Deep Mixture and Generative Models: Representation, Approximation, Robustness, and Application

Recent progress on deep architectures has enabled efficient representation and learning of complex high dimensional probability distributions over rich sensory data. In particular, deep mixture models and deep generative models have emerged as the most powerful techniques for this task. The proposed research aims at addressing some of the fundamental questions in this field: What […]

Read More
Accuracy Assessment of Optical Tracking for Orthopedic Robotic Surgical Tool

Highly accurate spatial measurement systems are among the enabling technologies that make image-guided surgery possible in modern operating theatres. We consider the problem of positional accuracy assessment for robotic surgical tool while using a multiple camera optical tracking system (OTS). Since the position of the surgical tool with respect to the bone is guided by […]

Read More
Health Information Interoperability with Bidirectional Transformation and Assurance (HealthBX)

The objective of the HealthBX project is to research and develop advanced software engineering methods for the purpose of increasing the interoperability of different clinical health information systems used in the province of British Columbia (BC). BC clinics use a variety of different health information systems to maintain electronic patient data. However, the abilities for […]

Read More
Learning PDF Document Structures using Recursive Neural Networks

Portable Document Format or PDF is the de facto standard for presenting textual-visual content. In this project, we aim to develop a machine learning framework for PDF document understanding. Despite the recent proliferation of deep learning-based methods for the analysis and processing of natural images, there have been considerably less efforts on designing similar approaches […]

Read More
Accelerate Transaction Latency of Pool Mining in Cryptocurrency Networks

In this project, using such mainstream cryptocurrencies as BitCoin and Ethereum as representatives, the intern will analyze the transaction collection strategies of their mining pools, and then collect transactions and the corresponding blocks data to build a large dataset, from which the computing power of different mining pools and their proportions will be analyzed, together […]

Read More
Impact of Post-Quantum Cryptography on PKI, Common Libraries, Protocols and Crypto Agility Requirements

Advances in quantum computing have Entrust Datacard and their customers concerned about whether the industry is ready to move to post quantum cryptographic algorithms, particularly for PKI use cases. Entrust Datacard and University of Ottawa will test the quantum-readiness of commercially-available PKI. The end goal is to provide guidance to the community about the impact […]

Read More
The control tower of the future

In our vision, each human operator participating to an emergency response mission should equipped with a portable mobile command center that collects, elaborates and displays the meaningful information generated within the area of operations. In such scenario, the availability of a reliable network able to offer the required performance and reliability to an heterogeneous set […]

Read More
Detection of Fights in Crowd Video

Detection of fights and anomalous behavior of individuals in a crowd is a common problem in computer vision. Some tools that currently exist rely on optical flow of tracked features is a sequence of video frames. These motion algorithms are sensitive to independently moving objects in the frame. What constitutes an “anomaly” is context (eg. […]

Read More
A Care Management Use Case: Correlation Detection between Dental Claiming Patterns and Overall Cost of Care by Participant

Green Shield Canada (GSC) is going to achieve the capability of data analytics in order to make data-driven decisions in various care management use case scenarios. One of these use cases is to detect specific patterns and associations between dental hygiene and health care costs of the individuals covered by them, predict points of intervention […]

Read More
Stateful Intrusion Detection using Algebraic State-Transition Diagrams

Increasingly, cyber threats evolve targeting companies, industries and governments. As defense systems are strengthening, threat actors developed new tactics, strategies and techniques to break down security perimeters. Generally, the security of the perimeters are enforced by multiples intrusion prevention and detection tools responsible to provide proactive insights, real-time insights and operational insights for the detection, […]

Read More