Projets novateurs réalisés

Explorez des milliers de projets réussis issus de la collaboration entre organisations et talents postsecondaires.

29 670 projets achevés

2811
AB
4990
C.-B.
801
MB
663
NL
825
SK
8841
ON
9197
QC
95
PE
568
NB
1088
NS

Projets par catégorie

Efficient implementation of compact deep neural networks for mobile applications

Computer vision has become part of our daily life with applications in surveillance cameras, medical imaging, self-driving cars, and so on. Recently, deep convolutional neural networks (CNNs) have shown substantial progress in many vision applications such as image recognition and object detection. Utilizing CNNs from 2012 have reduced the error of image recognition dramatically which is now below than human level (i.e. 2.75% vs. 5%). Deep CNNs, however, require a large number of parameters and computations which make them difficult to deploy into smart mobile devices. Several studies have been conducted to find solutions to reduce the complexity of CNNs. Although they showed promising results for some benchmarks, the generalization of the methods into real-world applications has not been fully understood yet. In this work, we aim at finding the best method to compact deep CNNs and to embed them into cell-phone platforms.

Voir la description complète du projet
Superviseur du corps professoral :

Pierre Langlois

Étudiant :

Partenaire :

Huawei Technologies Canada Co Ltd (Montreal, QC)

Discipline :

Computer science

Secteur :

Technology; New and Digital Media; Other

Université :

École Polytechnique de Montréal

Programme :

Accelerate

Projection hydroclimatique de la teneur en eau des sols et des faibles débits en milieu forestier

Les changements climatiques vont intensifier les périodes de faibles débits et affecter les teneurs en eau dans les sols. Les projections de débits produites à ce jour sont cependant minées par des limitations importantes, notamment une estimation simpliste de l’évapotranspiration et une méconnaissance des propriétés des sols en milieu forestier. Ce projet propose d’intégrer une représentation plus complète et cohérente de l’évapotranspiration et des processus d’écoulement dans les couches superficielles de sol afin d’améliorer la qualité des projections futures des faibles débits et des teneurs en eau pour un ensemble de bassin versants forestiers du Québec.

Voir la description complète du projet
Superviseur du corps professoral :

François Anctil

Étudiant :

Partenaire :

Ouranos Inc

Discipline :

Engineering

Secteur :

Accommodation and food services; Agriculture; Professional, scientific and technical services; Public administration

Université :

Université Laval

Programme :

Accelerate

Communication Aid for Non-English Speaking Newcomers

The project will examine the use of pictograms – like the simplified pictures that appear on information signage – and other visual symbols in an audio-visual strategy to facilitate and enhance the use and learning of English as an additional language for Arabic-speaking Syrian refugees. The software for the project is PictoPages, whose development was funded by the George Reed Foundation and was designed by specialists from the University of Regina. PictoPages, developed to assist those with acquired or developmental verbal communication limitations, includes text, recorded speech, and symbols. The software is available for iPad and may be adapted for use on iPhone. The project is focused on those who have limited to no English skills, limited resources, and a range of educational backgrounds. TO BE CONT’D

Voir la description complète du projet
Superviseur du corps professoral :

Malek Mouhob

Étudiant :

Partenaire :

United Way of Regina

Discipline :

Computer science

Secteur :

Other services (except public administration)

Université :

University of Regina

Programme :

Accelerate

Efficient Face Recognition for Wearable Camera Devices

Titan Sécurité Inc. has deployed wearable video camera devices for security and surveillance applications, and seeks to accurately detect and recognize objects appearing in captured videos. This project focuses on video-based face recognition (FR), where facial trajectories captured with video cameras are compare against one (or few) reference stills for each individual of interest. The performance of these FR systems is typically poor due to complex and changing video surveillance environments, e.g., variations of facial appearance due to pose, illumination, blur, etc. Given the state-of-the-art accuracy achieved with deep learning architectures on many challenging visual recognition problems, Titan Sécurité Inc. seeks to design Siamese networks based on deep convolutional neural networks (CNNs) for still-to-video FR. However, since these networks represent complex solutions for real-time applications, this project seeks to develop specialized techniques to reduce their time and memory complexity. These include advanced techniques for reducing search time, selecting features, and pruning parameter. In particular, this project will focus on developing filter-level pruning techniques that can simultaneously accelerate and compress a CNN based on information extracted from its layers […]

Voir la description complète du projet
Superviseur du corps professoral :

Éric Granger

Étudiant :

