×Period affected by the first consecutive holidays
during the Olympic Games (7/28 to 8/6)
●Recent (from 8/7)
*The effective reproduction number is excerpted from Toyo Keizai Online
*Average value of flows of people 6 to 13 days before the day
Prediction system under development
Characteristics: Directly predict the numbers of newly infected people and seriously ill
patients per day up to one month later considering flows of people and seasonality based
on the LSTM model (one-week average value)
The data volume in appearance was increased by using standardized data instead of that of prefectures.
Research achievement: Prediction of the number of newly infected people using AI1
Repeat learning every week to update the prediction model. If flows of people are grasped, the
daily number of newly infected people for one month from now can be predicted (one-week
average value) (average 20%): Up to the 4th wave
High accuracy up to two weeks later because the value of past flows of people of about two weeks
1. E. A. Rashed and A. Hirata, “Infectivity upsurge by COVID-19 viral variants in Japan: evidence from a deep learning modeling.” Int. J. Environ. Res. Public Health, 2021.
Which input values are important factors?
- From the result of simultaneous learning of six prefectures
The original variant of the novel coronavirus can be predicted at an average accuracy of 81.6%
Used Google mobility