韩国裸舞

Towards AI-driven Food and Nutrition Science and Society: Opportunities and Challenges

Tome Eftimov

Senior Researcher, Computer Systems Department, Jo啪ef Stefan Institute

Tome Eftimov is a senior researcher at the Computer Systems Department at the Jo啪ef听Stefan Institute. He is a visiting assistant professor at the Faculty of Computer Science听and Engineering, Ss. Cyril and Methodius University, Skopje. He is a part of the ELIXIR Food and Nutrition Community. He was a postdoctoral research fellow at the Stanford听University, USA, where he investigated biomedical relations outcomes by using AI methods.听In addition, he was a research associate at the University of California, San Francisco,听investigating AI methods for rheumatology concepts extraction from electronic听health records. His research interests include natural language processing, statistical听data analysis, metaheuristics, representation learning, and machine learning. He is an听organizer of several workshops related to AI at high-ranked international conferences听including the Big Food and Nutrition Data Management and Analysis at the IEEE BigData听conference 2019, 2020, and 2021. He is a scientific coordinator of a EFSA funded project听related to information extraction in food safety and actively participates in several European听projects related to AI and food and nutrition data, including COMFOCUS.
听

Abstract

Lancet Planetary Health in 2019 noted that the focus of future improvements in our wellbeing and societies will depend on investigating听the links between food systems, human health, and the environment. However, despite the large number of available resources and work done in the health and environmental domains, there is a lack of data and digital resources that can be utilized in the food and nutrition听domain, as well as their interconnections. For the purpose of attaining human and societal wellbeing through advances in the field of artificial听intelligence (AI), the talk will focus on opportunities for utilizing big data from food and nutrition and their interrelations with the biomedicine听and the environment. Huge amounts of data containing valuable information is now available in various datasets, registries, and scientific and听grey literature, which makes it possible to use advanced Artificial Intelligence (AI) methods. However, before applying AI methods on real-life
data, that is heterogeneous (i.e., of different types and formats), unstructured (textual) data needs to be structured and normalized with other听structured data. In this talk, we will explain AI methods and resources that can be used on different levels in the modeling process, starting听from raw data to discovered knowledge. Finally, the existence of such methods and resources will be linked to several application scenarios of听utilizing food and nutrition data in predicting emotional distress, COVID-10 mortality rate, and food chain traceability.

Dr. Eftimov's presentation will be supported by his collaborators: Barbara Korou拧i膰 Seljak and Gjorgjina Cenikj.

Chair: Laurette Dub茅 (Scientific Director of MCCHE)
Co-Chair & Moderator: John G. Keogh (Managing Principal, Shantalla Inc. Toronto )
Special Panel: A panel with scientists, business and policy leaders will discuss how scientific and technological developments and听ontologies bridging farm, food and human behavior, can accelerate the design and long-term performance of convergence platforms ecosystems听targeting achievable and time-bound real-world solutions placing human and environmental health at the core. This will advance the design of听integrative digital architecture and governance framework to scale up how real-world data generated by individuals and institutions within and听across disciplines and sectors can contribute to a World reset on convergence economy, building upon the challenges and possibilities reviewed听above. Capitalizing on digital transformation of science and society, convergence economy takes a person-centered approach to bridging organizations听and systems across sectors and jurisdictions, fully acknowledging that developed and developing worlds share the same planet, for听world-scale transformation toward sustainable prosperity and affordable nutrition and health.

ABOUT THE SERIES

The Convergent Innovation Webinar Series features cutting edge science, technology and innovation in agriculture, ;food, environment, education, medicine and other domains of everyday life where grand challenges lie at the convergence of health and economics. Powered by data science, artificial intelligence, and other digital technologies, this disciplinary knowledge bridges with behavioural, social, humanities, business, economics, social, engineering, and complexity sciences to accelerate real-world solution at scale, be it in digital or physical contexts. Initiated in the agri-food domain, the series is now encompassing other grand challenges facing modern and traditional economies and societies, such as ensuring lifelong wellness and resilience at both the individual and population levels.