Innovative Projects Realized

Toronto Seed Strategy – Pilot Orchard Documentation

In the spring and summer of 2022, the Toronto Seed Strategy Working Group (TSSWG – a group of landscaping business owners, commercial plant growers, and plant researchers, convened by Jonas Spring of Ecoman Landscaping and Gardening) is initiating a Pilot Seed Orchard where locally-sourced, native plants will be grown to produce seeds for native plant production. This Seed Orchard (hosted by NVK Connon Nurseries in Dundas, ON) addresses a surging demand for locally-sourced, native plants in the Greater Toronto Area, which currently lacks sufficient supply. Landscaping companies are seeing a demand for locally-sourced native plant gardens, but they can’t find appropriate or sufficient quantities of plants. Within Canada’s commitment to mitigate climate change, urban greening projects, ecological restoration, and gardening with native plants are important strategies to reduce water and fuel consumption, increase biodiversity, and provide ecosystem services – and they require significant quantities of locally-sourced native plants. As a pilot project, the TSSWG Seed Orchard will be an important model for similar organizations as cities and regions mobilize to rapidly address ecological restoration needs in the face of climate change. The Intern’s research position will focus on the 1) documentation and description of the Seed Orchard operations, through diagramming and writing, 2) documentation of seedling growth and harvest activities, using photography, and 3) compiling of all documentation into a brief report and presentation that can be easily used by all members of TSSWG, and shared with other regions working on similar native plant seed strategies.

Low latency, robust and reliable multi-party interactive live video streaming

A multi-party live video communication, such as live tutorials and fitness classes, are an emerging application which involves a large number of users from different places with heterogeneous network conditions like 3G/4G/5G or Wi-Fi networks. Video Content/Service providers usually deploy their Content Delivery Networks (CDNs) over the public Internet to avoid expenses of dedicated connectivity. Thus, they often seek solutions to provide seamless services over the changing conditions of Internet that can introduce packet error, packet loss, or out-of-order packets. However, existing solutions neither scale well with the number of users nor adapt to diverse network conditions of users that require the same video to be streamed in different bitrates depending on user network condition. In this project, we will develop error detection and correction with retransmissions techniques for low-latency multi-party live video streaming. Moreover, we will devise a prediction-driven proactive CDN server scaling and placement algorithm in which CDN servers are spawned/teared down dynamically according to users’ demand change.

Refining of Kisolite Clay for Cosmetic and Phamaceutical Applications

There are four main objectives for the proposed project:

(1) To investigate three techniques of aiding the wet screening process including: (a) inclined screening combined with water jets, (b) sonication, and (c) a combination of those two techniques, to find optimum operating conditions for each technique and allow them to be evaluated and compared.

(2) To implement the most suitable technique on the industrial scale and establish its optimum operating conditions.

(3) To design and integrate all unit operations for producing the refined clay and optimize the overall production process.

(4) To refine the Kisolite clay to a suitable size range for inclusion into nanofibre structures (if time allows).

AI & Sustainable Finance: using NLP to analyze ESG disclosures of Canadian companies

Sustainable finance is a rapidly evolving discipline, where investors are in the process of acquiring and developing new tools allowing them to evaluate the sustainable impact of the companies they choose to invest in. Public companies have adopted the practice of publicly disclosing ESG-related information under the form of public reports following ESG disclosure frameworks and standards. Analyzing these reports represents a challenge for investors because of the vast quantity of reports and information they contain, the structure of the information, and the difficulty of quantifying and scoring the information. Investors often rely therefore on the ratings offered by rating agencies, but many investors would like to better equip themselves to do that work for more transparency on their evaluations. Part of the AI and Sustainable Finance currently explores the opportunity for a Natural Language Processing tool capable of collecting online reports published by Canadian companies, extracting, and analyzing said information.

Caractérisation d’espèces fongiques du Canada et du Rwanda

Les champignons produisent une panoplie de molécules qui ont des utilisations multiples dans plusieurs domaines tel que dans l’industrie agroalimentaire, les applications environnementales via la biodégradation de déchets et rejets industriels, et la médecine. Des composés issus de plusieurs champignons ont démontré une capacité à inhiber des virus et des bactéries, ralentir des maladies neurologiques et neutraliser la prolifération de certaines cellules cancéreuses. Récemment, un intérêt marqué s’est manifesté envers les molécules produites par les champignons psychotropes: Les résultats d’essais cliniques et recherche neurologiques ont démontré que les extraits de ces champignons sont capables de significativement améliorer les cas de dépression récalcitrante, d’anxiété débilitante, de syndrome de stress post-traumatique, spécialement chez les vétérans de guerre, et à assister à éliminer la dépendance aux substances, notamment les opiacés. Ce projet vise donc dans un premier temps de caractériser avec précision les champignons issus des inventaires de Mycocultures inc., et du Cercle des Mycologues de Montréal à travers une analyse moléculaire de leur ADN.

Security and safety intelligent systems on smart spaces: privacy perseveration approach

We are witnessing the rapid development of the Internet of Things (IoT) which provides ubiquitous sensing and computing capabilities to connect a broad range of things to the Internet while connecting people and spaces. That opens a wide range of opportunities to foster user-centered service, improve safety, and well-being. Intelligent IoT-based solutions have been shown to have significant potential in people safety and risk environment monitoring, due to their ability to operate at a fine granular level and provide rich low-level information.
To obtain mean-full insights into data generated from ubiquitous IoT devices in smart spaces, artificial intelligence (AI) techniques have been widely exploited to train data models for enabling intelligent IoT applications. Traditionally, data is sensed and communicated to data analytics and AI functions which are placed in a cloud server or a data center for data learning and modeling. This incurs critical limitations, such as the offloading of massive IoT data to the remote servers may be infeasible due to the required network resources and the incurred latency. The use of third-party servers for AI training also raises privacy concerns such as data breaches as the training data may contain sensitive information and also open extended security challenges.

