Innovative Projects Realized

Mobile Data Usage & Signal Strength – Manage, Analyze and predict estimated data usage and signal strength to conduct automatic cause analysis using deep neural network and unsupervised learning techniques

Enterprise mobility management enables to collect various metrics from million of devices. This industrial research project focuses on identifying the key performance indicators and formulas to identify and predict coverage issues and identify data usage problems within a device. Using the key performance indicators, the intern will explore all feasible machine learning approaches. Final goal is to design an AI smart diagnostic system to detect the issue related to data usage and signal strength and conduct automatic cause analysis. This would allow the clients to act proactively by getting deeper insights in their mobile applications. The solutions aim to provide a data usage and signal strength diagnostic solution to help client avoid their business disruption due to issues in mobile devices. This will help the Canadian organization to minimize the maintenance cost while reducing downtime and minimal business disruption.

Transfert de données anonymes en mobilité à travers la « preuve à divulgation nulle de connaissance »

A-Malgam Technologies Inc. est une entreprise québécoise spécialisée dans le développement Blockchain et IoT pour la mobilité des données massives. Dans un souci d’offrir des solutions plus conviviales et sécurisées à ses membres-clients, A-Malgam souhaite explorer les capacités des technologies émergentes et ce qu’elles peuvent apporter lorsqu’il est sujet de transfert de données anonymes en mobilité. Le secteur des transports, et plus particulièrement celui de la mobilité des personnes, est un domaine où la diffusion d’équipements connec-tés, collectant constamment des données, est probablement la plus évidente. Avec cette démocratisation des systèmes connectés en mobilité, il devient de plus en plus important pour les intervenants de protéger la vie privée des citoyens. C’est afin de remédier à cette problématique que l’anonymisation des transferts de don-nées prend tout son sens. Malheureusement, les processus actuels de transfert de données n’offrent présen-tement aucun moyen viable pour lutter contre la problématique de traçabilité de transactions et sont le plus souvent vulnérables à plusieurs failles notamment la possibilité d’ajout d’émetteurs fautifs. Ce projet vise à créer un tout nouvel algorithme qui assure et certifie l’anonymat des données collectées.

Methods for the Estimation of Traffic Matrices

The accurate knowledge of origin/destination traffic matrices allows network operators to efficiently
perform network management operations to maximize network performance (minimize network
congestion, average delay, jitter, energy consumption, etc.) and increase network reliability in case
of device failures and other exceptional events. However, traffic matrices cannot be directly
measured, and network operators, such Videotron, can only rely on estimations based on the
elaboration of a limited amount of information, such as partial peak flow, link utilization, SNMP link
counts, multicast group composition and multicast trees. The aim of this project consists in
developing an efficient method for the optimal estimation of traffic matrices, when both multicast
and unicast traffic is considered. In this way Videotron will improve the performance of network
management operations that are crucial for the efficient functioning of the network.

Development of a solution to assess the quality and to optimize AI-based video codecs

Current video codecs consider algorithms to analyze video imagery in order to find out which bits can be removed for file size reduction without subjective video frame degradation. Integrating AI with encoding process improves the quality of encoding and decoding. AI permits the software to proactively assess the quality of the encoded video before transmission. This allows the compressing system to detect and remedy any possible artifacts in the video frames. The main objectives of the company regarding this project can be summarized as 1) Quality assessment regarding the AI-based video codecs from the industry perspective. 2) Determination of codec capability of running on off-the-shelf hardware. 3) Evaluation of AI-based codecs optimization techniques such as vectorization, SIMD, GPU, etc. The enhancement in such technologies could improve the entertainment industry in the country and also potentially assist smart city projects in Canada.

Automated Part Numbering for 3D Printed Medical Devices for Covid-19 Response using Generative Design Methodologies

Thousands of 3D printers across Canada are producing PPE for frontline workers. Different printers and materials affect the quality and safe re-usability of parts. Trying to track down this information for every single one of millions of parts would be impossible. The purpose of this project is to improve the quality and safe re-use of 3D printed PPE by developing a system for printing a unique identification code onto every single part that will let end users know what type of material was used and how and when the part was printed.

Dimethyl Sulfoxide (DMSO); A novel technique for gold recovery from mercury-contaminated tailings from artisanal and small-scale gold mining

The proposed research aims to optimize the use of DMSO as a lixiviant in gold recovery. To date, mercury and cyanide are the popular lixiviants used in the gold processing industry. These chemicals are harmful to both the environment and humans, and have been the major concern in gold mining. The proposed lixiviant, DMSO, is an FDA approved chemical that is cheap and environment friendly. The successful use of DMSO in gold mining is beneficial to the gold mining industry.

Upon the successful use of DMSO for gold leaching, Newlox Gold Ventures Corp, being the partner organization for the study, will have the opportunity to pilot the use of DMSO in gold leaching. The company also has the advantage of promoting the technique to other miners in the industry, as well as establish collaborations with local and national governments.

