Prediction of the Flight Delay Based on Neural Network and Support Vector Machine: A Comparative Study

Yuxin Huang

doi:10.47297/taposatWSP2633-456910.20230402

PDF
Export
Share
Collection
Album

Prediction of the Flight Delay Based on Neural Network and Support Vector Machine: A Comparative Study

Volume 4, Issue 2

Views: 0 Downloads: 0

Prediction of the Flight Delay Based on Neural Network and Support Vector Machine: A Comparative Study
Tan Kah Kee College of Xiamen University,Xiamen,China,363105
Vol. 4, Issue 2, Pages: 68-72(2023)
Published： 2023 ，
DOI：10.47297/taposatWSP2633-456910.20230402

Full txt

Yuxin Huang. (2023). Prediction of the Flight Delay Based on Neural Network and Support Vector Machine: A Comparative Study. Theory and Practice of Science and Technology, 4(2), 68-72.
DOI：

Yuxin Huang. (2023). Prediction of the Flight Delay Based on Neural Network and Support Vector Machine: A Comparative Study. Theory and Practice of Science and Technology, 4(2), 68-72. DOI： 10.47297/taposatWSP2633-456910.20230402.

摘要

Abstract

This paper training a model which aims to predict the flight’s delay based on the ANN and SVM

which are current mainstream machine learning models. We use the dataset of the flight delay from Kaggle and divided it as three parts: 0.7:0.15:0.15

for training dataset

validation and test dataset. The mean relative error of the prediction model are 18.6% and 21.2% by ANN and SVM

and the time cost of predicting a single roughness value based on cutting parameters are about 100.4ms and 58.5ms with ANN and SVM. Based on the experimental results

these two models can accurately and efficiently predict the delay and the ANN model have a little better accuracy than the SVM.

关键词

Keywords

Flight delayNeural networkSupport vector machine

references

Moreira, L., Dantas, C., Oliveira, L., et al. (2018) On evaluating data preprocessing methods for machine learning models for flight delays. In: IJCNN. Rio de Janeiro. pp. 1-8.[2] Zhang, S., Li X., Zong M., et al. (2017) Efficient kNN classification with different numbers of nearest neighbors. IEEE transactions on neural networks and learning systems, 29(5): 1774-85.[3] Sun, J., Wu, Z., Yin, Z., et al. (2018) SVM-CNN-Based fusion algorithm for vehicle navigation considering atypical observations. IEEE signal processing letters, 26(2): 212-16.[4] Pamplona, D.A., Li, W., Barros, A.G., et al. (2018) Supervised neural network with multilevel input layers for predicting of air traffic delays. In: IJCNN. Rio de Janeiro. pp. 1-6.[5] Indolia, S., Goswami, A.K., Mishra, S.P., et al. (2018) Conceptual understanding of convolutional neural network-a deep learning approach. Procedia computer science, 132: 679-88.

Alert me when the article has been cited

Submit

Two Multi-Unit Artificial Intelligence Decision Modes in Video Games：A Comparison

A CNN-based Physical Layer Design for Communications System

Related Author

No data

Related Institution

School of Information Engineering, Wuhan University of Technology

University of Electronic Science and Technology of China (UESTC)University of Glasgow

⁰