The main goal of this project is to develop machine learning and natural language processing approaches to help customers to communicate their preferred brands and/or retailers via Heyday solutions. These approaches will automate answers and help to humanely engage with customers. In order to reach these objectives, some challenges will be tackled such as automatically recognizing the users intent and replying to frequently asked questions. Recognizing ambiguous words is another challenging task to provide accurate answers.
The emerging edge computing (EC) paradigm promises to deliver superior user experience and enable a wide range of Internet of Things (IoT) applications by bringing storage and computing facilities closer to the end users. Virtualization technologies such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV) will allow sellers and buyers to access the open EC ecosystem.
Applying advances in ambient intelligence technologies, this research aims to design and develop a smart workplace to optimize not only physical comfort in employees but also participant happiness. Through ubiquitous monitoring of ambient factors and affective states a number of important research questions associated with designing and developing a smart workplace will be tackled.
The smart grid represents a marriage between power systems and information technology to provide increased and reliable access to power. The greater dependence on information systems however makes it more vulnerable to cyberattack. Modeling these systems accurately is a significant challenge due to their complexity and connected nature. In this work, we focus on the open research problem of developing a modeling platform that combines co-simulation, real equipment and data analytics.
Novel view synthesis is the process of generating new images from an unseen perspective, given at least one image of a scene. There may be more than one probable novel view associated with each unseen perspective, an assumption made by existing methods. This simplifying assumption prevents these methods from being applied to more difficult novel views where the set of probable novel views is highly varied. This project proposes to investigate a new approach to generate a wide variety novel views from a single image, and can produce multiple probable outputs.
In Canada there are just over 17,000 public rail crossings—17% have gates, 22% just have bells and lights, and the remaining 61% have a white, reflective X crossing sign which at times is accompanied by a stop sign. In the U.S., the Federal Highway Administration’s (FHWA) latest figures (2009) indicate there are 136,041 public rail crossings—31% have gates, 16% have flashing lights and 1% have highway traffic signals, wigwags and bells. The remaining 52% have a yellow and black crossbuck. Unsecured rail crossings, combined with distracted drivers, can lead to fatal accidents.
Energy consumers and prosumers are currently dealing with each other via utility companies, which is a slow, costly and indirect mechanism. With the aim of moving toward a free market, the goal of this project is to provide a suitable platform for automatic development and evolution of smart contracts in distributed transactive energy markets. This platform will make the blockchain technology, underlying smart contracts, applicable to direct transactions between energy consumers and prosumers, enabling additional steps towards a free market.
The goal of this project is to create new algorithms and state-of-the-art methods for resource allocation in a financial context. This model can be applied to other domains, such as fleet and personnel management, scheduling of computer programs, manufacturing production control or controlling a mobile telecommunication network. Alpine Macro provides market insights, investment strategy and asset allocation recommendations supported by proprietary models, charts and data. This project will enhance Alpine’s repertoire of tools and techniques for supporting investment decisions.
The intelligent control of space cameras project is concerned with development of the next generation of space cameras. Currently, there is a large gap between the onboard capabilities of standard commercial cameras and those currently in space (examples include image resolution, onboard storage, advanced scene understanding and exposure control).
Analyzing customer behavioral patterns and attrition aids organizations in understanding its core customers and improve its decision-making processes in regards to customer attrition and targeted marketing. In this research project, we will develop behavioural analytics super network models and algorithms for behavioural customer segmentation and attrition prediction in the presence of big data. Our models will help our partner organization develop better understanding of its customers and how to better manage their business relationships with them, thus solidifying its market position.