Innovative Projects Realized

Explore thousands of successful projects resulting from collaboration between organizations and post-secondary talent.

13270 Completed Projects

1072
AB
2795
BC
430
MB
106
NF
348
SK
4184
ON
2671
QC
43
PE
209
NB
474
NS

Projects by Category

10%
Computer science
9%
Engineering
1%
Engineering - biomedical
4%
Engineering - chemical / biological

Combining Seq2Seq Models with Collaborative Filtering Techniques for Explainable Recommendation

Layer 6 builds state-of-the-art recommender systems for TD’s online businesses. Collaborative Filtering (CF) is a common recommendation approach that widely adopted by many e-commerce platforms. Modern CF algorithms attempt to exploit latent features to represent users and items, which can lead to the lack of transparency of the recommender systems. In order to build a trustworthy recommender system, it is necessary to provide explanations associated with each recommendation so that users can understand why a specific item has been suggested. The proposed research project would explore the potential of combining sequence-to-sequence (seq2seq) natural language generation models with collaborative filtering techniques into a multi-task learning setting. The result would be a recommender system that could predict customers’ needs with a high degree of accuracy, while producing effective, personalized explanations. Such explainability would build trust between the recommender system and TD’s customers, and accordingly drive sales and customer loyalty.

View Full Project Description
Faculty Supervisor:

Richard Zemel

Student:

Yichao Lu

Partner:

Layer 6 AI

Discipline:

Computer science

Sector:

Information and communications technologies

University:

Program:

Accelerate

Extension of AWSOM to Strut-Braced Wings

Bombardier is interested in investigation a novel aircraft configuration known as the strut-braced wing configuration, which is has the potential for improved fuel efficiency relative to current tube and wing aircraft. However, Bombardier’s preliminary multipdisciplinary design optimization tools need to be extended in order to be applicable to this configuration. The intern will extend the capabilities of Bombardier’s tools to enable sizing of strut-braced wing. This will allow accurate estimation of wing weight and stiffness properties of strut-based configurations, thereby facilitating design and evaluation of such configurations. This capability will assist Bombardier as it examines various options for future aircraft.

View Full Project Description
Faculty Supervisor:

David Zingg

Student:

Timothy Chau

Partner:

Bombardier Aeronautic Inc

Discipline:

Aerospace studies

Sector:

Aerospace and defense

University:

Program:

Accelerate

Natural Language Interface for Ad Hoc Queries in Analytics

The main aim of this project is to design a database that provides a simplified way for individuals without the technical background to query information from the database. Such a database will operate on natural language, where the user asks the database a question about information retrieval and it presents the user with suitable answers. A database of this format aids users who are unfamiliar with scripting and database management languages, such as SQL, to use it seamlessly without the need for any prior training.

View Full Project Description
Faculty Supervisor:

Frank Rudzicz

Student:

Yomna Omar

Partner:

CaseWare International

Discipline:

Computer science

Sector:

Information and communications technologies

University:

Program:

Accelerate

Assessing Volatile Organic Compounds as a Measure of Crop Health

Plants produce a blend of volatile organic compounds (VOCs) quickly in response to various growing conditions and plant stressors. These compounds are released well before there are any obvious signs of stress, such as wilting or loss of chlorophyll. Blueberry and other crops with thicker leaves, are slow to show obvious signs of stress and therefore are more prone to reduced crop quality and quantity than other field crops. As a first step to developing an unmanned crop monitoring device, we will be measuring VOCs produced during crop stress and measuring changes in these VOCs during the growing season, as the stress levels increase.

View Full Project Description
Faculty Supervisor:

Erik Krogh

Student:

Larissa Richards

Partner:

Spectrum Sense Ai Inc.