Enhanced Content-Based Similarity Detection for Book Recommendation

Recommendations is one of the main ways Kobo users discover content on the platform. By using purchase history, Kobo can suggest other books similar to a certain item. However, this does not provide meaningfulrecommendations in some cases, especially for bestsellers and fiction books. Currently, only for books that have no purchase history does Kobo supply recommendations based on text. The purpose of this project is to improve its text-based similarity analysis to provide better recommendations for all titles regardless of popularity and genre, as well as for all users who want recommendations that better reflect their purchases. Through this project, Kobo will benefit from an enhanced recommender system, and in effect, an improved customer experience and an increase in purchase conversion.

Characterization of antiviral coatings: Wetting studies and efficacy

There is an urgent need to develop antiviral coatings that would be applied to functional surfaces such as personal protection equipment (PPE) and others to arrest the spreading of COVID-19. In this project, the University of Waterloo researchers will work with industry partner, SiO2 Innovation Labs, to develop an optimal composition of such antiviral coating by characterizing the wetting and associated properties along with the efficacy of the coating against different viral loads. Once successfully achieved, the desired coating material will propel the industry partner in marketing their coating to large number of end-users and would eventually save millions of lives worldwide.

Developpement d’un outil numerique amallorant la versatilite des impulseurs en vue dereduire Ie nombre de pompes intermildiaires, et conception d’un plus gros impulseur pour les pompescentrifuges mult

Pour des constructeurs des pompes hydrauliques, la conception, la fabrication et la caracterisation des pompes
centrifuges presentent toujours un grand defi. Une meilleure fabrication de ce type des pompes exige une
determination avec precision de tous les parametres cies des composantes de la pompeo II s’agira, dans Ie cadre
de celie proposition de recherche, de developper des modeles numeriques fiables et precis d’impulseur de
pompe centrifuge permellant d’etudier de maniere approfondie les ecoulements complexes de liquide dans la
pompe, les contraintes, Ies vibrations, les poussees axiales et radiales induites, ainsi que la cavitation. Tout ceci
dans Ie but d’ameliorer les performances des pompes centrifuges etla versatilite des impulseurs disponibles chez
Technosub.

Development of paper-based Rapid Diagnostic Kit for COVID-19

Until an effective vaccine becomes widely available for COVID-19, a frequent home test of the coronavirus on a weekly basis might become a new norm. Therefore, developing rapid, accurate, stable, and cost-effective tests is critical for combatting the spread of COVID-19 over the long term. Aptamers are single-stranded DNA oligonucleotides that can be selected from a large DNA library to bind to many target molecules. They can overcome the problems associated with antibodies since DNA is highly stable, cost-effective with a little batch-to-batch variation. However, aptamer sequences for COVID-19 viral proteins are not yet available. Therefore, we aim to isolate such aptamers to fill in this gap. The industry partner, ChitoLytic will provide chitosan and other functionalized paper surfaces for paper-based biosensor development. They already have acquired a patented technology that demonstrated the detection of lipids on a paper-based microfluidic device. Chitolytic platform will be tested for our proposed aptamer-based detection of COVID. The expected outcome is a paper-based colorimetric assay using aptamers for specific binding of the COVID-19 virus in the saliva, thus aiming to develop the first paper-based biosensor for the detection of COVID-19 virus in the saliva.

Étude des systèmes de communication V2X pour l’automatisation des mines souterraines

L’industrie minières ne cesse de développer les moyens lui permettant d’améliorer à la fois la sécurité de ces travailleur et l’efficacité de sa productivité. L’usage des véhicules connectés et automatisés (CAV) représente la future étape transformatrice de cette industrie lui permettant d’atteindre ces deux objectifs toute en permettent à celle-ci de prendre le virage de l’industrie 4.0. Pour permettre au CAV dans leur version évoluée de voir le jour dans les mines souterraines, il est nécessaire d’analyser et de maitriser le fonctionnement des systèmes et des technologies de communication utilisées pour supporter les échanges entre ces véhicules autonomes, voir même entre ces véhicules et tous les acteurs évoluant dans leurs environnements. Il s’agit dans cette proposition de mettre en avant les connaissances requises pour l’usage des CAV dans en milieux confinés minier.

Integration of Data Mining into a Homomorphically Encrypted System: Enabling COVID-19 Researchers to Discretely Mine Sensitive Data

Krate Distributed Information Systems Inc. (Krate) and Saskatchewan Polytechnic (SP) are developing an advanced encryption module that will integrate with the distributed computer platform of fellow startup Distributed Compute Labs (DCL). DCL’s distributed computer is already functional and in use by scientists and researchers across Canada. This module will equip DCL’s distributed computer with the ability to process encrypted data without ever needing to decrypt it. It will also allow data to be publicly yet securely stored, computed, and transmitted without needing to ensure that the involved devices are trustworthy and secure. These will be accomplished by combining technologies like distributed systems, ubiquitous computing, blockchain, and smart contracts with encryption and other techniques. It will revolutionize data management, analysis, and cybersecurity because it is capable of conclusively ending the crisis of identity thefts and data breaches, and it offers governments, health providers, and health researchers the ultimate system for processing Personally Identifiable Information.