Partenaire :

Titan Securite

Discipline :

Engineering

Secteur :

Administrative and support, waste management and remediation services; Professional, scientific and technical services

Université :

École de technologie supérieure

Programme :

Accelerate

Preference analyses and development of an e-health app facilitating communication of test results for hereditary cancer syndromes

An estimated 5-10% of cancers are inherited through family members. To identify patients’ risk for developing hereditary cancers, genetic testing can be used. Communicating hereditary cancer genetic results to patients is challenging for health care practitioners. Practitioners want to ensure that patients understand and communicate their preferences for receiving information. Tools to aid patients in communicating their preferences need to be developed. The intern will work with us as we: 1) ask patients about their views on different characteristics affecting their understanding of genetic test results; 2) develop and test an e-health App alongside Molecular You that patients can use to understand test results; 3) determine patients’ preferences for receiving genetic test information; and 4) elicit feedback on the App from health care practitioners and patients. Molecular You will have the opportunity to expand their existing digital health platform to support shared decision-making in the context of communicating hereditary cancer panel test results.

Voir la description complète du projet
Superviseur du corps professoral :

Dean A Regier

Étudiant :

Partenaire :

Molecular You Corporation

Discipline :

Sociology

Secteur :

Health and Related Sciences & Technology; Professional, scientific and technical services

Université :

The University of British Columbia

Programme :

Accelerate

Securing Accessible, Quality Early Learning and Care for Families Working Non-Standard Hours in Alberta: A Systematic Scoping Review

Across Canada, many families struggle to find high quality, affordable child care. Most child care options for families are limited to daytime and weekday work hours; this creates even greater challenges for shiftworkers who rely on paid child care. When child care is not available, mothers usually bear the greatest burden as many women, whether parenting alone or with a partner, act as the default primary caregiver. Exploring current literature available regarding shiftwork and access to quality, child care through a scoping review will provide a richer understanding of the nature and extent of what research exists regarding these issues.

Voir la description complète du projet
Superviseur du corps professoral :

Rebecca Gokiert

Étudiant :

Partenaire :

College of Licensed Practical Nurses of Alberta

Discipline :

Sociology

Secteur :

Public administration

Université :

University of Alberta

Programme :

Accelerate

Functional Proteomics to Inform Targeted Therapy for Head and Neck Cancer

To ensure effective cancer treatment, it is vital to match the drug with the molecular characteristics of the patient’s tumor. This research project is focused on developing functional diagnostic assays that may be used eventually in the clinic to stratify patients for targeted therapies. The project will provide a unique opportunity for the interns to work with a clinician at the forefront of cancer treatment and scientists of a partner organization that is developing innovative tools to enable precision cancer medicine. This project will generate unprecedented insights into the pathogenesis of cancer progression and therapeutic resistance and provide a foundation for translation of innovative proteomic technologies into transformative new approaches for cancer diagnosis and treatment. Furthermore, this project will provide the proof-of-concept for the partnering organization for the eventual translation of its innovative technologies to the clinic to benefit patients.

Voir la description complète du projet
Superviseur du corps professoral :

Anthony Nichols

Étudiant :

Partenaire :

Precision Proteomics Inc

Discipline :

Life Sciences

Secteur :

Professional, scientific and technical services

Université :

Western University

Programme :

Accelerate

Les évolutions des négociations commerciales et le droit international économique : questions choisies

Le succès du commerce extérieur canadien est largement attribuable aux réductions des barrières commerciales qui se sont négociées dans les forums internationaux depuis la fin de la Seconde Guerre mondiale. Les importations et exportations constituent près de 65% de la production canadienne. Or, à l’heure actuelle, les accords de libéralisation des échanges subissent une remise en cause de la part d’importants partenaires commerciaux, ce qui se répercute sur les entreprises et industries canadiennes.
Les tendances au protectionnisme observées sur les marchés mondiaux, l’absence de consensus aux dernières conférences ministérielles du Cycle de Doha et la création de nouveaux accords régionaux contribuent toutes au sentiment d’incertitude quant au futur de l’Organisation mondiale du commerce. Cette recherche aura pour objectif de cerner les impacts juridiques de la redéfinition des accords commerciaux, afin de répondre aux besoins de toute entreprise canadienne.

Voir la description complète du projet
Superviseur du corps professoral :

Geneviève Dufour;David Pavot

Étudiant :

Partenaire :

McCarthy Tétrault S.E.N.C.R.L., s.r.l.

