Application of Long Short Term Memory to Predict Flight Delay on Commercial Flights

Penerapan Long Short Term Memory untuk Memprediksi Flight Delay pada Penerbangan Komersial

  • Muhammad Genta Ari Shandi IT Telkom Purwokerto
  • Rifki Adhitama Institut Teknologi Telkom Purwokerto
  • Amalia Beladinna Arifa Institut Teknologi Telkom Purwokerto
Keywords: Departure delay, Flight, Long short term memory, Model, Recurrent neural network

Abstract

Delay in airline services, become an unpleasant experience for passengers who experience it. This study aims to build a model that can predict flight delay (departure) using the Long Short Term Memory method and can find out its performance. In this study there are two scenarios that have different ways of preprocessing. Both of these scenarios produce predictions with error values calculated using Root Mean Squared Error (RMSE), respectively from the first to the second scenario namely: 41, 21. Between the two, the second scenario is better than the first scenario due to extreme data deletion ( anomaly) in the second scenario with an error value using RMSE of 0.116.

Downloads

Download data is not yet available.

References

Kemenhub, Penanganan Keterlambatan Penerbangan (Delay Management) Pada Badan Usaha Angkutan Udara Niaga Berjadwal Di Indonesia. Indonesia: Menteri Perhubungan Republik Indonesia, 2015, hal. 20.

“US Top 40 Airports,” World Airport Codes, 2016. [Daring]. Tersedia pada: https://www.world-airport-codes.com/us-top-40-airports.html. [Diakses: 13-Feb-2020].

D. Meyer, “Heavy rains ground hundreds of flights at NYC airports,” New York Post, 2019. [Daring]. Tersedia pada: https://nypost.com/2019/08/07/heavy-rains-ground-hundreds-of-flights-at-nyc-airports/. [Diakses: 13-Feb-2020].

“Hundreds of NYC-Area Flights Delayed, Canceled Second Day in a Row,” NBC New York, 2019. [Daring]. Tersedia pada: https://www.nbcnewyork.com/news/local/winter-storm-covers-new-jersey-roads-delays-new-york-flights/2235023/. [Diakses: 13-Feb-2020].

U. S. D. of Transportation, “Reporting Carrier On-Time Performance,” 2019. [Daring]. Tersedia pada: https://transtats.bts.gov/. [Diakses: 01-Feb-2020].

A. Ahmad, “Mengenal Artificial Intelligence, Machine Learning, Neural Network, dan Deep Learning,” J. Teknol. Indones., no. October, hal. 3, 2017.

P. Sugiartawan, R. Pulungan, dan A. Kartika, “Prediction by a Hybrid of Wavelet Transform and Long-Short-Term-Memory Neural Network,” Int. J. Adv. Comput. Sci. Appl., vol. 8, no. 2, 2017.

P. Sugiartawan, A. A. Jiwa Permana, dan P. I. Prakoso, “Forecasting Kunjungan Wisatawan Dengan Long Short Term Memory (LSTM),” J. Sist. Inf. dan Komput. Terap. Indones., vol. 1, no. 1, hal. 43–52, 2018.

S. Hochreiter, “Long Short-Term Memory,” vol. 1780, hal. 1735–1780, 1997.

J. Zheng, C. Xu, Z. Zhang, dan X. Li, “Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network,” 2017 51st Annu. Conf. Inf. Sci. Syst. CISS 2017, hal. 1–6, 2017.

L. Chen dan C. Min, “A Comparisons of BKT, RNN and LSTM for Learning Gain Prediction,” Aied 2017, vol. 1, hal. 650–655, 2017.

R. Zhao, J. Wang, R. Yan, dan K. Mao, “Machine health monitoring with LSTM networks,” Proc. Int. Conf. Sens. Technol. ICST, 2016.

Published
2020-06-20
How to Cite
Ari Shandi, M. G., Rifki Adhitama, & Amalia Beladinna Arifa. (2020). Application of Long Short Term Memory to Predict Flight Delay on Commercial Flights. Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 4(3), 447 - 453. https://doi.org/10.29207/resti.v4i3.1759
Section
Artikel Rekayasa Sistem Informasi