Anzeige
Erschienen in:
2017 | OriginalPaper | Buchkapitel
Boosting Performance of Influenza Outbreak Prediction Framework
verfasst von : Nikita E. Seleznev, Vasiliy N. Leonenko
Erschienen in: Digital Transformation and Global Society
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
The work is dedicated to enhancing the performance of the model calibration framework used for influenza prediction in Russian cities. To increase the speed of calculations and to avoid the decreased fitting accuracy due to local minima problem, the parallelized version of the algorithm is introduced and the comparison of the available optimization methods is performed. The numerical experiments were performed on the data of influenza outbreak incidence in Moscow and Saint Petersburg. The obtained speedup of the calibration algorithm allows to work with bigger incidence datasets and obtain influenza dynamics prediction in more reasonable time compared to the initial serial algorithm. The work results can be applied to enhance performance of different healthcare decision support systems, as well as for increasing the effectiveness of decision making in adjacent areas.