Rapid Decision Model of Disaster Relief Logistic, Based on Internet of Things (IoT) Data Analytics using Case-Based Reasoning
Abstract
A Forecasting demand for an emergency logistics assistance plays an important role for optimal
disaster logistics management. An accurate demand forecasting can prevent an out-of-stock, can
save time, and ensure a proper allocation of emergency logistical relief to overcome a longer
suffering of victims. This paper aims to design a model for estimating emergency logistical
assistance requests after an earthquake. The Case-based Reasoning (CBR) method is applied to
build the model, while the implementation of the Internet of Things (IoT) supports retrieving data
to the model to produce the forecasting results quickly. The results show that the forecast error
for each relief logistics; food, blankets, and tents, respectively 10.48%, 16.78%, and 15.99%.
Since all forecast errors are in the range of 10% -20%, thus the forecast results indicate that
model is valid to use for a forecasting emergency logistical assistance requests after an
earthquake occurs.