After an earthquake, a timely and rapid emergency response is an important prerequisite for improving the efficiency of emergency relief and reducing earthquake disaster losses. The prediction of emergency material demand is not only a prerequisite and foundation for emergency response in post-earthquake disaster areas, but also one of the key problems that need to be solved urgently at present. Considering the lack of information in the post-earthquake disaster area, a model for predicting the demand for earthquake emergency supplies in the case of unclear information in the disaster area is constructed. Firstly, a rational simplification of the historical database of the disaster area is carried out using principal component analysis, and a weighted KNN algorithm is used to filter the earthquake case set. Secondly, the PSO-BP hybrid neural network algorithm is used to predict the number of post-earthquake casualties. The prediction results of the number of casualties are combined with the knowledge of inventory management to indirectly complete the prediction of the demand for materials in the disaster area. This paper composes a solution to the problems of cluttered historical data and insufficient prediction accuracy in traditional prediction models, and ensures the efficiency and practicality of the earthquake emergency resource demand prediction model.
Research on Emergency Material Demand Prediction Model Based on Improved Case-Based Reasoning and Neural Network
2021-10-20
840800 byte
Conference paper
Electronic Resource
English
Demand Prediction of Railway Emergency Resources Based on Case-Based Reasoning
DOAJ | 2021
|A Neural Network Method of Similar Case Retrieval in Case-based Reasoning
British Library Online Contents | 2006
|Research of Distributed Network Fault Management Based on Case Reasoning
British Library Online Contents | 2002
|Flight Conflict Relief Method Based on Artificial Neural Network and Case-Based Reasoning
Springer Verlag | 2021
|