Testing whether southern resident killer whales are endangered because of the collapse of winter and spring Chinook populations in California that occurred over a century ago

We will test the hypothesis that southern resident killer whales have been endangered since the late 1800s when mining, logging, dams, pollution, and water diversion destroyed the Chinook populations that returned in the millions to Oregon and California. We will estimate historic run sizes of Chinook salmon available to northern and southern resident killer whales based on catch records and the numbers of cans of Chinook processed at canneries (from California to BC during the 1800s). We will also compare historical seasonal abundances with relative numbers of Chinook returning to spawning rivers today—and will compare seasonal numbers of Chinook needed to sustain resident killer whales by locations to identify when and where the nutritional bottleneck southern resident killer whales are experiencing is occurring—and whether fishing restrictions imposed in BC are ultimately benefitting southern resident killer whales or not.

Multimodal Representation Learning for Healthcare Data

The abundance of electronic health record (EHR) data has accelerated the adoption of data-driven methods to automate various tasks ranging from patient care to resource management in hospitals around the world. The use of specific types of data such as X-ray images, doctor’s note and others have been used individually to implement machine learning models suited for a specific task. However, such single mode of data is not able to provide an overall picture of the patient health. In this project, we aim to develop an end-to-end machine learning model that can learn a combined representation of all these different types of data which can be fine-tuned for multiple downstream tasks such as treatment outcome prediction, hospitalization and length of stay prediction and many more.

Discovering new insight on pathogenic mechanisms to identify new therapeutic opportunities in thalassemia

We are well aware of the impact heart disease has in thalassemia patients. This impacts upon patients quality of life, and ultimately that death due to heart failure is an all too common event. We now understand much about the complexity of the heart, its structure and how it functions. This has also allowed researchers to identify things which change in the heart that cause failure of the heart.
Exactly WHY heart failure develops in people with thalassemia has still to be fully understood. Only when we know these details will more effective therapies be developed.
The research conducted in my laboratory, and in partnership with various colleagues worldwide, is designed to understand what causes changes in the structure and function of the heart in individuals with what is called metabolic syndrome (common in obese and diabetic patients). We have also recently become interested in thalassemia due to our discovery that a hormone which causes inflammation and heart disease binds and transports iron. Now, we believe there is huge potential in merging knowledge from the research of metabolic diseases with heart disease in thalassemia patients.

Enjeux et potentiels socio-économiques de la transformation numérique dans certaines filières du secteur bioalimentaire québécois

Le secteur biolimentaire québécois doit faire face à des problématiques de concurrence internationale forte, de manque de relève, de rendements non-optimaux et d’un besoin urgent de réduire son impact environnemental. La littérature scienti-fique met en évidence l’importance d’une transition numérique du secteur, soit l’utilisation des nouvelles technologies, qui permettrait au secteur d’améliorer ou résoudre ces problématiques. Ce projet a pour but d’estimer et de documenter le potentiel socio-économiques et les retombées financières potentielles des investissements pour la transition numérique du secteur en fonction du niveau de technologie utilisé. Pour ce faire, une enquête sera effectuée pour consulter les différents acteurs du secteur et des études de cas de l’utilisation de certaines technologies dans des secteurs définis seront réalisées. Les résultats et documents obtenus permettront d’accompagner les politiques publiques et les investissements dans l’utilisation de nouvelles technologies et de l’IA dans certaines filières du secteur bioalimentaire.

AI Model White Space Analysis for SR.ai’s Investment Research Platform

The field of responsible investing is rapidly expanding, with even greater attention on the importance of responsible investment in 2021, as seen in the aftermath of the hugely impactful COP26 summit. Directing our financial resources in a sustainable direction has the potential to have a massive impact on helping us meet the Sustainable Development Goals set forth by the UN. Though the importance of better alignment between finance and sustainability is clear, and now has a very strong consensus around it, investors still lack the right tools to support their research process in terms of sustainability. They rely on high level data that is largely known not to be reliable, which leads to massive misallocations of capital. The mission of SR.ai is to bring more rigour to the world of responsible investment, using our technology backed by peer-reviewed research in sustainable finance, produced through collaboration with the University of Toronto RiskLab quantitative finance research center, led by our CEO Alik and his PhD Supervisor Luis Seco.

The mission of SR.ai is to help the responsible investment industry in directing global financial resources towards sustainable and socially responsible companies and initiatives.

Adapting data infrastructure for process improvement on legal & financial service teams

North America is about to experience the greatest wealth transfer in human history. Estate planning and settlement can be enormously stressful and cumbersome processes involving lawyers, accountants, trust services, and loads of paperwork–often when least expected. The time and financial burden of planning or settling an estate presents a demanding problem to the average Canadian at a time when many are emotionally taxed and grieving. At the same time, businesses and consumers alike are seeing a need for digital transformation in historically slower-moving industries such as legal services and healthcare. The onset of the Covid-19 pandemic has added fuel to the speed of that transformation, but organizations must figure out quickly how to make sense of all the data now being brought online with it. Data infrastructure and business intelligence projects in transforming industries such as legal and financial services present a clear opportunity to positively impact organizations and the people they serve. Improvement of service and reduction of time requirements are both commercially and socially valuable, as they reduce the emotional and financial burden of estate planning and settlement.