Innovative Projects Realized

Universal Soldier: A deep neural net for unsupervised 3D segmentation of tomographic images of bones

The process of identifying the object in an image, and the object background is accomplished by the human brain instantly. We develop such skills with experience, and often take it for granted. In digital imaging and computer vision, the same operation called image segmentation is a bottleneck of quantitative analysis. In particular, automated image segmentation is difficult in 3D, and especially so when the object is of biological origin. Automated segmentation of 3D datasets would abolish these limitations and increase the precision of quantitative image analysis, with high throughput. A way to mimic the precision and accuracy of human visual perception is to train an artificial neural network on a vast variety of examples. We have accrued a big library of 3D images of bones and skeletons, and will train the Universal Soldier Neural Net to recognize, tag and quantify the image components.

McCol Metals International Market Expansion

At McCol Metals, we have developed an innovative process to recover metal elements and then sell them to the international market. Our innovative recovery process has created a circular economy for Mixed Metal Oxide anodes and provides sustainability to the global Platinum Group Metal markets. We have currently commercialized and secured a 5-year contract locally with Vale and have been able to target global customers who can benefit from the recovery process. Going ahead, we want to focus on growth and development in international markets in the regions of North America, Europe, and South America. This project will help us determine our options for expansion.

AI, IoT, and Cloud-Based Technologies to improve safety in the marine industry

With thousands of accidents annually, often resulting in hundreds of deaths and injuries, billions in economic losses, and devastating environmental pollution, the marine industry remains one of the most dangerous industries nationally and internationally. The work environment on ships is inherently risky and poses numerous challenges to the ship crew. Moreover, the nature of their work requires them to engage in different job tasks and responsibilities that are physically and mentally demanding in an environment full of risks. Human-induced risks on board ships are not well identified, assessed, or mitigated, leaving the ship crew exposed to a higher chance of getting into an accident. Furthermore, the industry relies on basic tools for risk identification and assessment that are tedious, time-consuming, and ineffective. To improve the safety issues in the marine industry, we are proposing a novel approach to risk management. This approach is based on a risk assessment methodology designed for the marine industry to meet its specific characteristics and unique risks through utilizing advanced technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and cloud computing to assess activities and risky circumstances.

Innovation en méthodologies internes de génie-conseil – Développement durable & Appels d’offres à l’international

Innovation en méthodologies internes de génie-conseil – Développement durable & Appels d’offres à l’international

Le but de ce projet est de définir des méthodes internes pour améliorer la réponse aux appels d’offres de projets à l’international pour l’organisme partenaire, EXP.
Des équipes multidisciplinaires, des outils généralisés et des méthodes fonctionnelles sont nécessaires pour intégrer transversalement le développement durable dans des projets d’envergure, particulièrement dans le milieu du génie-conseil.

Exploring Innovations in the Japanese Robotics Industry

The intern aims to study the Japanese Robotics Industry by looking at several cases such as Ascent Robotics and analyze the advanced products that are produced by the industry. The intern will be studying the market performance, technological proficiency and other such parameters of products such as mobile manipulators that are produced by Japanese startups. Through this, the intern aims to identify strengths and weaknesses of the industry and identify transferrable successful attributes to the Canadian Robotics industry and start up culture. Such a project will allow the partner organization in helping Canadian students and innovators to launch successful technological startups.

Historical and future variability of wind and solar energies in Alberta and Ontario.

Wind and solar sources are important in the generation and supply of energy in a clean and renewable way. The potential for renewable energy generation in Canada is well-known and is projected to be a leading industry over the next years by power generation companies like TransAlta Corporation. The purpose of this project is to explore the climatic variability and drought occurrence of wind and solar energies in the provinces of Alberta and Ontario through historical data obtained from ERA5 datasets. This research will assist the decision-making of TransAlta in terms of exploration of the historical and current variation of renewable sources and diagnose the potential of projects managed by the company.

Marketing Strategy for B2B Launch

Development and execution of a robust marketing strategy for Clavis’ B2B platform.

Optimization of the detection of mycotoxins in plant material using LCMS

Mycotoxins are acutely toxic compounds produced by fungi when they infect food crops such as grains and cereals but can also be found in cannabis flower and products. These compounds are known to cause cancer and kidney failure when ingested and are therefore closely regulated by Health Canada. There are 4 main mycotoxins that are tested for and must be below a certain threshold value before these products can be sold. The accurate and sensitive detection of these compounds in cannabis is difficult due to the complexity of the small molecules that are also extracted from the plant when trying to isolate mycotoxins. This project aims to produce and reliable and accurate method for the quantitation of these compounds that would ensure the safety of cannabis products.

AAI: Optimal Postal-Code Level Customer Acquisition

The customer acquisition strategy for an organization is most effective if informed by insights into which customers would provide the most value, how much it would cost to acquire those customers, and what is the probability of success for acquiring a particular customer. While it is not tractable to do such analysis at the individual level, there is a desire to analyze the questions surrounding customer acquisition at quite low levels of granularity, for example, at the postal code level. Deloitte has created a solution called Acquisition AI which takes a first step toward intelligent customer acquisition by offering a model to forecast the probability of acquisition success by postal code.

Development of chemically modified probes for robust molecular diagnostics

The COVID-19 pandemic has highlighted the public need for molecular diagnostic tools to identify pathogen panels through nucleic acid amplification tests (NAAT). Many clinical labs worldwide have now established infrastructures for routine molecular assays using classic quantitative PCR (qPCR). In order to further advance this – now routine – tool for in vitro diagnostics (IVD), it has become imperative to develop underlying technologies for robust, specific, and sensitive detection of pathogens, namely next-generation oligonucleotide probes. Hence, this project introduces a novel strategy for the development of chemically-modified probes based on intercalating nucleic acids (INAs) and DNAzymes. Discovery of optimized probes is accomplished through identification and selection from candidate pools through “DNA encoded” tags or barcodes. Resulting probes should in turn be compatible with existing workflows and qPCR instrumentation for fluorescent signal detection of a pathogenic target-of-interest or multiplex target panels, such as respiratory or gastrointestinal gene panels.

Understanding the Rise of the Asian Tech industry: Innovation and Best Practices

The project will investigate through first-hand experience how Asian technology firms ideate, develop, debug, test, and ship their software products. The methodologies in Asia can be very different from Canada’s software industry, in which some segments still use outdated development practices. The projects main deliverable to the partner organization (The Cansbridge Fellowship) will be a detailed report on Asia’s, specifically Japan’s, software development methodologies. Cansbridge will also benefit from having an expanded Asian business network to share with Canada. The second part of the report will highlight the key differences between Canadian and Asian software practices. The intern will bring these new perspectives back to the Canadian technology industry, bringing in new ideas to combine with our own to make Canada a stronger player in the technology industry,

Optimisation of an radiofrequency electron source input coupler

The CLS uses a high energy electron accelerator to produce synchrotron light for user experiments. This project is to design and construct a part for a new radiofrequency electron source that is being installed at the CLS in a new electron source lab. The part needs to be designed to produce very high gradient electric fields for a new type of electron source that is being developed as a future electron source for the CLS. The project will involve make computer simulations of high power radio waves to design the component dimension, then construct a low power prototype in the CLS workshop for testing on the workbench with electronic test equipment.