The Air Transport Hybrid Forecasting Based on Aircraft Types
Keywords:
Air transport, Forecasting, Air traffic, Airport, AircraftAbstract
This research aims to: (1) create an appropriate hybrid forecasting equation for each type of aircraft; and (2) forecast each type of aircraft. Each type of aircraft’s data is collected from Phuket International Airport over a period of 336 hours (14 days) for train data and 24 hours (1 day) for test data, and then the data is analyzed by Microsoft Excel and Microsoft Visual Basic for Applications. Result found: an appropriate hybrid forecasting equation comes from the simulated annealing algorithm and the gradient descent algorithm, which afterward forecasted all types of aircraft. Code B is 100 percent accurate; Code C is 82.53 percent accurate; Code D is 100 percent accurate, and Code E is 100 percent accurate.
References
Aksornkitti, B., Santisiri, W., & Wongwiwat, A. (2020). The analysis and comparison of factors in delay and flight on time, one airline of Asia Region. Rajamangala University of Technology Tawan–Ok Social Science Journal, 9(1), 70–77. (in Thai)
Arthakamol, W., & Sriwong, W. (2021). Personal communication: Air Traffic Flow Management--ATFM. Aeronautical Radio of Thailand Company Limited. (in Thai)
Chantrapha, U., & Kantanantha, N. (2021). Forecasting export values of cars, equipment and parts of Thailand by Time series Methods. Thai Journal of Operation Research, 9(2), 12–20. (in Thai)
Dantas, T. M., Oliveria, F. L. C., & Repolho, H. M. V. (2017). Air transportation demand forecast through bagging Holt–Winters method. Journal of Air Transport Management, 59(2017), 116–123. doi: 10.1016/j.jairtraman.2016.12.006
GeeksforGeeks. (2022). Introduction to hill climbing: Artificial intelligence. Retrieved from https://www.geeksforgeeks.org/introduction-hill-climbing-artificial-intelligence
Huangsuwan, S., Chansawat, B., & Noitonglek, K. (2021). Commercial aviation: Social and environmental issues. EAU Heritage Journal Science and Technology, 16(1), 1–15. (in Thai)
Hutem, T., Somtom, K., Luangsuwan, W., & Tantiphanwadi, P. (2021). The use of simulated annealing algorithm for farmer’s freight vehicle route design. Thai Industrial Engineering Network Journal, 7(1), 93–106. (in Thai)
Hyndman, R. J., & Athanasopoulos, G. (2021). Forecasting: Principle and practice. Retrieved from. https://otexts.com/fpp3/
Menon, A. (2018). Linear regression using gradient descent. Retrieved from https://towardsdatascience.com/linear-regression-using-gradient-descent-97a6c8700931
Netisopakul, P., & Supasa, N. (2019). Appropriate model analysis for garment sales forecasting. MUT Journal of Business Administration, 16(2), 77–96. (in Thai)
Phaettho, P., & Lekhavat, S. (2021). Applying mathematical modelling for job shop scheduling problem: A case study of automotive part factory. Thai Journal of Operation Research, 9(2), 82–92. (in Thai)
The Civil Aviation Authority of Thailand. (2020). Thailand’s air travel demand forecasting. Retrieved from https://www.caat.or.th/th/archives/53358 (in Thai)
The International civil aviation organization. (2018). Annex 14th, aerodrome–volume I Aerodrome design and operation (8th ed.). Canada: International Civil Aviation Organization (ICAO)
Sutthison, T., & Haruay, S. (2020). The development of a hybrid model for forecasting the time series of monthly household electrical distribution units of people in the Northeast, Thailand. The Journal of KMUTNB, 30(4), 630–644. (in Thai)
Ventura, L. M. B., Pinto, F. O., Soares, L. M., Luna, A. S., & Gioda, A. (2019). Forecast of daily PM 2.5 concentration applying artificial neural network and Holt–Winter model. Air Quality Atmosphere & Health, 12(2019), 317–325. doi: https://doi.org/10.1007/s11869-018-00660-x
