Innovative Projects Realized

Internet-based mental state monitoring using patient’s textual data

Among all chronic diseases, mental health issues have the highest burden on health care systems. However, unlike other chronic diseases, like Diabetes or hypertension, no monitoring procedures exist to monitor patients’ mental health status to prevent relapse and crisis situations. It is therefore necessary to develop cheap, convenient and accessible monitoring systems that could be used outside clinical setting. Most mental health diseases demonstrate a range of physical and behavioral symptoms (e.g. change in tone, posture and use of words, aka psychomotor symptoms) that could be measured using smart devices prevalently used by patients. Recent Internet-based methods of care delivery (eg online psychotherapy) provide the opportunity to utilize such digital evaluations of behavior (behavioral phenotyping) for long-term and remote monitoring of mental health status. Our proposal is to process digital behavioral data generated by the patients in an online platform (i.e. text, voice and video feedback) using machine learning approaches to develop an algorithm to predict their mental status. Furthermore, using recent advancements of deep learning in natural language processing, we are going to generate more personalized therapy content for patient interactions to improve the quality of the care.

A Reliable Lora based Tracking and Monitoring System for Underground Mines

The mining industry directly employs more than 426,000 workers across the Canada and contributed $97 billion to Canada’s GDP in 2017. However, mining workers are exposed to five-fold higher occupational hazards than the industrial average. Reliable underground communication is essential to alleviate incidents and escalate rescue operations. However, wireless communications in mines is a big challenge. Electromagnetic wave propagation is very poor in mines due to irregular confined shapes and rough walls. A recent wireless standard LoRa (Long Range) is promising in mine environments, due it’s, ultra-low power consumption, long range and deep penetration capabilities. This project aims to develop a unique and comprehensive monitoring and control system for underground mines using LoRa. It intends to develop a LoRa based tracking system that will use different range based techniques to estimate distance and apply advanced Machine Learning (ML) algorithms such as particle filtering, recursive neural networks or Kalman filtering on the estimated fingerprinting result to improve the accuracy. In addition, it will develop a medium access control (MAC) protocol to collect different mine data timely and ensure the Quality of Service (QoS) requirements. The outcome of this work will lead to significant improvements in miner safety and productivity.

Alignement strategique des technologies de I’information parI’utilisation de tableaux de bord

L’objectif du projet est d’ameliorer I’alignement strategique des technologies de I’information

(TI) au sein des organisations. Le projet se divise en trois objectifs principaux. Tout d’abord,

Les problemes rencontres par les entreprises dans la conduite de projet d’alignement

strategique seront recenses et documentes. Ensuite, en faisant usage d’un tableau de bord

equilibre et en se referant aux methodologies pronees dans la litterature academiques, une

analyse des outils en place sera effectuee dans Ie but de formuler des recommandations .

visant a ameliorer et corriger les metriques et indicateurs actuellement utilises par ses

departements des ventes. Finalement, Ie chercheur elaborera et implantera de nouveaux

outils donnant aux gestionnaires I’information requise pour prendre des decisions et mesurer

I’impact de ces decisions par rapport a la strategie d’entreprise. Ce projet offrira a BristolMyers

Squibb une revue de ses pratiques TI ainsi que des outils leur permettant de prendre

des decisions informees et de mieux mesurer I’effet de ces decision.

Evaluation and Improvement of High Voltage Module (HVM) of X-ray Generator – Year two

The motivation for this research comes from an overall need to improve the performance of high voltage module (HVM) and to reduce the size and its material costs while maintaining its efficient performance, with no partial discharge, arc or thermal issues. In particular, stable transient and steady state performances must be achieved for medical X-generators under wide load variation, ranging from 40-150 kV output voltage and 0.1-1000 mA output current to obtain defect free images. The desired HV module will combine the optimum cost-effective design with compactness. Therefore, the design must consider eliminating any high electric field and high temperature points in the system that lead to partial discharge and failures. Another concern about the module is its behavior under severe transient load conditions, which can happen when there is an arc in the X-ray tube. Understanding the induced voltage from the field in such a scenario is necessary to improve the design of the module. Additionally, uneven voltage distribution along the diode chains in the voltage multiplier will be a concern due to the parasitic capacitances under high frequency and high voltage conditions. Therefore, the proposed work will address the design improvements of the HVM of X-ray generators.

