Software and Data Sciences Projects

Advancing Video Categorization

Vubble, a Toronto-based media tech company, builds solutions for trustworthy digital video distribution and curation. The need for automation of video curation is prevalent, as video is quickly becoming the world’s dominant form of media consumption. Using a combination of algorithms and human curators, Vubble searches the internet to locate video content of interest to its users. Vubble has experienced significant year-over-year growth since incorporation, with an expanding customer base in the education and media spaces. Vubble is collaborating with Dr. Vida Movahedi and student research assistants from Seneca’s School of Information and Communications Technology to develop a machine-learning algorithm that will automatically output highly probable categories for videos. With this algorithm implemented into the Vubble workflow, they will be able to better address customer demand, while increasing their productivity and competitiveness.

 

 

Funders: Natural Sciences and Engineering Research Council of Canada (NSERC), Ontario Centres of Excellence (OCE), and SOSCCIP.

Data flow analytics to improve quality of seed-to-sale cannabis tracking

Ample Organics is a world-leading cannabis technology provider. Today, their seed to sale tracking and reporting software is available on four continents and is used by seventy percent of Canada’s cannabis licence holders. This comprehensive solution enables licence holders to meet regulatory requirements, tracking data about every gram produced. With continually evolving regulations, Ample Organics has identified a need for improved data collection and management. Through this collaboration, Ample Organics will understand what data is necessary to support the production of cannabis products. Seneca will facilitate this by evaluating data flow in place at cannabis facilities and recommending an optimized data collection procedure to be considered for Ample Organics’ new software modules.

The results of this project will enable Ample Organics to build an advanced analytics product supporting licence holders’ quality control and reporting capabilities. Improving data collection at cannabis facilities requires identifying the differences between the current state of data collection and what Ample Organics’ current products support. The Seneca team will expand on what data can be collected at cannabis facilities by understanding which data is important to collect. The project will result in formal data flow diagrams describing the current status of collected data, the creation of an optimized cannabis tracking data process flow to track all required variables needed for quality control, and building a software demonstration to visualize the data structure.

Funder: The Natural Sciences and Engineering Research Council of Canada (NSERC)

Development of Human Body Measurement workflow for 3D Scanning System

Perfitt Inc. is a Canadian company that is developing a photogrammetry system for fashion applications. Building upon previous research collaboration with Seneca, Perfitt aims to quickly and unobtrusively obtain a 3D model of a human subject using multiple cameras and photogrammetry techniques. The resulting model is then analyzed to obtain measurements for bespoke clothing production and off-the-shelf clothing size recommendations.

Taking body measurements for bespoke garments is a complex task that requires a lot of skill and experience. Being able to translate that skill into the controlling software is critical to the market success of the proposed system.

To solve this challenge, Perfitt turned to Seneca to leverage the expertise of Professors Philip Sparks (School of Fashion), and Chris Tyler (School of Software Development and Data Science), along with student Research Assistants: Tia McQuaid (School of Fashion), and Josue Quilon Barros (School of Software Development and Data Science). 

A group of over 20 subjects with different body shapes and skin tones, were recruited with the purpose to perform 3D body scanning and to take detailed traditional, hand measurements. The data obtained through this process was then used to develop algorithms taking digital measurements off the 3D model, and to calibrate them for accuracy. The incorporation of the automatic human body measurement capabilities into the 3D scanning system, is a significant step for Perfitt in its efforts to build a comprehensive solution for the fashion industry.

Funder: This project is funded by the Ontario Centres of Excellence (OCE) through the College Voucher for Technology Adoption (CVTA) program, and by NSERC CCI-IRCC [Natural Sciences and Engineering Research Council of Canada, The College and Community Innovation and the Industrial Research Chairs for Colleges] grant.

Improving online learning accessibility 

Blindside Networks provides the BigBlueButton platform, an open source web conferencing system for distance education. Blindside has partnered with Seneca since 2011, to enhance their BigBlueButton platform. 

Blindside is collaborating with Professor Fardad Soleimanloo and his students from Seneca’s School of Information and Communication Technologies to ensure the HTML5 client for BigBlueButton meets the accessibility needs for all students. For example, a deaf student requires live captioning capabilities; a blind student requires all text is available to a screen reader.  HTML5 support for mobile browsers is still emerging and is not fully adhering to the standards defined in Web Accessibility Initiative Accessible Rich Internet Applications (WAI-ARIA).  The Seneca team is using its deep expertise in web technologies to develop a WAI-ARIA compliant HTML5 client for BigBlueButton.

 

 

Funder: Ontario Centres of Excellence.

Increasing Accuracy of Text Extraction for a Single Category (Website Privacy Policy) of Legal Documents

Clausehound Inc. supplies business law training tools and curriculum to educational organizations including colleges, universities and startup services organizations. Clausehound's automations in contract drafting makes negotiation easier, and Clausehound collects "deal points" into inventory, to benefit deal negotiators on their current and future negotiations. Clausehound’s products are currently in-market and are generating revenues; however, improving the accuracy at which information is retrieved from their internally-developed legal knowledge repository, and routed to users for review and drafting, is crucial for the growth of their customer base. Building on a previous applied research project with Seneca, Clausehound is collaborating with Prof. Tanvir Alam to develop machine learning algorithms that will maximize the accuracy of text extraction and comparison from a single category of legal documents (website privacy policies) where a significant amount of data is available to train the algorithms.

