Projets novateurs réalisés

Animal identification and emotion detection using deep convolutional neural networks

According to a recent report, when it comes to animal protection laws Canada has not been performing adequately, receiving a grade of “D” on the Animal Protection Index (API). The low marks received were for not having adequate legislation protecting wildlife in captivity, working animals, farm animals, animals used in research and companion animals. At the same time, public support for improving animal welfare is high. In an effort to address this, we propose mobile application to identify animals and understand their emotions, which will utilize state-of-the-art convolutional neural networks. This solution will have a wide range of applications such as assisting in finding lost pets, preventing undesired animal trading, diagnosing emotional wellbeing of animals, and helping humans and wildlife to coexist by allowing humans to identify individual animals that frequent their communities or properties.

Smart handheld device for automatic blood analysis: Innovative prediction of livestock pregnancy and litter size

Have you ever done a finger prick to get a few drops of blood to test your glucose level using a handheld device? Or taken a “bed-side” pregnancy test using urine and a device at the palm of your hands? We’re planning to follow the same model and develop a device that can detect pregnancy and litter size in sheep. This is a novel device in the livestock industry and can provide results within minutes. The producers would have to collect a few drops of blood (probably from an ear prick) from the sheep, get it to the detection device, and get the result on their phone.

Bridging the Gap: A Research Evaluation of a High School to Post-Secondary Preparatory Program for At-Risk and Underrepresented Groups

Mathstronauts’ NEXUS Program is a 12-week program in which grade 11 and 12 students from underrepresented groups gain fundamental technical skills in the areas of STEM (Science, Technology, Engineering and Math) and soft skills (time management, note taking, etc.) to support their transition into post-secondary education. To investigate the impact of this intervention, our intern will use surveys and focus groups to identify the feasibility of the program in an online format, the short-term impacts of this program on the technical and soft skills of participants, and the long-term impacts of the program on post-secondary attitudes and decisions six-months after program completion. These assessments will contribute to a final NEXUS Program report which will be used by Mathstronauts to inform future improvements on the program. Additionally, the report will be a tool for school boards, community organizations, and research institutions to make similar programs widely accessible to students.

Towards Automated Recommendations for Taxonomy Expansion

The partner organization is building a knowledge graph to integrate the knowledge in the SharePoint documents/pages of each domain, which will be used as the central information base to support various information retrieval tasks such as intelligent chatbots that can automatically identify relevant information. A critical element of the knowledge graph is a taxonomy of the entities (keywords) extracted from the SharePoint documents/pages, which can enrich the relations between the entities. However, with the explosive increase of entities, maintaining the taxonomy becomes beyond the capacity of the taxonomists. Thus, this project aims to develop a prototype tool to assist taxonomists in expanding the taxonomy with new entities. The tool accepts a new entity as its input, analyzes its relationship with the existing taxonomy, and outputs the recommendation for how to integrate the entity. The tool is expected to save the analysis time of the taxonomists by 50%.

Communicating outcomes of future what-if scenarios for municipal climate action

This project communicates interactive cross-sectoral data about how municipal planning policies related to urban form may address both climate action and urban livability. The research generates numerous measured future what-if scenarios for neighbourhood-scale changes to population, population density, built form, building energy, mobility, urban greening. This project addresses a problem of communication by designing and delivering an interactive visually accessible dashboard to communicate the results of the research to planners and their constituent audiences- the public and elected officials.

Presence of SSAT-1 as a marker for early diagnosis and monitoring of cancer

Cancer is one of the leading causes of death worldwide. In Canada, cancer accounts for 30% of all deaths, and half of all
Canadians will develop cancer in their lifetime. Many cancers can be prevented or controlled through early detection, but the
availability of such tests is scarce and a reliable general biomarker for different types of cancers has not been yet discovered.
Moreover, cancer survivors are at greater risk of developing a second cancer, and affordable and safe monitoring for the rest
of their lives is not available. We propose the development of serological and qPCR tests for early diagnosis of cancer based
on the presence of SSAT-1.
Since the technology will be used to screen for early-stage cancers, it is a life-saving approach, and therefore of clear social
benefit to Canada. The health benefits to Canada in developing reliable and cost-effective early cancer detection and screening
devices will assist the Canadian medical community and patients at large. Early detection and screening save lives and costs
that burden the medical budget. Also, this methodology is beneficial to monitor populations at high cancer development risk,
such as smokers, industrial, and occupational workers.

