This project aims to use machine learning to determine the thermal state of a battery pack used in electrical vehicles. In fact, battery pack are made of numerous individual cells, and it is essential to monitor their respective state to ensure the battery pack operates in ideal conditions. By doing so, the autonomy of the […]

Le traitement des surfaces est une pratique courante dans l’industrie manufacturière afin d’améliorer les propriétés mécaniques des pièces. Cette technique est particulièrement exploitée dans l’industrie automobile, où les surfaces de pièces risquent d’être endommagées. Les traitements couramment utilisés sont souvent complexes, aléatoires et dommageables pour la surface traitée. Le traitement par laser est ainsi une […]

The proposed work combines artificial intelligence and diagnostic medicine. Using X-ray images, radiologists and veterinarians can perform an array of measurements to assess patient health. In a veterinary setting, standard measurements and annotations are performed on X-ray images to assess heart and knee health in canines, namely vertebral heart score (VHS) and tibial plateau angle […]

As an online business, Spärkel relies on data to adapt and improve all business strategies. Covid-19 forced many retailers and competitors to expedite their investments in online capabilities. This poses a challenge to Spärkel’s competitiveness. Using the Advanced Reporting Intern will allow the company to gain better insight into the performance of business strategies. In […]

La federation des prodecteurs de lait du Quebec regroupe tous les prodecteurs de la province et negocie en leur nom, avec les transporteuts des contrats de transport. Ces contrats specifient dans quel ordre seront collectes les prodecteurs ainsi que le tarif a verser. Ce projet consiste a developper un outil d’aide a la decision permettant […]

Les résidus de la Mine Raglan contiennent des minéraux pouvant réagir avec l’eau et l’air et potentiellement produire un drainage acide et riche en métaux s’ils ne sont pas gérés d’une manière optimale. Des essais au laboratoire ont permis de déterminer la qualité d’eau qu’ils produisent et leur comportement géochimique. La présente étude vise à […]

With improvements in photovoltaic performance and price drops, solar energy will soon become cheaper than many traditional sources. Irradiance-the amount of solar energy reaching the Earth-is key In feasibility studies of solar energy systems. Over 20 years of archival satellite imagery enable us to generate long-term data series to better understand climatic averages of irradiance. […]

This project aims to design an embedded system to enhance human speech in noisy industrial environments to boost automatic speech recognition (ASR) performances. Speech recognition is desirable for workers to log information in the system without using their hands, which improves productivity significantly. In this project, the system will learn to remove the ambient noise […]

The covid-19 pandemic has greatly affected SpÃrkel’s supply chain. Slower manufacturing in China and busy shipping routes will make stock-outs and fluctuating supply levels common for the foreseeable future. This is pushing SpÃrkel to adapt and invest in long term marketing strategies such as Public relations and influencer marketing for which the intern will research […]

Located in Montréal, Canada, Nanogrande is a pioneer in the high-precision metal additive manufacturing market and the premier Canadian metal 3D printer provider. To solidify their unique market position, it is key to increase their deposition process expertise and explore technologies for process performance improvement and added value proposition. The proposed project aims to support […]

Avec les progrès prodigieux des dernières années en matière d’agriculture de précision, ce projet apporte une solution originale à la problématique de la détection automatique des mauvaises herbes ainsi que leur éradication dans les bleuetières de bleuets nains (sauvages). Le principal objectif de ce projet consiste à développer un système robotisé autonome capable d’effectuer la […]

This research is carried out on the topic of natural language processing and specifically on word representation on Question Answering tasks. The state of the art in Question Answer task is Google’s Bidirectional Encoder Representations from Transformers (BERT) language model. Koïos Intelligence is interested in fine-tuning this model for their closed domain artificial intelligence (AI) […]