英文摘要 |
This research investigates potential variables of buding destruction in earthquakes and their influences by conducting an empirical study of Jwu-Shan area in Taiwan. Jwu-Shan was one of the most serious damaged areas during the 921 earthquake which was 7.0 magnitude. In this study, MATLAB6.5 software of back-propagation neural network was used with its superior attributes, i.e., learning and memory, to establish a forecast model of hazards in middle and lower buildings in an earthquake by means of training, testing and validation. The model was tested with the data of partial old communities in Chia-Yi. Damaged buildings were classified into 3 categories: safe, unsafe, and collapse by geography information system (GIS) with data spatialization and transformation. The results suggest that the artificial neural network is capable to forecast building destruction in earthquakes with a low error rate. The paper concludes with applications of a back-propagation neural network in planning urban disaster prevention. |