Characterization of a novel humanized monoclonal antibody specific to VEGF-C: Impact on lymphatic metastasis in cancer

Cancer cells can travel to distant sites through the lymphatic system; this system is similar to a network of pipes within the body that carries fluids and cells to all organs. The metastatic spread of cancer cells through this network is one of the reasons why this disease is so difficult to stop. We are working with Kalgene Pharmaceuticals to test a new compound that can impact the lymphatic system. The hope is to block this network and thus stop metastatic spread thereby improving patient survival. We in partnership with Kalgene will provide the scientific and technical expertise in order to push this new compound to the clinic.

Ideal growth conditions for optimal nutrient content and yield in companion crops grown in vertical farming

Just Vertical builds, sells, and supports indoor growing gardens and farming modules. Indoor vertical farming is becoming more popular but is currently limited by the varieties of crops that can be grown and subsequently, the nutritionally density of those crops grown indoors. Building on the first research project between Just Vertical and Seneca in 2020, this project will produce recipes to effectively grow nutritious, high-yielding crops in AEVA units using conditions that optimize the growth of a variety of
crops grown at the same time.
The Seneca research team will develop methods for crop nutrient analysis, perform chemical analyses, and make recommendations to Just Vertical on optimizing food growth and nutrition. The project will also evaluate how common growing mistakes can affect crop yield and nutrition. These results will be implemented by customers through proprietary growth recipes, which will give Just Vertical a competitive edge to attract new customers and market share.

Data & Reporting Analyst

Learners.ai is pioneering the application of a new approach for financial services and eCommerce firms to scale their products/services and accelerate revenue using a data-driven approach. The project “Scalable Reveune Operations for Learners.ai” is aimed at implementing the go-to-market strategy for a scalable Revenue Operations service created by Learners.ai after successfully delivering results several clients.

An Enhanced Micro-Suspension System

VueReal is currently developing LED technology that requires transfer of devices during fabrication to other sites. However, these devices are fragile. During the transfer process, an unacceptably large number of devices are damaged due to failures in their suspension systems. This reduces the fabrication yield and therefore increases production cost. It is not obvious whether these failures arise due to temperature variations, shocks during transportation, or other reasons. This project aims to address this challenge and propose directions for further development.

The objective of this project is to propose a solution that will alleviate device failures during transportation. The first step in the proposed approach is to model and simulate the device and its suspension system using Finite Element Modeling and to carry out thermal and structural (shock) analyses on the model. This will allow us to identify the root cause(s) of those failures. We will then re-design the suspension system in order to address those causes. Different solutions will be developed, simulated, and validated. Finally, a candidate solution will be proposed.

VueReal is a Canadian leader in Micro-LED technology.

Developing a Field Deployable Assay System for Environmental Monitoring

There are currently over 9,000 potentially contaminated sites in Canada that require environmental assessment. The Field Deployable Assay (FDA) is a simple and cost-effective method for performing accurate environmental monitoring and site assessments. The FDAs are composed of a stationary main body and a variety of interchangeable cartridges. These cartridges act as miniature greenhouses, easily allowing for the monitoring of the growth of plants and fungus over an extended period. Based on the rate of seed germination, seedling growth and plant-fungal interactions, the degree of contamination of a site can be determined. The goal of the research is to refine the existing cartridge models as well as developing new models. New species will also be added to the list of suitable candidates that can be used, allowing for more robust environmental assessments.

Promoting BEST (BEtter, Faster, Longer, STronger) Walking for People with Parkinsons

This project aims to improve how people with Parkinson Disease (PD) walk. Typically, people with PD develop a shuffling gait and limits walking for health and fitness and can also lead to falls and fractures. This project is based on a SMART sensor, Heel2ToeTM, that attaches to the outside of the shoe and gives a “beep” when the wearer makes a good step, one in which the heel is the first point of contact with the surface. Starting a step with a strong heel strike, changes a stooped shuffling gait to one that is upright and striding. The aim here is to make this technology as useful as possible. To do this, we will invite 100 people with PD to try the Heel2Toe sensor and give us feedback about their experience while we track their progress. According to Parkinson Quebec, there are 25,000 people with PD in Quebec and 3924 are registered with Parkinson Quebec.