Projets novateurs réalisés

Biochemical analysis of a lysosomal integral membrane protein

Lignin – the key to a more efficient use of biomass?

Energy from hydrogen, research for future mobility

Drying in Fluidized Beds

Multimodal (MR-PET-EEG) Neuro-Imaging

Human Trafficking: A Review of Germany and Canada

The proposed research is to study the policing and secularity methods used by the Canadian and German governments to combat the illegal trafficking of humans within and without sovereign nations. The current application of the Canadian justice system against trafficking has yielded alarmingly low conviction rates. Findings in Germany will stand as a comparison to the system in Canada. The goal of this comparison is to gain an understanding of what is needed to develop a stronger and more robust system in Canada.
The research is expected to draw parallels between the two systems and find areas that need improvement. This will lead to a publication that will add to the exceedingly thin literature surrounding the subject of human trafficking in Canada.

Machine Learning for categorizing women’s health risks

This research project deals with categorizing women belonging to different developing countries into different health risk segments and sub segments and subsequently analyze patterns of diseases/infections in various geographical regions accordingly by using Optimized machine learning approach. XgBoost algorithm would be implemented to achieve this goal among other existing algorithms as this offers better model efficiency and performance. Efficient implementation of these programs, would not only improve health outcomes, but could save time and money for health organizations and practitioners. Furthermore, this platform could be used to create automated customized awareness programs for patients (for both male and female). This will aid policy makers in designing specific programs and policies to address women’s health in developing nations.

Implementation of the technology for Continuous Long-term Monitoring of Pregnant Women for Safe Childbirth

This research explores the concept of Internet of Things and how the current technology of smartphones can be used to improve the continuous health monitoring of pregnant women across the globe. A very convenient and cost-effective system has been proposed to ensure a completely non-invasive way of collecting the biometric data of pregnant women and sending it remotely to the expert health practitioners, thus enabling routine health checkups at the comfort of their homes. Precisely, we focus on the first 500 days of life which refers to the time between conception and about 6 months after delivery. Pregnant women and their babies are exceptionally susceptible to medical emergencies during this period. Timely medical attention is important to prevent health complications and ensure that babies develop properly. An iOS application will be used for transmission of information and communication between patients and their doctors. TO BE CONT’D

Amazon Alexa for antibiotics interaction guidance system

Antibiotics are used to treat bacterial infections. Interactions between certain antibiotics and medicines may cause side-effects and decreased effectiveness of antibiotic therapy. Quite often, the prescription consists of multiple antibiotics to treat infections caused by different kinds of bacteria and it requires thorough knowledge of the interactions among these antibiotics and other medicines. For example – Cephalosporins may increase the chance of bleeding if taken with blood-thinning medications such as heparin and warfarin, which can be life threatening in certain situations. Current technology advances such as Amazon Alexa (intelligent personal assistant) can be programmed to assist physicians and patients with understanding drug interactions within an instant, rather than having to look it up on the Internet or in a medical guide. A database with Information on the antibiotics and their adverse reactions with each other will be mined from the Johns Hopkins Antibiotic Guide will be created. TO BE CONT’D

Grants Management Software: Evaluation of Adoption of GrantsManagement Software Amongst Government Agencies and Non-Profit Organizations

As a grants life cycle involves many steps, it is crucial for grantmakers to monitor and

manage the process. While digital management offers efficiency, multitude of clients and

solutions they require results with highly fragmented market. By identifying the stakeholders

in grants management marketplace and by assessing their needs, software vendors can

become more competent in designing solutions that are suitably tailored for clients . By

conducting a competitive analysis of industry with regards to vendors, grantmakers,

government and clie nts, all parties will have a comprehensive understanding of how effective

to adopt software to grants management functions.

Research for Innovative Mining Methods

Narrow-vein steeply dipping deposits are challenging to mine economically because they are poorly oriented for surface mining, and underground mining normally requires development of extensive underground infrastructure before mining the vein. Memorial University is currently collaborating with Anaconda Mining for the development of innovative narrow-vein mining (NVM) technology to mine several of these deposits currently held by the company e.g. the Romeo & Juliet Deposit. The research proposed in this MITACS Accelerate Cluster will fund graduate students and post-doctoral fellows to investigate numerous aspects of the proposed narrow-vein-mining method. The proposed research activities and internships will be done by a multi-disciplinary team of graduate students, post-doctoral fellows and faculty supervisors with backgrounds in several engineering disciplines (mining, drilling, mechanical, electronics and civil) and earth sciences (geophysics).

Visual Recognition for Large-Scale and Weakly-Labelled Video Data

The main objective of this project is to investigate, develop and evaluate state-of-the-art computer vision and machine learning techniques, which are suitable for accurate modeling and recognition from large-scale video datasets that are weakly labeled. In particular, we will focus on the learning of visual recognition models for an application area of interest to SPORTLOGiQ Inc. – person re-identification for monitoring and tracking of player, activity recognition and group behavior understanding, and player and team performance evaluation in sports games. Learning recognition models in such cases typically leads to complex and ill-posed optimization problems, where video data sets are weakly-annotated. The recent years have witnessed substantial technical advances in areas such as deep learning (e.g., convolutional and recurrent neural networks), transfer and weakly-supervised learning, information fusion and distributed optimization, which promise to address such complex visual recognition problems, previously thought intractable. TO BE CONT’D