首页> 外文期刊>Journal of airport management >Predicting on-time departures: A comparison of static with dynamic Bayesian networks in the case of Newark Liberty International Airport
【24h】

Predicting on-time departures: A comparison of static with dynamic Bayesian networks in the case of Newark Liberty International Airport

机译:预测准点起飞时间:在纽瓦克自由国际机场的情况下,将静态和动态贝叶斯网络进行比较

获取原文
获取原文并翻译 | 示例
           

摘要

This paper proposes to evaluate how a network of interrelated operational variables influence the percentage of on-time gate departures in the case of Newark Liberty International airport (EWR). It compared a static with a dynamic Bayesian network model to determine whichone is the most likely to balance bias versus variance, which are two key elements in machine learning. Both models featured high variance and low bias, which limits generalisation beyond the training set. Nevertheless, both models stressed the significance of surface congestion in limitingthe percentage of on-time gate departures, even when gate departure times are compared with those in the flight plan.
机译:本文建议评估在纽瓦克自由国际机场(EWR)的情况下,相互关联的操作变量网络如何影响准时登机口的百分比。它比较了静态模型和动态贝叶斯网络模型,以确定哪个最有可能平衡偏差和方差,这是机器学习中的两个关键要素。两种模型均具有高方差和低偏差的特点,这限制了训练集以外的泛化范围。尽管如此,两个模型都强调了地表拥塞在限制准时登机口起飞百分比方面的重要性,即使将登机口起飞时间与飞行计划中的时间进行了比较也是如此。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号