EFRA will explore how extreme data mining, aggregation and analytics may address major scientific, economic and societal challenges associated with the safety and quality of the food that European consumers eat. EFRA’s goals are: i) develop and test solutions to discover and distil food risk data from heterogeneous and dispersed/scarce data sources with minimal delay and appropriate format; ii) design relevant human aspects & interactions with users to measure usefulness for human risk prevention actions in real-world use-cases iii) demonstrate how solutions enable the development of trustworthy, accurate, green and fair AI systems for food risk prevention iv) achieve groundbreaking advances in performance and effectiveness of food risk data discovery, collection, mining, filtering, and processing; v) integrate relevant technologies (big data, IoT, AI) to foster links to food data innovator communities vi) position its contributions into the overall ecosystem of public & private stakeholders that share data, technology and infrastructure to ensure the safety and quality of food in Europe.
CNR will lead WP3 (Data Analytics & AI Prediction Models) focusing on the definition of novel sustainable machine/deep learning techniques to achieve good trade-offs between accuracy, latency and resource usage. It will also contribute to WP1 an integrated, energy-efficient cloud/edge HPC architecture and to WP4 the strategies for the re-allocation of cloud & HPC resources for greener operations.