Evaluation and Improvement of High Voltage Module (HVM) of X-ray Generator

The motivation for this research comes from an overall need to improve the performance of high voltage module (HVM) and to reduce the size and its material costs while maintaining its efficient performance, with no partial discharge, arc or thermal issues. In particular, stable transient and steady state performances must be achieved for medical X-generators under wide load variation, ranging from 40-150 kV output voltage and 0.1-1000 mA output current to obtain defect free images. The desired HV module will combine the optimum cost-effective design with compactness. Therefore, the design must consider eliminating any high electric field and high temperature points in the system that lead to partial discharge and failures. Another concern about the module is its behavior under severe transient load conditions, which can happen when there is an arc in the X-ray tube. Understanding the induced voltage from the field in such a scenario is necessary to improve the design of the module. Additionally, uneven voltage distribution along the diode chains in the voltage multiplier will be a concern due to the parasitic capacitances under high frequency and high voltage conditions. Therefore, the proposed work will address the design improvements of the HVM of X-ray generators.

Advancing biomonitoring eDNA practices. The case of PCR inhibition and implications on eDNA detections – Year Two

Conventional biomonitoring methods based on capture and observations can be difficult, destructive of habitat, stressful for the organisms, inefficient, and expensive. Living organisms shed DNA into the environment (eDNA) and this signal can be detected using molecular methods. eDNA allows species detection without physical observation or capture. The non-invasive nature of eDNA is essential for revealing elusive and invasive species. Despite the advantages and growing applications of eDNA for biomonitoring, there are still uncertainties to be addressed before its acquisition by industry and regulators acceptance. Our project aims to compare conventional biomonitoring methods with eDNA to detect target species in both lentic and lotic ecosystems. We will approach PCR inhibition, a recurrent issue on environmental samples than can generate false positive results. We will explore alternatives to identify, assess and overcome inhibition in eDNA surveys. With a better understanding of the influence of PCR inhibition on eDNA detection sensitivity and efficiency, this project will advance the accuracy of eDNA in biomonitoring programs. Performing accurate molecular tests on environmental samples, rather than deploying time-consuming and labour-intensive methods, is valuable to the environmental industry to complement conventional approaches or overcome their limitations, overall improving environmental assessment and management decisions.

Advancing biomonitoring eDNA practices. The case of PCR inhibition and implications on eDNA detections

Conventional biomonitoring methods based on capture and observations can be difficult, destructive of habitat, stressful for the organisms, inefficient, and expensive. Living organisms shed DNA into the environment (eDNA) and this signal can be detected using molecular methods. eDNA allows species detection without physical observation or capture. The non-invasive nature of eDNA is essential for revealing elusive and invasive species. Despite the advantages and growing applications of eDNA for biomonitoring, there are still uncertainties to be addressed before its acquisition by industry and regulators acceptance. Our project aims to compare conventional biomonitoring methods with eDNA to detect target species in both lentic and lotic ecosystems. We will approach PCR inhibition, a recurrent issue on environmental samples than can generate false positive results. We will explore alternatives to identify, assess and overcome inhibition in eDNA surveys. With a better understanding of the influence of PCR inhibition on eDNA detection sensitivity and efficiency, this project will advance the accuracy of eDNA in biomonitoring programs. Performing accurate molecular tests on environmental samples, rather than deploying time-consuming and labour-intensive methods, is valuable to the environmental industry to complement conventional approaches or overcome their limitations, overall improving environmental assessment and management decisions.

Expanding the Applicability of Inductively Coupled Plasma Tandem Mass Spectrometry in Clinical and Semiconductor Industries

This internship aims at advancing the use of inductively coupled plasma (ICP) tandem mass spectrometry (MS/MS) for the analysis of clinical samples (including whole blood) and of materials used by the semiconductor industry during their manufacturing process. The complexity of biological samples indeed limits the broad use of conventional inductively coupled plasma mass spectrometry (ICPMS) for their analysis. For instance, the measurement of a very small concentration of manganese in whole blood is highly skewed due to the presence of a huge concentration of iron. However, ICPMS/MS allows the accurate measurement of the Mn concentration directly in whole blood, without sample pretreatment. An extremely small quantity of impurities must be measured in the high-purity chemicals used in the manufacturing of semiconductors, as any impurity can affect the performance of semiconductors. ICPMS/MS has great potential for decreasing the smallest quantity of impurity that can be measured (called detection limit), thereby allowing the semiconductor industry to improve their purification procedures. During this project, the intern will research instrument conditions that improve detection limits and develop methods for the analysis of clinical and semiconductor samples to benefit PerkinElmer’s customers and thereby substantially increase PerkinElmer’s competitiveness in the ICPMS/MS market.