Discipline :

Sociology

Secteur :

Professional, scientific and technical services

Université :

Université de Sherbrooke

Programme :

Accelerate

Exploration of machine/deep learning techniques using Raman spectroscopy for the identification and classification of brain tumors and prostate cancer

Cancer cells are nearly impossible to distinguish from normal tissue without sophisticated detection methods and conventional methods fail to provide real-time information during the surgical procedure. ODS Medical is developing an exclusive Raman spectroscopy system that collects data through an optical probe and is interfaced with sophisticated machine learning algorithm to identify tissues abnormalities in real-time. This technology has proven to be effective for brain tumor and prostate cancer detection. As a result much larger datasets have been acquired both for brain and prostate. Those datasets will be analyzed in order to improve the current model and develop new models based on convolutional neural networks. A global objective of this research project is to build robust mathematical models on which ODS Medical can rely on.

Voir la description complète du projet
Superviseur du corps professoral :

Samuel Kadoury

Étudiant :

Partenaire :

Reveal Surgical

Discipline :

Engineering

Secteur :

Health and Related Sciences & Technology; Biotechnology; Technology

Université :

Polytechnique Montréal

Programme :

Accelerate

Understanding mental health experiences of adults 50 years and older living in the Similkameen: A qualitative study using photovoice

The purpose of this study is to understand and promote awareness of the mental health experiences of adults 50 years of age and older who live in a rural community. This study uses photovoice, a research and advocacy method that helps people to tell their stories with photos. Participants will determine what types of experiences (e.g., stigma, resilience) will be explored by taking photos. After attending a photovoice workshop, participants will take their photos. Individual interviews about the most meaningful photos (chosen by the participant) will be used to gain insight into the participants’ experiences. Transcripts of the interviews will be analyzed inductively using constant comparison, such that themes will be analyzed and coded as they emerge. The participants will determine collaboratively how the findings should be presented (i.e., knowledge translation activities). Possible activities include a community gallery night and a summary report for community members.

Voir la description complète du projet
Superviseur du corps professoral :

Carolyn Szostak;Nelly Oelke

Étudiant :

Partenaire :

South Okanagan Similkameen Mental Wellness Society

Discipline :

Sociology

Secteur :

Health and Related Sciences & Technology

Université :

The University of British Columbia - Okanagan

Programme :

Accelerate

Volumetric Collision Course Modelling for Road Safety Analysis

Proactive road safety analysis allows for the pre-emptive diagnosis of road safety issues without direct observation of traffic accidents by observing traffic-conflict-like events, and this is made possible with large quantities of high-resolution road user trajectory data acquired from video data. However, several practical challenges exist in relation to the nature of this data for use in large-scale automated road safety analyses applications of this nature. Two small, but key, issues with deployment of such a system related to road user size are identified, studied, and addressed, namely: volumetric-based collision prediction modeling, and unsupervised camera calibration from estimated road user classification size and movement.

Voir la description complète du projet
Superviseur du corps professoral :

Liping Fu

Étudiant :

Partenaire :

Transoft Solutions Tech Corp

Discipline :

Engineering

Secteur :

Professional, scientific and technical services

Université :

University of Waterloo

Programme :

Accelerate

Finding Access to Social Services for Calgary’s Non-Status Migrants

This study 1) examines the lives of 3 to 5 non-status migrants in Calgary; 2) determines the challenges that these individuals face in accessing healthcare and social services; and 3) ascertains available services as well as the obstacles to services that are essential to these individuals’ social and economic integration. In general, my research answers the question, “From the viewpoint of non-status migrants, how do the federal, provincial, and city governments facilitate delivery of healthcare, community, and social services to non-status migrants?” Findings from this study will be used to formulate a policy-brief for policymakers and immigration agencies to guide them in making and carrying out decisions that respect and impact the principles of social justice and of the attendant basic human right to social services. In addition, a database of resources for non-status migrants that will be hosted on the website of Migrante Alberta will be created.

Voir la description complète du projet
Superviseur du corps professoral :

Liza Lorenzetti

Étudiant :

Partenaire :

Migrante Alberta

Discipline :

Sociology

Secteur :

Other services (except public administration)

Université :

University of Calgary

Programme :

Accelerate

Précédent
1...2,3132,3142,3152,3162,3172,3182,319...2,473
Suivant

Joignez-vous à un écosystème d’innovation florissant.

Abonnez-vous à notre infolettre dès maintenant!

S’inscrire