基于历史数据挖掘的海上船舶交通事故预测  

Predicting maritime ship traffic accidents based on historical data mining

作　　者：张哲[1] ZHANG Zhe(Wuhan Technical College of Communications,Wuhan 430070,China)

机构地区：[1]武汉交通职业学院,湖北武汉430070

出　　处：《舰船科学技术》2024年第14期174-177,共4页Ship Science and Technology

摘　　要：为优化船舶航行路线,减少因交通事故导致的延误和拥堵,提升海上运输效率和效益,研究基于历史数据挖掘的海上船舶交通事故预测方法。从海事机构获取海上船舶交通事故历史数据后,采用数据挖掘方法中的一维局阿尼自编码器对海上船舶交通事故历史数据展开挖掘,得到海上船舶交通事故特征,再建立灰色SCGM(1,1)C模型,将海上船舶交通事故特征输入到该模型中,并运用当前预测状态中间值作为修正产生,对灰色SCGM(1,1)C模型预测结果进行修正后,得到海上船舶交通事故预测结果。实验表明,该方法具备较强的海上船舶交通事故历史数据挖掘能力,灰色SCGM(1,1)C模型输出的海上船舶交通事故预测结果 DBI数值较高,预测海上船舶交通事故能力较好。Optimize ship navigation routes,reduce delays and congestion caused by traffic accidents,improve maritime transportation efficiency and efficiency,and study a prediction method for maritime ship traffic accidents based on historical data mining.After obtaining historical data of maritime vessel traffic accidents from maritime institutions,the one-dimensional local autoencoder in data mining methods is used to mine the historical data of maritime vessel traffic accidents,obtain the characteristics of maritime vessel traffic accidents,and then establish the grey SCGM(1,1)C model.The characteristics of maritime vessel traffic accidents are inputted into the model,and the intermediate value of the current prediction state is used as a correction.After correcting the prediction results of the grey SCGM(1,1)C model,the prediction results of maritime vessel traffic accidents are obtained.The experiment shows that this method has strong ability to mine historical data of maritime vessel traffic accidents.The grey SCGM(1,1)C model outputs a high DBI value for predicting maritime vessel traffic accidents,indicating a good ability to predict maritime vessel traffic accidents.

关 键 词：数据挖掘 海上船舶 交通事故预测 灰色模型 自编码器 预测值修正 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]