Ã山ǿ¼é

Ìý°¿±¹±ð°ù±¹¾±±ð·É:ÌýResponsible AI that properly addresses real-world stakeholder needs is at the heart of Co-Chairholders and ’s work. They work to carefully integrate domain expert knowledge with cutting-edge AI and IoT methods and tools for the improvement of animal (and human) welfare. Scientific evidence shows that farm animal welfare and cow longevity go hand in hand, guiding the industry's interest in improving animal welfare, as increasing longevity is seen as an answer to economic, social and environmental sustainability concerns in the dairy industry. The consists of a Digital Living Laboratory, focused on the needs of animals and end-users, primarily in the Canadian dairy sector. Grounded in industry partnerships, members of the dairy community sit on both the scientific and management committees, where they contribute to research orientations, leading to the co-creation of research projects and initiatives.


Launched in 2023, our team has been conducting pilot research and working to build functional and resilient data collection infrastructure for implementation on dairy farms in 2025. This deployment will ensure robust continuous monitoring across a network of farms, while respecting data confidentiality and cybersecurity. We have also developed a framework for the study of animal behaviours and emotions, presenting a paradigm shift for both annotation and data analysis based on continuous and heterogeneous data sources. Our approach relies on the use of IoT, computer vision and machine learning to improve our ability to detect and monitor changes in animal welfare and longevity earlier than possible with visual methods, and to generate predictions to aid on-farm decision-making, ensuring that resources and efforts are focused on the animals most likely to succeed in the long term. This research combining animal welfare and technological development will help the end-users’ community develop evidence-based practices and provide new keys to the entire livestock value chain to ensure its sustainability.

Ìý ÌýÌý

Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý Ìý

Presented by: Dr. Yichuan Ding
Project Abstract:ÌýThe "ED PreVisit" web application is an innovative AI-driven tool designed for patients planning a visit to an Emergency Department (ED), allowing them to undergo a preliminary self-triage prior to their physical arrival. With data sourced from renowned hospitals such as Jewish General Hospital, the application identifies symptom patterns, anticipates potential outcomes, and tailors its questioning to pinpoint the patient's chief complaint.ÌýWith a user-friendly bilingual interface, patients input vital details and describe symptoms, while the app transforms this data into the IT system of the target ED. This proactive approach not only expedites the registration and triage process, but also avoid unnecessary ED visits by directing non-urgent patients to general practitioners or pharmacists. Moreover, it provides ED managers with future information about patient arrivals, which can be used for better demand forecasting and resource planning.ÌýThis app can also offer estimated waiting times for various EDs, allowing patients to choose one with the shortest wait. Once a patient selects an ED and submits the questionnaire, the app will also provide tailored preparation instructions for the ED visit, based on the patient’s profile and chief complaint. Spanning from January 1 2025 to December 31, 2025, the project's focus is the development and internal evaluation of the app, ensuring its efficacy and ease of use.Ìý

Presented by:
Project Abstract:ÌýAs students enter high school, math topics tend to become more abstract, which proves difficult for many students and requires additional instructional support. Teachers of advanced mathematics need more resources to support their students' learning, but their options are currently limited. Even with the growth of online resources, many do not provide personalized support or are not connected to specific secondary math curricula.ÌýSome teachers are starting to turn to generative AI to help create new content, but little is known about how they should do so. Specifically, generative AI (genAI), such as ChatGPT, has not typically been created for educational purposes and given that many are based large language models (LLMs), there is a growing need to understand how these tools can be used to optimize teaching and learning in mathematics.ÌýIn this project, we will use an interdisciplinary approach to explore three main areas: 1) Why and how teachers are (or are not) using generative AI, 2) Teachers needs with regard to content/resource generation, andÌý 3) The scope of existing genAI tools.ÌýÌý

Presented by: Dr. Shangpeng Sun
Project Abstract:ÌýRemarkable increases in the use of synthetic herbicides have been reported for weed control. However, up to 98% of crop spray does not stay on the plants and flows into the environment, causing soil and water pollution. Therefore, reducing herbicide use is critically needed to develop resilient and sustainable agriculture, and it has significant positive impacts on public health, society, and the ecological environment.ÌýIn this initiative, we aim to develop an AI-powered aerial-ground collaborative mobile system for precision spraying to reduce herbicide use.Ìý

Presented by:
Project Abstract: When AI systems are adopted in critical applications, any failure can pose serious risks to the health, safety, and well-being of users or other related stakeholders. Accurate estimation of the severity of the risks and thorough planning for mitigating them are indispensable but extremely challenging. This is especially true for marginalized and minority communities. Considering such a gap, we aim to accelerate the design of inclusive AI systems through a concrete case study of an accessible form of payment for the elderly population. As a first step, we plan to identify the barriers preventing marginalized users, in particular the elderly population, from participating in the design process of such AI systems. The outcomes from this research contribute to improving the existing co-design practices toward the development of inclusive AI, and inform the construction of a shared set of vocabulary that technologists and policymakers can use to prevent harms and risks AI can bring to the minority and marginalized stakeholders of the technology at design time.

Presented by: Dr. Joseph Levitan
Project Abstract: Research has shown that culturally grounded education for Indigenous community members supports engagement, wellbeing, and learning. However, implementing culturally grounded education effectively, particularly in remote areas, has proven difficult due to the lack of culturally grounded materials and the time it takes to create quality curriculum. Over the past 6 years our team has been able to develop and implement culturally grounded curriculum in rural Indigenous areas of Peru. However, it is a challenge to do this work at scale. Artificial intelligence (AI) shows promise for addressing this issue. To demonstrate that AI can create culturally grounded learning materials and curriculum based in community epistemologies, our team will train offline AI software to use community-led, collaboratively gathered knowledge, such as local plants, animals, and cultural practices to foster literary, numeracy, and critical thinking skills based in communities’ ways of thinking and being. This work will engage in community-based practices and follow First Nations OCAP ethical principles.