 

Funder: Ontario Centres of Excellence (OCE)

Medical Diagnostic Data Ingestion Optimization

TeleMED Diagnostic Management Inc., founded in 2000, is a Toronto-based medical data management company that designs, builds and implements customized, electronic solutions for managing and sharing electrocardiogram (ECG) and other medical test data for the medical diagnostics industry. TeleMED’s solutions utilize cloud technology and feature leading-edge functionality for privacy protection, customized report generation and quality assurance monitoring. TeleMED's technology solutions have been commercially available for more than fifteen years, with their major customers being Canadian pathology laboratory networks. TeleMED’s ViTELflo platform provides labs and clinicians with a vendor and network agnostic single-platform management of data that streamlines operations with up to a 40% increase in productivity.

TeleMED is collaborating with Professor Chris Tyler, NSERC Industrial Research Chair for Colleges (IRCC), and student Research Assistants from Seneca’s School of Information and Communications Technology to develop a validated ingestion tool for accepting a new file format of cardiology tests that will allow TeleMED to expand the services it offers its customers. Through the proposed collaborative applied research project, Seneca will develop new technology with TeleMED that will accept and convert all DICOM reports, from any medical diagnostic equipment, to a format that can be read and integrated into TeleMED's existing ViTELflo cardiology data management system. This project will enable TeleMED to continue to grow its business by adapting their software platform to accommodate the emerging DICOM medical diagnostics industry standard data file type, while maintaining a system that provides an efficient way for clinicians and their patients to access medical data.

Funder: The Natural Sciences and Engineering Research Council of Canada (NSERC)

Personalized real-time location-based service recommendation

Wazzio, established in 2013, is a technology company that has been offering value-added services to IT resellers that augment their product portfolios. In 2017, Wazzio identified an underserved market with high growth potential, spurring the development of the Rylli app platform, connecting customers to service providers. Launched in 2018, Rylli targets two audiences: service providers with immediate availability and busy people who need to access various services instantly. At its core is a realization that, very often, people need access specific service(s) immediately and do not want to — or cannot afford to — spend a lot of time researching potential providers only to discover that the provider’s next availability is weeks away.

Since the key concept behind the app is on-demand access to services, Rylli’s core driver is a real-time recommendation engine that will present consumers with a list of relevant service providers who have availability at the time of search. Wazzio will engage with Dr. Mariam Daoud, from Seneca’s School of ICT, to develop customized data mining algorithms for this engine to enhance their existing platform. Seneca’s team will research various techniques to reveal individual and group patterns and purchasing tendencies, which in combination with other information will be used as a basis for generating accurate recommendations, specific for each consumer. Receiving meaningful, accurate service suggestions will have a significant, positive impact on Rylli consumers’ experience and perception of the app, leading subsequently to higher customer satisfaction, customer retention, positive app reviews, more subscribers and ultimately revenue growth for Wazzio.

  

Funders: Natural Sciences and Engineering Research Council (NSERC) and Ontario Centres of Excellence (OCE)

TeamWorks TAVI Project

Founded by Dr. Sylvain Plante, an interventional cardiologist at Southlake Regional Health Centre (Newmarket, Ontario), Inideo Inc. offers a suite of cardiac specific patient information flow and electronic medical records applications. The software has a significant impact on healthcare by enabling time and costs savings through workflow efficiency. In order to expand their product offering, Inideo and Southlake partnered with Professor Asma Paracha and student research assistants from Seneca’s School of Information and Communications Technology to develop new modules to handle patient information flow related to a novel surgical procedure: transcatheter aortic valve implantation (TAVI). The project requires the research team to assess the workflow needs of TAVI procedures, adapt existing databases and create a useful web-interface and reporting system.

Funder: FedDev Health Ecosphere.

Transition from Angular 1 to Angular 7 platform for an Innovative Enterprise Software

Bitnobi is a privacy protected, data-sharing platform that allows a data provider to set the rules of engagement for end-user data queries. This enterprise software acts as an interface between a data provider and end-users in order to provide a more efficient way of interacting with data sources without giving raw data or making copies.

In collaboration with Seneca’s School of Information Communications Technology, under the supervision of Dr. Mark Shtern, two senior year research assistants will transition, Bitnobi’s current interface is powered by Angular 1 to Angular 7. This transition will make it easier for the Bitnobi development team to use different user interface objects depending on the user application.

Deliverables include: (a) mapping software code that pertains to each user interface object; (b) transition of Bitnobi’s interface from Angular 1 to Angular 7; and (c) documentation of each new javascript module.

 

Funder: Ontario Centres of Excellence (OCE)

Utilizing Machine Learning Techniques to Understand Connectivity and Usage Patterns for Improved Online Contact Search

The Networking Effect (TNE) is an all-in-one e-tool that supports connectivity and the building of business relationships. It lets individuals and organizations develop, grow and manage their business network quickly and easily. More than just a database of business cards, TNE’s goal is to go beyond traditional services such as LinkedIn with a much stronger focus on business, and even personal, interests and goals.  TNE is collaborating with Dr. Allan Randall from Seneca’s School of Information and Communication Technology, who will utilize machine learning techniques and principles to add intelligence to the search capability of the existing TNE platform.  This intelligence will drive better connections, and significantly differentiate TNE from other products on the market.

The Networking Effect logo

Funder: Natural Sciences and Engineering Research Council of Canada (NSERC) and Ontario Centres of Excellence (OCE)

Seneca Applied Research
Seneca Innovation