Authors

Baousis, Vasileios; Hadjiefthymiades, Stathes; Palamarchuk, Yuliia; Panagidi, Kakia; Šaulienė, Ingrida; Sofiev, Mikhail; Sozinova, Olga; Šukienė, Laura; Vaitkevičius, Lukas

Abstract

Use Case: EO for Personalized Health care Services

This EO4EU Use Case focuses on further expanding the capacity of the PASYFO model. PASYFO is the first-ever operational Personal Allergy Symptom Forecasting System that includes a mobile application. The symptom forecasting model utilises a multitude of data sources, including spatiotemporal information. The interfaces with data sources such as CAMS, SILAM, and EO are envisaged to be updated, helping the upscaling of the model’s capabilities. Involved modules dealing with spatiotemporal data, such as the monitoring of atmospheric composition, can greatly benefit for the expressive feature space provided by the self-supervised upstream task. The performance of the detection of patterns that can be identified in a supervised way will be enhanced, and models will be facilitated to improve their tradeoff between volume of annotated data required and performance. Moreover, the model’s performance in new areas of the globe would be facilitated by a robust and generic representation provided by the selfsupervised approach. Find out more at pasyfo.eu.

Poster

Type:
Conference Publication
DOI:
https://doi.org/10.5281/zenodo.12698641
Published: