Open AccessA structured data preprocessing method based on hybrid encoding
Author(s) -
Chang Liu,
Yang Liu,
Jingyi Qu
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1738/1/012060
Subject(s) - encoding (memory) , computer science , civil aviation , preprocessor , data set , data pre processing , data mining , convolutional neural network , set (abstract data type) , artificial neural network , aviation , artificial intelligence , machine learning , real time computing , engineering , programming language , aerospace engineering
With the rapid development of civil aviation transportation industry, the passenger throughput in civil aviation is increasing, while the problem of flight delays is becoming more and more serious. For flight delay prediction under big data, deep learning methods can be applied to make high-precision predictions. Since data preprocessing is one of the most important parts, the method based on hybrid encoding is proposed in this paper. Firstly, the flight and meteorological data are fused with the associated primary key, Since weather data has a greater impact on flight delay. Then, the fused data is encoded according to different data types. Min-Max encoding is used for continuous features, and CatBoost encoding is adopted for discrete features respectively. Finally, the data set which has been preprocessed can be put into the deep convolutional neural network ResNet to verify the effect. The experimental results show that the prediction accuracy rate of flight delay level can reach 94.02% on the structured data set after hybrid encoding.