自适应过滤法在水上交通事故预测中的应用

水上交通事故预测对于提高海上安全管理和预防事故的发生有重要的作用.为提高水上交通事故预测的准确性,构建了自适应过滤模型.以2011—2017年我国水上交通事故数据为基础,对2018年水上交通事故进行预测,并与一次指数平滑法、灰色GM(1,1)预测法预测结果进行对比验证.通过比较发现,自适应过滤法的相对误差较小、预测精度更高,本次预测相对误差率仅为1.68%.研究结果表明,自适应过滤法具有较好的自适应性,对于数据点较少的情况具有更高的预测精度.

Application of Self-adaptive Filtering in the Prediction of Waterway Traffic Accidents

The prediction of waterway traffic accidents plays an important role in improving maritime safety management and preventing accidents.In order to improve the accuracy of water traffic accident prediction,constructed a self-adaptive filtering model.Based on China’s waterway traffic accident data from 2011 to 2017,uses self-adaptive filtering model to predict the number of waterway traffic accidents in 2018,then compares and verifies with other prediction models.By comparison,it is found that the relative error of the adaptive filtering method is smaller.The relative error rate of this prediction is only 1.68%.The research results show that the self-adaptive filtering method is adaptive and has high prediction accuracy in the case of fewer data points.