Test and expand the capabilities of the Zetane software for application in complex artificial intelligence industrial (AI) projects with the objective of augmenting the users’ ability to gain new insights in model performance and gain more trust on how the data influences the AI models to arrive at the AI’s recommendations.
The objective of the project is to automate the detection of pavement defects. Defects can be of different types: cracks, deformations, potholes and others. These defects are cataloged and detailed in standards established by the Quebec Ministry of Transport in Quebec and various authorities in other regions of the world. At present, the inspection of pavement defects (e.g. potholes, cracks, ruts) is mainly done manually. Inspectors crisscross the roads or scrutinize images taken from inspection vehicles.
Existing data lake systems lack the support for storing or discovery features that could be used with different ML projects.
These limitations negatively affect the process of decision-taking. Data scientists spend most of their time finding, preparing,
and integrating relevant data sets to finish analytics tasks. Feature discovery systems are needed to ease the process of building
data science pipelines to drive significant insights efficiently, effectively and fairly.
As Internet usages are proliferating communications networks are faced with new shortcomings. Future networks will have to support in 2020 mobile traffic volumes 1000 times larger than today and a spectrum crunch is anticipated. Wireless access rates are today significantly lower than those of fixed access, which prevents the emergence of ubiquitous low cost integrated access continuum with context independent operational characteristics. Communication networks energy consumption is growing rapidly, especially in the radio part of mobile networks.
Recent increased enthusiasm towards Computer-Integrated Manufacturing (CIM) coupled with developments in smart sensor technologies and advances in communication systems have resulted in simultaneous incorporation of several advanced monitoring and sensing technologies within manufacturing and industrial sectors.
The increasing frequency of flooding has driven research to improve near real-time flood mapping from remote-sensing data. In Quebec, in
the spring of 2017, several regions experienced severe flooding caused by consecutive record-setting rain events during snowsmelt from early
April to mi0-d-May. The current project aims to provide real-time monitoring tools not only for flooding but for drought as well, i.e.,
visualization and simulation tools using both remote sensing data, but also data collected from an Internet of Things network.
The main goal of this project is to develop an artificial intelligence based approach for recommendation to improve Videotron marketing solutions. We aim to focus on improving Vidéotron return on investment (ROI), engaging more users and retaining subscribers using advanced artificial intelligence techniques. The proposed system will be based on a collaborative filtering technique that involves state of the art deep learning and reinforcement learning techniques.
In Canada, approximately 1 in 4 adults are living with obesity. Obesity is cause by a complex interplay of genetic, behavioural, and environmental factors that can increase the risk of developing non-communicable diseases such as Type 2 diabetes mellitus, coronary heart disease, asthma, several cancers, and disability in adulthood. Restricting caloric consumption and increasing physical activity levels are used in efforts to induce weight loss. However, using these methods alone may not be sufficient in sustaining long-term weight loss.
The ubiquity of smartphones and their embedded technologies today can provide transportation agencies with affordable travel survey methods which place less burden on respondents and enables collection of continuous, high quality travel data. Such technologies, however, have not yet made the leap from speciality tools of academia to industry, primarily due to the specificity of domain knowledge required to produce useful information and gaps in the literature due to the difficulty of implementation.
The adequacy of hospital nurse staffing in Canada is essential for the delivery of quality health care to Canadians. In light of permanent nursing staff shortage in most of Canadian hospitals, using of supplemental nurses to bolster permanent nursing staff is widespread. Having suitably qualified staff on duty at the right time is a large determinant of service organization efficiency in providing continuity of care. On the other hand, attractive schedules are an important factor leading to successful recruiting and retaining valuable nursing personnel.