Estimation of Disease Severity in Rice with Deep Learning Neural Networks

NIRS is a popular secondary analytical method that is being used for non-destructive quantification of compounds and mixtures in the agriculture and agri-food sector. The study aims to estimate the starch content (amylose and amylopectin) in rice samples with NIRS. A dataset is being established by obtaining NIRS spectra (400 to 2500 nm, 0.5 nm resolution) on over 400 milled and ground rice samples. Iodine-binding and spectrophotometric techniques will be used for acquiring the ground-truth.

A Sustainability Evaluation of Post-harvest Fisheries Opportunities for First Nations in Nova Scotia

Many First Nation communities are now exploring and developing post-harvest livelihood activities related to the purchase, transformation, and sale of catch from band harvesters. This research will assess post-harvest businesses currently operating within NS Mi’kmaq communities, and new livelihood opportunities currently being considered by Mi’kmaq Band Councils and entrepreneurs. This assessment will focus on the overall sustainability of the fishery operations, including social, economic, environmental, and cultural factors, among others.

Optimization and validation of collagen fiber manufacturing

Natural biomaterials such as cotton, wool and bamboo are common biofibres due to their accessibility and high performance characteristics in textiles. However, their strictly defined composition is severely limiting, as the materials cannot be adapted for alternative uses. Thus, producing biomaterials at an industrial scale has been an active area of research, where the goal is to create materials found in nature at a high throughput.

Using/An application (with) Artificial Intelligence in Telemedicine and Telehealth

There is a fact that over the last decades life expectation is increased, and human nation is experiencing a longer life span. The idea is to utilize technology in a way that people (senior or patients) can stay at their own home with less care facilities and less life quality degradation with less third-party assistance. In this research, I will be conducting a series of researches in which I can model seniors'/patients' behavior while they are home so we can have a better insight from their behavior, their patterns/trends of their habits.

Integrating multiple deep learning models to track and classify at-risk fish species near commercial infrastructure

Companies must not harm species at risk around their fixed infrastructure and need a way to detect and monitor at risk fish. However, a species at risk cannot be tagged and studied using conventional surgically implanted fish tracking technology. Innovasea is therefore developing a platform to monitor fish using a combination of sensors such as acoustic devices, visual and active sonar and optical cameras. This effort requires a robust accurate method to detect fish and classify them by species.

Aerial drone to perform adaptive in-water sampling in marine environments

In-water measurement and sample collection solutions for environmental marine monitoring will be studied. Fine-scale responsive measurements cannot be achieved cost-effectively with satellites or aircraft. For near-surface monitoring, an unmanned aerial system (UAS) could achieve the necessary spatial-temporal sampling.
The proposed solutions deploy a payload sensor and/or sample grabber from an UAS with a winchable tether. However, the winch and tether can impact the UAS dynamics.

AI Optimized On-Board Computer for Edge computing in Aerospace Applications

Space systems such as small satellites and rovers operating in earth’s orbit, or more recently in interplanetary missions are starting to utilize the features of Artificial Intelligence (AI) in their designs, to reduce human interactions, minimize error and preserve communication bandwidth. AI in space applications can be seen in service vehicles, autonomous image and signal processing, Earth observation, telecommunication and surveillance.

Can targeting substance misuse risk in university students be an effective strategy for injury prevention?

The proposed research project is a novel addition to a larger funded trial evaluating a substance misuse intervention program for university students, Univenture, that is being carried out at five universities across Canada. The postdoctoral project is experimental in nature and aimed to investigate whether the personality-targeted psychological intervention for substance misuse also results in reduced risk-taking behaviors and physical injury among 1st and 2nd year university undergraduate students.

Well-being in Nova Scotia’s communities: Applying a community well-being framework to track provincial health

Engage Nova Scotia currently holds the most information on Canadian’s well-being in one place, both in terms of number of Canadians and the content of the information. Drawing from the Canadian Index of Well-Being framework, we are able to compare well-being between communities in Nova Scotia to better understand what helps or hinders a high quality of life. This project will focus on analyzing the well-being data and developing infrastructure within the organization to build on this research.

Optimizing Wall Formwork Shuttering Design Using Prefabricated Panels in Concrete Construction

Determining an optimal formwork shuttering solution is not a well answered problem, relying heavily on the designer’s preferences and past experiences rather than efficient algorithms and standardized procedures. This results in inefficient solutions that increase overall costs and construction time. Globally, formwork is nearly a $6 billion USD/ year industry; even minor improvements in efficiency of design will result in huge cost savings.

This research aims to develop a standardized methodology and identify general heuristics for solving typical wall formwork problems.