Machine learning has been applied in various fields and shown promising results in recent years. Researchers have found that tuning machine learning models in a proper way can vastly boost the model performance with respect to the specific AI task. However, tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming. There is therefore great appeal for automatic approaches that can optimize the hyperparameter of any given model.
The recent outbreak of the SARS-CoV-2 associated coronavirus disease, COVID-19, had been declared a global pandemic by the World Health Organization. There is still only a minimal understanding of the virus and an absence of effective targeted therapy for its treatment. Epigenetic regulations in cells control the expression of genes without modifications to the genetic codes itself, and epigenetic-targeted therapy development had been widely proposed as a promising approach to antiviral therapeutics.
As smart home and artificial intelligence technologies are developing rapidly, smart home devices contribute to better living quality and safer spaces. These smart devices are intelligent agents. They receive a variety of signals through sensors placed in ecobee’s thermostats, light switches and other smart devices and controls the heating and cooling, lighting, as well as providing important notifications. In this project, we would like to analyze sensory data and develop various machine learning solutions for characterization of the devices’ environment (e.g.
Ontario’s Greenbelt is composed of nearly 2 million acres of protected land including natural areas that provide ecosystem services to millions of people. While these areas face reduced pressure from land use conversion, they still face a pressures typical of natural systems in peri-urban landscapes including loss of biodiversity, invasive species, impacts from infrastructure projects and a changing climate. In order to determine the extent to which these pressures are shifting natural systems, indicators of system health are needed.
COVID-19 pandemic has brought the world to standstill with more than 3 million people infected and more than 200 000 mortality so far. It has literally brought the health care systems in many countries to the breaking point, if not beyond. The economic consequences have been devastating with millions of people out of work. We are taking a novel approach by focusing on two SARS-CoV2 (COVID-19) methyltransferases that are essential for viral replication. Both enzymes (nsp14 and nsp16) are druggable.
With the advancement of modern technology, especially the increase in network speed, videos are taking more and more important places among media types. With vast potential applications, video recognition has received great attention. However, video recognition is a non-trivial task: a lot of training data are needed for complicated neural networks, but annotated data are hard to acquire. As a result, there is a growing tendency to bank on self-supervised learning approaches that can make use of unlabeled data.
SOTI has developed a software product called SOTI SNAP that allows anyone to create an app with no programming or technical knowledge. The goal of this project is to develop media scheduler widgets so that users can create playlists consisting of mixed media (videos, images, documents) and then deploy them at specific hours on certain days.
Implanted medical devices have dramatically improved the lives of millions of patients worldwide. However, in many cases, the body’s immune system rejects these devices and encapsulates the implant in fibrous scar tissue. This reaction is most detrimental to sensors for continuous monitoring and treatment of chronic conditions such as diabetes and those of the central nervous system. Device functionality is usually severely limited and risky additional surgeries for implant removal and reinsertion are required.
The emergence of viral pandemics, exemplified by the Coronavirus Disease (COVID-19), has exposed the urgent need for the development of viral infection therapeutics. In a short span of time, more than 1.5 million individuals have been infected and there have been nearly 90, 000 deaths worldwide. Our objective is to pharmacologically validate a new strategy for viral infection therapeutics by designing molecules that inhibit HDAC6, a protein implicated in viral entry.
Global service providers in highly regulated financial sectors must accommodate an ever-changing, sometimes competing, landscape of regulatory concerns. This project seeks to determine a reasonable path forward in technology design and adoption to accommodate current and anticipated infrastructure changes. Moreover, bridging the service layer across multiple, distinct distributed systems of varying complexity will pose new challenges while performance and observability of these systems become critical consideration.