著者
IKEDA Takashi KUSAKA Hiroyuki
出版者
Meteorological Society of Japan
雑誌
気象集誌. 第2輯 (ISSN:00261165)
巻号頁・発行日
pp.2021-067, (Released:2021-08-20)
被引用文献数
8

We developed fifty-five models for predicting the number of ambulance transport due to heatstroke (hereafter referred to as the number of patients with heatstroke) on the next day in Tokyo, using different combinations of eleven explanatory variables sets and five methods (three statistical models and two machine learning) for 10 years (2010-2019). The root mean square error (RMSE) for the number of heatstroke patients was minimal when the best model was developed by combining six explanatory variables (temperature, relative humidity, wind speed, solar radiation, number of days since June 1, and the number of patients with heatstroke on the previous day) and the generalized additive model. The best model remarkably improved prediction by 52.1 % compared to a widely used model, which primarily utilizes temperature as an explanatory variable and the generalized linear model as a method. Further analysis investigating the contribution of the explanatory variables and method to the prediction showed that RMSE was reduced by 49.7 % using the above six explanatory variables compared to using the only temperature and by 14.6 % using the generalized additive model compared to using the generalized linear model.
著者
Ujita Hiroshi Ikeda Takashi Naitoh Masanori
出版者
一般社団法人日本機械学会
雑誌
JSME international journal. Ser. B, Fluids and thermal engineering (ISSN:13408054)
巻号頁・発行日
vol.45, no.3, pp.607-614, 2002-08-15
参考文献数
14
被引用文献数
5

SAMPSON is the integral code for severe accident analysis in detail with modular structure, developed in the IMPACT project. Each module can run independently and communication with multiple analysis modules supervised by the analysis control module makes an integral analysis possible. At the end of Phase 1 (1994 - 1997), demonstration simulations by combinations of up to 11 analysis modules had been performed and physical models in the code had been verified by separate-effect tests and validated by inegral tests. Multi-dimensional mechanistic models and theoretical-based conservation equations have been applied, during Phase 2 (1998 - 2000). New models for Accident Management evaluation have been also developed. Verificaton and validation have been performed by analysing separate-effect tests and inegral tests, while actual plant analyses are also being in progress.