Discipline:

Chemistry

Sector:

Forestry

University:

Program:

Accelerate

Investigation on processes for removal of chloramines from saturated sodium chloride brine solution

ERCO Worldwide, A division of Superior Plus LP, Saskatoon facility (“ERCO Worldwide-Saskatoon”) is a manufacturer of caustic soda, chlorine, hydrochloric acid and sodium chlorate. This facility has four fully developed underground brine wells. The brine solution as produced from the brine wells contains 26% sodium chloride in it. This saturated brine is purified and supplied to the electrolyzer system to produce caustic soda, chlorine, hydrochloric acid, and sodium chlorate. When brine containing chloramine is electrolyzed, it forms nitrogen trichloride (NCl3) along with chlorine.NCl3 is a contaminant in chlorine, and certain composition of this contaminant can possibly create hazardous conditions in the processing vessels. The project is to develop a suitable process to remove chloramines from brine. This project proposal focuses on the examination of various processes available to remove chloramine from brine, test them in bench scale and recommend a process, which is cost effective and is adaptable with the existing operation.

View Full Project Description
Faculty Supervisor:

Ajay Dalai

Student:

Irina Shulga

Partner:

ERCO Worldwide

Discipline:

Engineering - chemical / biological

Sector:

Alternative energy

University:

Program:

Accelerate

Identification of heterotic gene pools to accelerate hybrid breeding in Brassica napus (canola)

Heterosis is a natural phenomenon where offspring (hybrids) outperform their parents in many agronomic traits, although exploited in breeding the mechanisms controlling heterosis remain elusive. Genetic distance between parents has been positively correlated with heterosis, yet does not adequately explain the phenomenon. Dividing lines from any crop into heterotic groups that provide optimal combining ability upon crossing, is one of the most important goals of any hybrid breeding program. The main objective of this proposal is to define the heterotic pools of Brassica napus (canola). Comparative datasets, one from a diverse population of unrelated lines and the second from elite breeding lines, and their representative hybrids will be utilised. The level of genetic diversity and the uncovered heterosis will be assessed using phenotypic and genotypic measurements. TO BE CONT’D

View Full Project Description
Faculty Supervisor:

Isobel Parkin

Student:

Sampath Perumal

Partner:

Cargill Global Edible Oils Solutions

Discipline:

Forestry

Sector:

Life sciences

University:

Program:

Elevate

Understanding the mediators of employee wellness in an activity-based workspace

Adoption of an activity-based workspace is rapidly increasing. Employees in activity-based workspaces do not have a set workstation. Instead, employees can choose from a variety of workstations (e.g. desks, lounge space, quiet offices) according to their needs. Despite increasing adoption, we know little about the impact of activity-based workplaces on employee wellness, satisfaction, and productivity. The goal of this project is to understand person-related, work-related, and organization-related factors that determine who thrives in this workspace and who perceives the activity-based workspace as a source of stress. The CIBC CRE group operates under an activity-based workspace (branded ‘CIBC@work’) in which employees can book and work in a number of different workspace. It is expected that the current work will inform wellness interventions to be evaluated within the CIBC CRE workplace.

View Full Project Description
Faculty Supervisor:

Alexandra Fiocco

Student:

Laura Krieger

Partner:

CIBC

Discipline:

Psychology

Sector:

Medical devices

University:

Program:

Accelerate

3D Imaging Development for Part Dimensional Measurement

Manual inspection method is still applied by mounting parts on customized checking fixtures and thus dimensions are checked with different gauges/feelers. Typically, it could take 10 -30 minutes to fully inspect the required spatial dimensions of one part. This project will develop an automated 3D dimensional inspection system for deep drawing parts. After manually mounting the part, the system will fully scan the whole part by 3D sensors/scanners. Interested features like primitives, holes, edges, diameters or angles then can be calculated or determined through 3D point clouds data post-processing. Shape and position tolerances will be evaluated if they can meet the customer’s requirements. The expected inspection accuracy and speed will be less than 0.3 mm and 1 min/part respectively.

View Full Project Description
Faculty Supervisor:

Kamran Behdinan

Student:

Shervin Aslani

Partner:

Van-Rob Inc.

