Drug Demand Prediction Research In A Massive Earchquake Disaster Based On Verhulst Model Of Continuous Interval Grey Number

Normally, massive earthquakes resulted in enormous casualty because of its paroxysm and destructiveness. Based on experiences in rescuing in many countries, we find that casualties can be reduced at the beginning of massive earthquake by enhancing speed and accuracy of rescues. However, because the influence of factors such as the limited time and information, inadequate relief channels, the whole demand of emergency medicine could not send in time after the massive earthquake, so it need to forecast the drugs, guarantee the adequate supply of emergency medicines and the efficiency and quality of medical care.According to the analyses on the characteristics of demand of emergency medicines during massive earthquakes, summarizes the research status, we find the shortcomings in the study and post questions. Consider the research methods and main content. On this basis, the drug needs to rescue the massive earthquake disaster emergency characteristics were analyzed and we know that it is difficult forecasting the drug demand directly due to the uncertainty of medicine demand for the emergency rescue. So in the paper we firstly forecast the number of the diseases and wounded and analyze the relationship between the number of wounded people and the demand of emergency medicines to forecast the quantity of different emergency medicines. At the same time, the number of patients in the massive earthquake shows saturation of “S-shape” and increases all the time, as well as a continuous and dynamic process. Based on the above analysis, we tease out the basis theoretical that is needed, consider the data characteristics to select interval gray numbers whitening methods, then analyze error sources of the classic gray Verhulst model, and select the gray discrete Verhulst model to portfolio construction continuous interval gray numbers(discrete) Verhulst mode; Then verified by the earthquake instance statistical data, and compared with different data models and give error checking. Finally, we use the model to forecast the earthquake rescue drug demands and guarantee the supply of drugs. Then the conclusions will be given, and this part also discusses the shortage of this research, and states the next step research prospects.