Situation Analysis of Big Fires and Conflagrations in China Based on GOM-SVM Predictor

摘要：

Fire prediction technology is very important for fire prevention. Grey system theory was applied extensively and had gained a series of achievements in fire prediction, but our preliminary study showed that the general GM(1, 1) model was inadequate to handle prediction as its only adapt to the data with exponential law. The advantages and disadvantages of grey forecasting methods and support vector machine (SVM) were analyzed respectively, this article proposes a new fire-forecasting model of grey support vector machine. The new model develops the advantages of accumulation generation in the grey forecasting method, weakens the effect of stochastic disturbing factors in original sequence, strengthens the regularity of data and avoids the theoretical defects existing in the grey forecasting model. The advantage of support vector machine, which can fit no linearity time series data efficiently, was also used in the model. The prediction of the big fires and conflagrations in china shows that the prediction accuracy has been improved quite a lot in comparison with general model.

关键词： big fire conflagration GOM (1 1) SVM prediction

作者: XIE Zhengwen WU Chao LIANG Xiaoyu QU Fang

作者单位: Safety and Environment Protection Research Institute,China Jiliang University,Hangzhou 310018,Zhejia School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China Safety and Environment Protection Research Institute,China Jiliang University,Hangzhou 310018,Zhejia

会议类型: 国际会议

会议名称: The 2008 International Symposium on Safety Science and Technology(2008年安全科学技术国际会议)

会议地点: 北京

会议语种:英文

页码: 2295-2299

在线出版日期: 2008-09-24（万方平台首次上网日期，不代表论文的发表时间）