motion synthesis

The goal of the project is to generate realistic human movement in 3D animations. This is important to make movement animations in games and movies appear real. Typically, creating high quality animations is a resource and time consuming process that requires the participation of human actors in motion capture sessions. In this work, we present a data-driven approach that aims to generate novel animations based on a library of past motion capture recordings that can make generating high quality animations low cost and fast by eliminating the need to record human actors.

Point-of-care breath analyzer for early-stage disease diagnosis

As the third documented emergence of an animal-to-human coronavirus during the past two decades (Severe Acute Respiratory Syndrome in 2002, Middle East Respiratory Syndrome in 2012), the current pandemic and near-certainty of future epidemics demands intensified surveillance and proactive screening. Definitive therapy for novel Coronavirus Disease 2019 (COVID-19) is likely at least half a year away. Current standard-of-care diagnostic testing with real-time Reverse Transcription Polymerase Chain Reaction (rRT-PCR) is resource intensive, costly and inaccurate.

Linearization of High Peak-to-Average Power Amplifiers for Digital Broadcast Radio Applications

Broadcast radio is changing from an analog medium based on frequency modulation (FM) to a full digital broadcast based on orthogonal frequency division multiplexing (OFDM). The high peak-to-average power ratio of the OFDM waveform requires different power amplifier topologies and a high degree of linearity. The research in this project analyzes current amplifier performance for digital radio broadcasting in the FM band, investigates new linearization techniques and explores new amplifier topologies.