...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Aeronautics, Astronautics and Aviation, A >Attention Mechanism-Based Deep Learning Method for Predicting Airport Acceptance Rate: A Case Study of Hong Kong Airport
【24h】

Attention Mechanism-Based Deep Learning Method for Predicting Airport Acceptance Rate: A Case Study of Hong Kong Airport

机译：Attention Mechanism-Based Deep Learning Method for Predicting Airport Acceptance Rate: A Case Study of Hong Kong Airport

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

The airport acceptance rate (AAR) is defined as the number of arriving aircraft an airport can receive in 60-min. Accurately predicting AAR is key for evaluating the efficiency of air traffic flow management. However, precise prediction is still a challenge due to the weakness of current methods and the uncertainty of the dynamic parameters. In this paper, a deep learning method is used to depict the AAR characteristics. First, the parameters (weather, air traffic flow, and runway configuration) that affect AAR are explained. Second, an attention mechanism based long-short-term memory network joint with a deep neural network (i.e., D-LSTM) method is proposed to predict AAR in Hong Kong international airport. Finally, the prediction performance of the D-LSTM method is compared. The results demonstrate that the D-LSTM method predicts better than other existing machine learning methods, e.g., the support vector machine and random forest methods; the accuracy of the D-LSTM model is 89%. The results also reveal that the AAR exhibits time trends and periodic change characteristics.

著录项

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