Software for prediction of postoperative atrial fibrillation following bypass surgery

The problem of accurately predicting the onset of sustained postoperative atrial fibrillation (AF) in patients undergoing coronary artery bypass grafting (CABG) remains open. Investigators have reported many clinical indices currently associated with postoperative AF following CABG. Contemporary machine learning techniques are well-suited to recognizing underlying trends in 'training' data consisting of several labeled examples, and to using the results to classify new unlabeled data with remarkable sensitivity and specificity.

Privacy analysis of mobile analytics

Many companies require the gathering of user behavioural data from mobile devices and device applications in order to: i) improve their products, ii) monitor their systems, iii) engage in targeted marketing, etc. Significant privacy concerns exist with the measurement and storage of such data. In general, existing research highlights that data anonymization can be insufficient to fully address these risks, i.e. that anonymized data can be clustered and correlated with external sources to reveal private information.

AWE technology development project - the virtual history of Fort York

Divani's AWE Augmented Reality product is expected to assist Fort York to create a more engaging experience for the attraction’s 100,000 annual visitors. By combining the historical value of Fort York with the immersive experience of AR, the organization will be able to increase revenue to assist with its financial goals. Divani Films is expected to benefit from a successful rollout by generating new revenue streams from the licensing of AWE technology and/or forming additional partnerships within the tourism industry as well as other industries (gaming, sports, etc.).

Investigate parametric machine learning algorithms to develop anomaly detection methods on real-time data

The industry partner, Metafor is developing a new class of IT system management solution. As part of this project, Metafor is building a product feature that monitors computer and network activities and looks for signs of anomalies. This is an important problem as anomalies are usually associated with abnormal user or system behaviors that can potentially result in problems such as system breakdown.

Investigate machine learning algorithms to develop anomaly detection methods

The industry partner, Metafor is developing a new class of IT system management solution. As part of this project, Metafor is building a product feature that monitors computer and network activities and looks for signs of anomalies. This is an important problem as anomalies are usually associated with abnormal user or system behaviors that can potentially result in problems such as system breakdown.

Evidence-based product support and the cultivation of a community of learners

While consumers adopt technological solutions based on their perceived usefulness, continued use of those products often depends on the support customers receive as they initially use the product, and when they run into problems or complex uses. Traditional support models (e.g., call centres) are often costly and only somewhat effective.

Measuring and quantifying mobile user quality of experience

The objective of this research is to develop an on-device, quality of experience (QoE) measurement suite, for Android based mobile devices. As mobile devices become the predominant method with which the world accesses the internet, it becomes increasingly important to understand the complex interaction between applications, mobile OS’s, the networks they run on, and the behaviours of a user base at large. Doing so with mobile devices raises a set of issues that aren’t present with traditional PC’s, and as such haven’t been explored thoroughly.

Assessing of affects on application-level mobile device quality of experience measures

With the growth of mobile device platforms such as smartphones and tablets, users now primarily experience the wireless networks they uses, whether cellular or WiFi based, through the context of the apps that they use. Hence, a heavy Skype user may perceive a given network to be of substantially different quality than would be perceived by a heavy text-messaging user. This reality has lead to a growing interest in quality-of-experience (QoE) measures as a compliment to more traditional network-level quality-of-service (QoS) measures.

Disaster recovery and cloud bursting as a cloud service

Cloud computing has revolutionized the way organizations consume computing power as a service. Infrastructure as a Service allows a company to move away from purchasing computing, networking, and storage resources to purchasing from a service provider in a public cloud. This project will research and develop off-site encrypted virtual machine storage and disaster recovery planning solution built using public cloud infrastructure.

Aperture antennas as mobile satellite terminals

Antennas are essential part of communication links. This project is investigating antennas for communication between a mobile terminal on earth to a satellite. The mobile terminal could be a flying craft or a vehicle in motion. These antennas should be able to transmit and receive data simultaneously in different channels. Besides, they should be capable of scanning the space to find the target satellite. Single channel antennas or antennas with mechanical tracking have been tested for this purpose and are available in market.

Pages