Authors: Xiaoxin Zhu; Baiqing Sun
Addresses: Faculty of Management Science and Engineering, Department of Management, Harbin Institute of Technology, Harbin, 150001, China ' Faculty of Management Science and Engineering, Department of Management, Harbin Institute of Technology, Harbin, 150001, China
Abstract: This paper aims at predicting the dynamic death tolls in earthquakes using a combination of case-based reasoning and a times series model from realistic perspective. The proposed methodology consists of three steps: 1) fuzzy clustering to classify Chinese earthquakes; 2) mortality rates calculating to predict the final death tolls; 3) time series modelling to predict dynamic number of deaths. The strength of this paper is that it provides scientific methods with overall forecast errors lower than 20%, and opens the door for conducting final and dynamic death forecasts with a qualitative and quantitative approach.
Keywords: humanitarian logistics; earthquakes; mortality prediction; CBR; case-based reasoning; times series model; China; dynamic modelling; China; seismic activity; death tolls; fuzzy clustering; fuzzy logic; classification; mortality rates; death forecasting.
International Journal of Emergency Management, 2017 Vol.13 No.2, pp.131 - 149
Received: 17 Aug 2015
Accepted: 02 Nov 2015
Published online: 06 Mar 2017 *