Comparing and Improving Approaches to Topic Modeling

The proposed research project aims at evaluating and improving a technique in Statistical Natural Processing called Topic Modelling in order to apply it to real-life scenarios. Topic modeling is a techniques that allows the quick discovery of what the main topics of a document collection are, and thus automatically answers the question “What do these documents talk about?”.
Several approaches have been proposed to implement topic modeling, but their evaluation have rarely taken the end-use into account.

Graphene Oxide membranes for acoustic drivers

The Graphene Audio group at TandemLaunch is working to revolutionize loudspeaker design through the use of graphene composite materials (Graphene-CMs) in loudspeaker membranes. Graphene is a newly discovered material with exceptional mechanical and electrical characteristics. Its low mass and high strength make it ideal for use in acoustic transducers offering an immediate benefit over existing loudspeaker technologies.
This project seeks to improve the manufacturing techniques and acoustic characteristics of these Graphene-CMs.

A remote sensing-based wetland inventory and classification framework for Newfoundland and Labrador using satellite optical and synthetic aperture radar data

This project aims to develop a remote sensing based framework for Newfoundland and Labrador (NL) wetland inventory and classification and monitoring through the synergistic use of satellite and airborne multi-spectral and ortho-imagery and space-born synthetic aperture radar (SAR) data. The proposed project involves collaboration from C-CORE, Ducks Unlimited Canada, and Santec. The results and approach will help Ducks Unlimited Canada for conserving wetland and for waterfowl, wildlife and people.

Design of Polar Codes for Multiple-Input Multiple-Output Communication Systems: Constellation and Code Design

Reliable communication over wireless channels has been an active research area for decades. By employing multiple transmit and receive antennas, multiple-input multiple-output (MIMO) systems increase the capacity of a wireless channel, bringing significant gain over single-input single-output (SISO) systems. One of the main tools to achieve the improved capacity are error correction codes. During the years since the introduction of the error correction codes, there have been many important breakthroughs in this field. Polar codes are the most recent of these revolutions.

Design of an Interface for the Intuitive Control of a Unmanned Air Vehicle fleet in Emergency Situations

The project consist of developing a novel interface to control a fleet of quadcopters in an emergency situation. The interactive system will have to interpret the user intent in such a way that minimum cognitive resources are required. Humanitas products target non experts in robotics whom need to maximize their concentration on medical support and logistic, thus they require an intuitive and not monopolizing control interface. It will also be required that feedback information can be sent to the user without using the visual feedback of their application control screen.

Document Engineering via Semantic Correlations - Year Two

We propose to develop smart algorithms for document generation, by innovating in the field of natural language processing and document intelligence. We envision the next generation of business applications able to parse and understand documents, to compose documents automatically, and to respond intelligently to voice commands. Our industrial partner, Koneka Inc. has a document automation platform that generates documents by assembling clauses (content-blocks) together based on a set of user inputs.

En Route to 5G: Long-term Evolution (LTE) Enhancements for the Internet of Things (IoT) - Year Two

Cellular wireless communication has reached a level of coverage and reliability that it is considered a commodity. However, the dramatic increase in Internet traffic to and from wireless devices poses significant challenges for network operators. While the current growth of traffic is mostly due to consumers communicating more frequently and larger amounts of data over the wireless infrastructure, much of the future growth is predicted to come from non-human operated devices or so-called machine-to-machine (M2M) communication.

Optimal Two-Dimensional Energy Management of Grid-Connected Thermal/Electrical Hybrid Energy System

This project is designated to develop a next generation optimal two-dimensional energy management algorithm for a novel grid-connected thermal/electrical hybrid energy system. On-site implementation of the model and algorithm will be phased into a real community at an undisclosed location for performance evaluation.

Feasibility Study of a TV-Based Video Chat Technology for Elderly with Dementia

According to the Canadian Institute for Health Information, many of Canada's increasing aging population experience physical and cognitive impairments that necessitate moving to a care facility, with 44% of these residents having or indicating symptoms of depression. Social isolation is a contributor; 22-42% of these residents reported feeling severe loneliness. Video chat sessions have been found to be valuable augments to in-person visits. However, for adults with impairments such as dementia, operating the associated technologies might be impossible.

RF Resonant Chemical Sensor System for Biomarker Detection and Biomedical Applications

Sober Steering is developing a wearable alcohol sensor system that communicates with a vehicle to prevent drunk driving. The FitBit-style wearable device will communicate wirelessly with a Sober Steering module located behind the dash of the vehicle to provide interlock functionality and instant alerts. The wearable alcohol sensor system will be monitored and controlled by a smart phone app (ideally controlled by parents or fleet vehicle dispatch). The proposed project aims to further develop sensors capable of providing alcohol sensing functionality for the wearable device.