In 2018 the Global Ocean Observing System (GOOS) approved Ocean Sound as an Essential Ocean Variable (EOV) within the Biology and Ecosystems Panel. This designation recognized that long-term monitoring of sound in the ocean will yield information on ecosystem health, climate change, and the effects of human activity on the environment. The bulk of the current ocean acoustic data collection is performed by archival recorders, supplemented by a small number of real-time gliders, buoys and cabled observatories.
Twitch is a video live streaming service and a subsidiary of Amazon. Twitch primarily focuses on video game live streaming, broadcasts of esports competitions, music and creative content. Twitch clients upload their encoded video to Twitch’s servers. The user generated content (UGC) is then transcoded. Transcoding is the process of decoding UGC, making alternations to it, and then encoding it again. During transcoding, video will be encoded at a lower bit rate or its resolution might be lowered.
In recent years, an increase in industrial robots in manufacturing has emerged. However, there are still possible safety issues and difficulty in specifying tasks for the robots to perform. The objective of this research project is to make a path planning system that uses demonstrations of how to perform a task to learn how to perform the task using techniques from the field of machine learning. These demonstrations will also show the robot how to move in the workspace safely and without entering collision with items in its surroundings.
Rail transit and freight rail properties apply rail grinding to maintain rail condition and ensure satisfactory performance of rail infrastructure systems. The proposed research investigates and applies a variety of computationally intelligent algorithms to establish useful relationships between rail corrugation, noise generation, and vibration. These relationships will support more timely and effective rail grinding interventions. The algorithms will process real-world rail corrugation, noise, and vibration data collected from three rail transit properties in North America.
This project aims to propose a novel fifth generation (5G)-enabled machine learning based edge computing solution for the optimal energy and space management of smart buildings and implement it in hardware to validate its performance. The proposed solution exploits the energy and space management databases, enriched by the emerging advanced sensor technologies and 5G wireless communication networks in smart buildings.
The proposed initiative is different from conventional small molecules or biologics therapies. The living “drugs” are patients’ own immune cells. However, due to factors, such as age, and genetic differences between individuals, there is no magic “one treatment for all patients”. Intrinsic interpatient heterogeneity requires “personalized immune-therapy”. We have to adopt a “quality control” when we re-engineer immune-cells.
As very large scale integrated circuit (VLSI) technology progresses, power consumption and power density of VLSI circuits increase when design complexity and transistor density increase. Low-power design becomes a major design challenge. Lowering the supply voltage is one of the most efficient ways to save power because power consumption is proportional to the square of supply voltage. Electronic devices are expected to operate at much a lower supply voltage than traditional designs, which is very useful for portable electronics and biomedical implants.
Canada population is getting older as the baby boomers enter their retirement years and the current models for communal care will not be able to scale to meet the demand and continuing to age in place and live independently is preferred leading to the best quality of life and outcomes. The recent COVID pandemic experience has made some of the challenges in communal care and provision of remote care clear.
XLScout is a startup engaged in democratizing innovation and connecting research and development with intellectual property (IP) departments across the world. The company is developing proprietary algorithms, using Artificial Intelligence and Machine learning, to mimic the behaviour of an expert searcher.
XLScout hosts a data vault of about 130+ million patent documents which occupies approximately 8TB of storage. Searching such documents is a cumbersome process requiring extensive effort, time and strategies that a novice searcher might not be aware of.
The objective of this research is to create a data architecture and a state-of-the-art machine learning algorithms to build a robust user-profile system that (i) extracts, stores, builds, and analyses synchronously up to 1 million user profiles generating at least 50 behavioral data (alpha-numeric value of 64 bytes) per second, (ii) provides over 5 millions user-profile recognitions per day through predictive modeling and REST API call, (iii) authenticates continuously to detect suspicious activities and anomalies without using cookies, location, and hardware information, and (iv) tolerates ef