Learning non-local features for 3D reconstruction of buildings

The goal of this project is to help automate the process of scanning buildings with consumer digital cameras. Currently, fully automated scanning with a commercial camera produces inaccurate scans, while accurate scans require significant manual effort on each individual photograph (of which there are many) of the building to be scanned. We plan to use modern machine learning techniques to reduce the human labor required to create very accurate 3D scans of buildings. The partner organisation, Butterwick Projects Ltd., will use the solution we develop to scan buildings with poor insulation, then manufacture insulated panels offsite that attach to the outside of the old buildings’ walls and roofs. Since this will be done in a factory, it will be very efficient, and won’t significantly disturb the current occupants. This is also why high accuracy is important – the panels need to fit the building very accurately despite being built offsite.

Root associated microbiome of trees growing in a fractured bedrock toluene phytoremediation site – Year two

Phytoremediation is a promising in-situ technology that uses plants and its associated microorganisms (particularly bacteria and fungi) to clean up contaminated soils. The efficacy of these processes however, requires an in-depth knowledge on the diversity of microbial communities closely interacting with plant roots. Several studies have demonstrated that plants growing in contaminated soils select for competent microorganisms able to degrade these contaminants. Although phytoremediation has received great attention in recent years, research to-date has been limited to typical unconsolidated sediments and its efficacy has yet to be shown in fractured bedrock environments. Therefore, the proposed research will aim to provide a practical evaluation on phytoremediation of petroleum hydrocarbons in fractured rock environments. Together, the results in this project will fill knowledge gaps in the scientific literature and evaluate phytoremediation systems as a viable remediation option for our industry partner in a toluene-impacted site. In addition, the proposed research will also provide new insights for industries and regulators to further develop rapid and cost-effective monitoring strategies for phytoremediation performance evaluation at other impacted sites.

Root associated microbiome of trees growing in a fractured bedrock toluene phytoremediation site

Phytoremediation is a promising in-situ technology that uses plants and its associated microorganisms (particularly bacteria and fungi) to clean up contaminated soils. The efficacy of these processes however, requires an in-depth knowledge on the diversity of microbial communities closely interacting with plant roots. Several studies have demonstrated that plants growing in contaminated soils select for competent microorganisms able to degrade these contaminants. Although phytoremediation has received great attention in recent years, research to-date has been limited to typical unconsolidated sediments and its efficacy has yet to be shown in fractured bedrock environments. Therefore, the proposed research will aim to provide a practical evaluation on phytoremediation of petroleum hydrocarbons in fractured rock environments. Together, the results in this project will fill knowledge gaps in the scientific literature and evaluate phytoremediation systems as a viable remediation option for our industry partner in a toluene-impacted site. In addition, the proposed research will also provide new insights for industries and regulators to further develop rapid and cost-effective monitoring strategies for phytoremediation performance evaluation at other impacted sites.

Production d’acide succinique à partir de bio-méthanol en utilisantMethylobacterium extorquens comme mini usine cellulaire

L’acide succinique est l’une des 12 substances les plus importantes en chimie inudstrielle. Il sert, entre

autres, à la fabrication de polymères tels le PBS (polybutylsuccinate). Présentement, 99% et plus de cet

acide est fabriqué à partir de carbone non renouvelable (pétrole et/ou gaz naturel). Plusieurs compagnies

et groupes de recherche travaillent activement au développement de procédés biologiques pour la production de cet acide à partir de substances renouvelables, essentiellement des sucres. Hors,

l’utilisation de sucres pose plusieurs problèmes : compétition ‘’malsaine’’ avec son utilisation alimentaire, et divers impacts environnementaux négatifs. Nous proposons ici une voie ‘’non alimentaire’’ pour la

production d’acide succinique, soit sa production à partir de bio-méthanol dérivé de déchets via la thermochimio-conversion (gazéification). Nous chercherons à développer via la sélection naturelle et le génie métabolique une souche de la bactérie Methylobacterium extorquens capable d’accumuler des quantités appréciables d’acide succinique, de l’ordre de 10 à 20 grammes au litre, à partir de….