Early Risk Detection Analysis using the PoP, Prediction on Predictions


Yuki, Koyanagi, Hideo Hirose


2nd International Symposium on Applied Engineering and Sciences (SAES2014), Big Data Session 1, December 20-21, 2014, Fukuoka, Japan

We deal with hear the risk analysis mainly regarding to the infectious disease spread. In observing the widely spread of patients caused by infectious diseases or the increase of the number of failures of equipment, it is crucial to predict the final number of infected patients or failures at earlier stages. To estimate the number of infected patients, the SIR model, the ordinary differential equation model, statistical truncated model are useful.
The predicted value for the final number of patients using data until truncation time T becomes a function (trend) of T. To grasp the prediction trend with truncation time, the L-plot is developed here, which is to plot the predicted final value at the truncation time. We consider the use of the L-plot to predict the final number of patients. For example, we have shown to use the decay function. Applying the multiple methodologies to the same data, we can expect better predicted values. This is called the PoP, the prediction on predictions. As one of the PoP method, we propose to use the ensemble method. By applying these methods to the SARS case, we have found that the ensemble method works well as a PoP method.

Key Words



Times Cited in Web of Science:

Cited in Books: