ANALYSIS OF CONTRIBUTING PARAMETERS OF AIR ROUTE DEMAND USING ARTIFICIAL NEURAL NETWORK APPROACH AND ITS IMPACT OF FLIGHT OPERATIONS
The accuracy of forecasting the number of air passengers is crucial for all parties, including airlines, regulators, manufacturers, and airports. Air Traffic Forecasting will be the base of how airlines do their business, manufactures produce aircrafts that match with the market, regulators regulate...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Subjects: | |
| Online Access: | https://digilib.itb.ac.id/gdl/view/71379 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | The accuracy of forecasting the number of air passengers is crucial for all parties, including airlines, regulators, manufacturers, and airports. Air Traffic Forecasting will be the base of how airlines do their business, manufactures produce aircrafts that match with the market, regulators regulate that related to flight route, and etc. Therefore, the objection of this research is to create a most accurate model to forecast air traffic and analyze variables that contribute to air traffic. The model use in this research is Artificial Neural Network. Tuning hyperparameter is needed in developing Artificial Neural Network model so the model doesn’t produce overfitting and underfitting. The method for tuning the hyperparameters used is Bayesian optimization by determining the number of hidden layers, the number of neurons in the hidden layer, the activation function, the optimizer, the learning rate, the number of batch sizes, and the number of epochs. The result shows that GDP and number of population had a significant effect on the number of passengers. Based on sesntivity analysis, it shows that changes in Human Development Index, number of population, and Room Occupancy Rate are very sensitive to changes in the number of passengers. |
|---|