Statistical learning of air passenger traffic at the Murtala Muhammed International Airport, Nigeria / Christopher Godwin Udomboso and Gabriel Olugbenga Ojo
Based on previous studies, aviation affair needs reliable forecasts of air passenger traffic flow. In this research, the performance of Artificial Neural Network (ANN) and Support Vector Machine (SVM) models were investigated on predicting air passenger traffic in the Murtala International Airport...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/56159/1/56159.pdf https://ir.uitm.edu.my/id/eprint/56159/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Based on previous studies, aviation affair needs reliable forecasts of air passenger traffic flow. In this research, the performance of Artificial Neural Network (ANN) and Support Vector Machine (SVM) models were investigated on predicting air passenger traffic in the Murtala International Airport
Nigeria. Past eleven years’ monthly data (2007-2018) obtained from Statistics Department of the Nigerian Airspace Management Agency (NAMA), MMIA, Lagos was used. ANN models with backpropagation steepest descent estimation techniques were compared with the SVM models with
different kernels. The comparative evaluation of these adopted models focused basically on a Root Mean Square Error (RMSE) statistical loss function. The efficiency of the ANN model was found better than that of the SVM model in predicting the domestic air passenger traffic flow, while the SVM model predicted the foreign air passenger traffic flow more efficiently than the ANN model. |
|---|