Infectious diseases from a variety of pathogens can lead to serious health conditions such as sepsis. To improve the prognosis and decrease the mortality rate of infectious diseases, point-of-care testing (POCT) of blood biomarkers is a critical approach. Testing of biomarkers such as C-reactive protein, IL-6 and procalcitonin could help identify the type of pathogen and classify the progression stage of infection.
CT (Computed Tomography) scans are widely used medical images used to diagnose disease such as cancer. CT Scanners pass x-rays through the body in order to generate cross-sectional images. Unfortunately pro-longed exposure to radiation (via x-rays) can damage the body, and thus one aims to minimize the x-ray dose they receive. However, modern CT scanners produce lower quality images when using low x-ray dose which defeats their purpose as a diagnostic tool. We propose a post-processing algorithm to enhance the quality of CT images produced at low radiation dose.
The main objective of the project is to upgrade the existing system at Cheetah Networks to make use of Canadian cellular CAT M1 monitored network data to develop innovative QoE analytics that can be used to provide actionable insights. The system will explore applying new techniques to capture in real-time QoE visibility into experiences locally, regionally and nationally. The primary methodologies that we will be employing are based on machine learning and deep learning techniques for data classification, clustering and analysis.
Over the past few decades, mental disorders (e.g., depressive and anxiety) have become a significant medical burden for people of all ages. According to the survey performed by the World Health Organization (WHO), at least one out of ten people in the world suffers from mental health diseases (i.e., mental disorders, neurological disorders and addition). Many factors, such as heredity, work pressure and aging, can attribute to these disorders and degradations. However, some of these mental health diseases are preventable and treatable.
Most ultrasound scans require time-consuming manual scanning of transducer arrays to obtain 2D images of the body. 3D images can be acquired by so-called matrix probes but these are large and bulky, and typically offer inferior image quality. Such probes do not exist in high-frequencies important for pre-clinical applications and to date no wearable 2D probe exists. Our vision is to create wearable flat-form-factor 2D arrays that could be used for longitudinal monitoring of the heart or other critical parameters in a hands-free way.
The goal of this project is to design and develop a wireless network testbed at the University of British Columbia (UBC) for Rogers Communications Canada Inc. to support different use cases for the fifth generation (5G) wireless networks. We will study the concept of self-organizing network (SON) and design a deep learning-based algorithm for our testbed to determine the optimal network parameters based on network traffic data and key performance indicator (KPI) statistics. We will also design a network traffic forecasting algorithm by capturing the mobility patterns of users.
Research into child safety applications using Artificial Intelligence (AI) methods is a new area of investigation. SafeToNet is continuing to develop AI monitoring tools together with a team of researchers at the University of Ottawa. These tools, when used over time, will take advantage of outgoing text-based communications from devices to detect the early onset and progression of developmental and mental health issues in youth.
The objective of this project is to develop and customize a cosimulation platform capable of integrating multi-formalism simulators for SG cybersecurity analysis. This enables one to provide a cosimulation platform which is characterized by scalability (no limitation in terms of nodes/buses of communication/power systems), compatibility with the Functional Mock-up Interface (FMI) standard and capability of synchronized integration of any two abstract simulators (NS-3, OMNeT++ for communication network and EMTP, MATLAB/Simulink for power system).
Lead scoring is essential for lead management. The result of lead scoring is a list consists of leads with scores assigned indicating how likely each lead can be converted into the next stage of sales process. The Lamb or Spam and the Rule-Based are the two lead scoring methods that have been discussed in the literature. As various machine learning algorithms and artificial intelligence started to reemerge, predictive lead scoring models seem to be the next promising solution for lead scoring activity.
Detection of financial fraud is a priority for financial institutions. There are a variety of techniques and models that can be used to address the problem of financial fraud. However, as fraudsters are becoming more inventive and adaptive, they have been able to penetrate the conventional protective methods. This is one of the main reasons for the growth in financial fraud activity, regardless of the efforts of financial institutions and government and law enforcement agencies.