The goal of this research is to investigate, design and evaluate user-adaptive visualization systems, which personalize interaction based on the individual needs of a given user. In order to achieve this goal, a visualization system is required as a starting point with which to carry out this research. As a first step, this research aims […]

Deep neural networks (DNNs) for automatic speech recognition (ASR) require large amounts of labelled data, which can be difficult and expensive to collect. However, recent research has shown that some features learned by DNNs are highly transferable to other tasks and datasets. Here we propose to design a multi-lingual training procedure to leverage large amounts […]

Many applications often need access to information from multiple independent data sources, including public sources found on the Internet and private sources e.g., hospitals. Software that sits between an application and the data sources, so called “middleware”, can help facilitate this access. However, development of this “middleware” can be very time consuming, is often only […]

Social network is becoming an increasingly popular media for information sharing. However, undesirable contents such as malicious rumors can spread through social networks among individuals. The technique to prevent undesirable content can also be applied in parenting control. As the more and more teenagers are using social network today, it is important to minimize the […]

Item-to-item and user-to-item recommendations are prevalent on most ecommerce websites and digital content related mobile applications. At Kobo, we strive to constantly improve our recommendation system, which is based on co-purchase patterns on Kobo’s website or through Kobo eReaders and mobile apps. This internship is to explore improving the system along several dimensions: incorporating additional […]

RightsEnforcer is a software system for Persistent Document Security, deployed and proven in the real world as a Windows-only client-server system. ‘Persistent’ information security controls access to the protected document, everywhere, always, and is therefore uniquely suited to be a dominant information security technology in ‘the Cloud’. But to thrive in the Cloud the RightsEnforcer […]

Interface designs based on initial consultations with one group of users are often found to not be suitable for other groups. This a problem both in practice and for our understanding of interface design. This project investigates why this happens, using as an example a system developed for INETCO Systems. The immediate objectives include understanding […]

Sketch3 is an experimental software project to accelerate sketching for ideation and in various design contexts, facilitating visualization in both 2D and 3D. The goal is to evolve a paradigm for ideating rapidly with a digital stylus (2D/3D) analogous to the fluid 2D sketching experience on paper. The software is expected to remove much of […]

The intern shall endeavour to develop a vehicle detection system for aerial satellite views with a reasonable accuracy and a reasonable execution time for a small urban area of 100 sq. km. The intern first will train, test, and evaluate a machine learning engine to automatically recognized the vehicles of interest in aerial satellite imagery. […]

Foreign exchange market, also known as Forex is a currency trading market spread all around the globe. There are multiple factors that effect the exchange rates in currency market. Considering these factors in development of a trading algorithm will result in more accurate trading decisions. The proposed research that will be covered by the activities […]

At present, there is an increasing demand from industries for new generation of interactive technologies to support productivity and minimize time wasted for meeting room set up. In response to this demand, SMART technologies is investing into development of new UC&C technologies. The goal of this research will be the development of a software for […]

This research project with the industry partner DataWind inc. is an interdisciplinary project that joins together Education, Learning system engineering, and Human-machine interactions. The challenge is to combine these four disciplines contributions in order to create a learning system for mobile devices that will be adapted to the individual self-learning, particularly for children in developing countries. […]