Detection of suspicious and/or abnormal real-time events from textual live data feeds

Social media and other real-time messaging applications represent valuable sources of real-time information that remain untapped by many service operators. The project is aimed at developing methodology for detecting suspicious and/or abnormal real-time events from textual live data feeds, based on predictive and/or anomaly detection algorithms applied to time series and text features.
TRT Canada is therefore interested in developing algorithms that will be able to recognize such events based on similarities with past events in order to address the mentioned scenario.

IRIS FaceMatch: A secure face-based identity detector without racial bias using deep learning

This project aims to address the race bias of face recognition technology by developing new face feature sets and building the suggested models based on an equal number of images from varied-race photos using appropriate deep learning algorithms. This research seeks to deliver industry partner IRIS with guidelines for a developed prototype that facilitates the adoption of IRIS’s FaceMatch technology for enhancing police capabilities to find unidentified individuals based on their photos while saving labor force and other police resources.

Next Generation User Product Documentation

Product documentation is an important information tool connecting any business to its end-users and customers. Comprehensive product documentation will likely result in positive evaluation of the products by the customers and may influence their future purchasing decisions. Many studies show product documentation remains an essential element of any new product even for modern electronic devices used for information and communication technologies.

NLP sentiment analysis for contact and support centers

In today’s competitive market, customer service has become essential to any company willing to expand and increase its business. Companies cannot afford to fall short of consumer expectations. With the recent progress in Artificial Intelligence (AI) and the impressive results in different industrial areas, companies are adopting AI techniques for customer service. Most of the applications of AI in contact centers are based on the use of chatbots. These conversational agents are trained to interact with the customer and answer questions.

Supporting Community Engagement in the Maker Movement

The Ville Cooperative (https://www.theville.ca/) is a holistic community centre, working to empower the local community to learn, share and grow in the spirit of health, wellness, and sustainability. One of the areas in which it hopes to realise it’s vision is through the newly rebranded fabrication lab - Learning Lab @ The Ville.
The Ville’s Learning Lab, like most makerspaces and fabrication labs, is currently undersubscribed; the space is neither heavily used nor being used near its potential.

Plant level implementation of a model for real time tracking of composition changes to steel, slag and inclusions during ladle processing

The Ladle Metallurgy Furnace is used for adjustment of chemical composition and temperature, and control of tiny particles called “inclusions”. Controlling inclusions is carried out by adding calcium to modify the solid alumina or magnesium aluminate inclusions to less harmful liquid inclusions.
During ladle process, reaction of top slag, steel and inclusions occur simultaneously. Therefore, establishing a model to describe ladle process is indeed a challenge.

Spatial mapping of turbulent characteristics of tidal flow and wakes in the Minas Passage Bay of Fundy

The strong tidal currents that make in-stream tidal energy possible, are also challenging to work in since they are also very turbulent. As the flow passes over the rough bottom and shoreline variations, eddies are generated over a wide range of scales. These eddies (i.e. turbulence) create fluctuating forces on tidal turbine blades and their support structures, degrading turbine performance and operating life. Understanding and predicting the levels of turbulent flows is an important component of the marine services that Luna Ocean provides to its clients.

Automatic Approach to Design Efficient Deep Neural Networks

Deep neural networks have demonstrated state-of-the-art modeling accuracy on a wide range of real-life problems, with some cases surpassing human performance. Despite the promise of deep neural networks as an enabling technology for a large number of industries and fields, there are two particular key challenges in the design of deep neural networks in real-world, operational scenarios. First, the design of deep neural networks is a very time consuming process for a machine learning expert, and often results in complex, non-optimal deep neural networks.

Development of a reliable and scalable underwater acoustic modem for networked applications

The proposed project represents a critical effort towards developing the enabling communication technology for the future of subsea connectivity where conventional communications technologies such as Wi-Fi and GPS cannot be used. The intern will work to completely overhaul traditional underwater communications methodologies and advance acoustic communications towards the higher reliability and data rates needed for future underwater networked applications and deployments.

Visual Analytic Tool for Lessons Learned Retrieval and Decision Making

According to the World Petroleum Council (WPC), the average age of employees in Oil and Gas companies is 50 years, and it is estimated that in the next 5 years 40-60% of them will retire. One consequence of this age-related crisis is losing the accumulated knowledge by retiring “gray-beards”. In this scenario, new software technologies are mandatory to retain decades of expertise and transfer it to new employees.

Pages