Discipline:

Engineering - mechanical

Sector:

Automotive and transportation

University:

Program:

Accelerate

Validation and Usability Analysis for a Return to Work Software Platform

Benefit payments totaled 2.5 billion dollars for Ontario workplaces in 2015. The most common injury resulting in occupational lost time claims is a strain or sprain. These injuries indicate that despite massive efforts to reduce musculoskeletal injuries in Canadian workplaces, these issues are still a prominent source of disability and have an associated $2.5 billion annual economic burden. A physical demands description (PDD) database allows health care practitioners to determine if an employee can return to work by comparing their residual functional physical capacities and physical job demands. These PDDs lack format standardization, require technical expertise to perform, and are time-consuming. This research will examine the utility of a new, rapid, and easy-to-use video-based PDD tool, examine its validity compared to traditional pen-and-paper methods, and assess if the new video-based PDDs aide occupational health physicians in determining an appropriate return-to-work plan.

View Full Project Description
Faculty Supervisor:

Peter Keir

Student:

Colin McKinnon

Partner:

MyAbilities

Discipline:

Kinesiology

Sector:

Medical devices

University:

Program:

Accelerate

Intelligent Perception of Mining Equipment Operation using a Single Camera

In order to further enhance the productivity of mines, it is crucial to optimize mining operations. Motion Metrics Int. Corp. offers a wide range of machine vision based products to monitor mining excavators, and to generate actionable information for the mine management board. Performance of the current Motion Metrics’ products can be improved by intelligent perception of equipment operation state from the videos captured by a single camera. Perception of the operation enables the existing solutions to understand equipment activity from video stream and take a proper action in real-time. Video streams can be annotated based on the activity of the target equipment, e.g. an excavator digging cycle, and can be redirected to different proprietary processes, such as algorithms to measure teeth length, analyze content of the loaded bucket etc. TO BE CONT’D

View Full Project Description
Faculty Supervisor:

Purang Abolmaesumi

Student:

Fatemeh Taheri Dezaki

Partner:

Motion Metrics International Corp

Discipline:

Engineering - computer / electrical

Sector:

University:

Program:

Accelerate

Radiomic-based deep learning for time-to-event outcome in pulmonary malignancies.

Advances in medical image scanning technologies has allowed for great improvement in medical care, from early tumor detection, to trailered treatments and predicting treatment outcome. However, this has resulted in the generation of huge medical image databases, with thousands of medical image scans per patient that need to be examined by clinicians, making it impractical for clinicians to study all the images. This has led to the development of computer-assisted detection programs to automate part of this process. In this project we aim to develop a computer algorithm that would be used for predicting the treatment outcome for lung cancer patient. This project will focus on a specific group of lung cancer patients treated with focused radiation therapy.

View Full Project Description
Faculty Supervisor:

Matthew Yedlin

Student:

Ahmed Sigiuk

Partner:

16 Bit Inc.

Discipline:

Engineering - computer / electrical

Sector:

Medical devices

University:

Program:

Accelerate

A Framework for MBFC Big Data System

The Mercedes-Benz Fuel Cell Division (MBFC) in Burnaby, Canada develops and runs the manufacturing processes required for the assembly of Fuel Cell Stacks prototypes. MBFC uses the Manufacturing Execution System (MES) to collect and analyse data from the manufacturing lines to the database system. However, because the size of the collected data is very large, MBFC is not able to detect certain fuel cell defects in a timely manner and sometimes not at all. This Mitacs project aims to develop and evaluate a big data mechanism that improves the predictive power and reduces the time taken to search MBFC’s data and detect failures in the manufacturing process in a real-time fashion.

View Full Project Description
Faculty Supervisor:

Irfan Al-Anbagi

Student:

Niloofar Zarifi

Partner:

Mercedes-Benz Fuel Cell

Discipline:

Computer science

Sector:

Energy

University:

Program:

Accelerate

Previous
1…791792793794795796797…1,106
Next

Join a thriving innovation ecosystem.

Subscribe to our newsletter now!

Subscribe