Dr. Chen Yang

(Keynote Speaker)

Ghent University, Belgium

Brief Bio: Chen Yang got his Ph.D. degree from Ghent University, Belgium. He is currently a Post-doc researcher in the Faculty of Bioscience Engineering at Ghent University. His research interests include data & knowledge standardization, ontology development and application, knowledge graph reasoning, knowledge representation, etc., especially for the applications in agriculture, food and nutrition science.
Chen Yang is in charge of the Ontology for Nutritional Epidemiology (ONE), which is a member of the Open Biological and Biomedical Ontology Foundry (http://obofoundry.org/), the European ELIXIR Ontology Lookup Service (https://www.ebi.ac.uk/ols/index), the BioPortal ontology repository (https://bioportal.bioontology.org/), etc. Chen Yang is also a contributor of the Information Artifact Ontology (IAO), the Ontology for Nutritional Studies (ONS), etc. Chen Yang is a leading expert of two European Horizon 2020 projects, invited speaker of seven international/European level conferences, and invited peer-reviewer of several leading academic journals in information technologies, agriculture, food and nutrition science.

Title of Speech: DIKW-based knowledge graph for AIoT in agriculture

Abstract: The Artificial Intelligence of Things (AIoT), a combination of artificial intelligence technologies and the Internet of Things (IoT), is booming recently for more efficient IoT operations. The AIoT enhances human-machine interactions and data management. In agriculture, AIoT is especially complicated because of the numerous influencing factors such as temperature, humidity, nutrition, genotype, domain knowledge, etc. Therefore, efficient data integration in agriculture is still challenging. A knowledge graph enables data/knowledge integration and representation through multilateral logic relationships, and makes the information both human- and machine-readable. We suggest to develop knowledge graphs according to the Data, Information, Knowledge, and Wisdom or “DIKW” pyramid. The introduction of the DIKW-based knowledge graphs would help integrate agricultural data and experience/knowledge from different sources (e.g. IoT sensors, weather forecast, soil data, expert/grower experience, etc.) in various formats (e.g. data, photo, etc.). A dynamic graph database based on a DIKW hierarchy enables real-time data-knowledge interaction according to real-time inputs from sensors, which provides a basis for the AIoT for future agriculture practice.