Vessel Collision Accidents Analysis based on Factor Analysis and GA-SVM

摘要：

　　In order to explore the inherent law of serious collisions and provide a reference to determine the result of accidents,this paper proposed a new model of vessel collision analysis and prediction based on data mining.After collecting complete vessel collision accidents reports,indexes of the severity of vessel collision were extracted and quantified.By using the method of factor analysis,the related indexes were reduced to several principal factors.And then the importance of each index was determined by regression analysis.Combined with support vector machine(SVM)model optimized with genetic algorithm(GA),it achieved the prediction of the severity of vessel collision.The experimental results show that the proposed model performs better in the area of prediction than other three similar models.

关键词： vessel collision data mining factor analysis support vector machine genetic algorithm

作者: Hui Fang Zhiqiang Guo Jie Yang Jie Yang

作者单位: Key Laboratory of Fiber Optic Sensing Technology and Information Processing,Ministry of Education,Sc School of Information Engineering,Wuhan University of Technology Wuhan,Hubei Province,China

会议类型: 国际会议

会议名称: 2017 IEEE 2nd Advanced Information Technology,Electronic and Automation Control Conference(IAEAC 2017)(2017 IEEE 第2届先进信息技术、电子与自动化控制国际会议)

会议地点: 重庆

会议语种:英文

页码: 191-195

在线出版日期: 2017-03-25（万方平台首次上网日期，不代表论文的发表时间）