Neural networks trained with WiFi traces to predict airport passenger behavior

The use of neural networks to predict airport passenger activity choices inside the terminal is presented in this paper. Three network architectures are proposed: Feedforward Neural Networks (FNN), Long Short-Term Memory (LSTM) networks, and a combination of the two. Inputs to these models are both static (passenger and trip characteristics) and dynamic (real-time passenger tracking). A real-world case study exemplifies the application of these models, using anonymous WiFi traces collected at Bologna Airport to train the networks. The performance of the models were evaluated according to the misclassification rate of passenger activity choices. In the LSTM approach, two different multi-step forecasting strategies are tested. According to our findings, the direct LSTM approach provides better results than the FNN, especially when the prediction horizon is relatively short (20 minutes or less).

[1]  Volker Tresp,et al.  Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks , 2016, 2016 IEEE International Conference on Healthcare Informatics (ICHI).

[2]  Antonin Danalet.  Activity choice modeling for pedestrian facilities , 2015 .

[3]  Ching-Fu Chen,et al.  Passengers' shopping motivations and commercial activities at airports - The moderating effects of time pressure and impulse buying tendency , 2013 .

[4]  Geoffrey E. Hinton,et al.  Generating Text with Recurrent Neural Networks , 2011, ICML.

[5]  Jacek Skorupski,et al.  Managing the process of passenger security control at an airport using the fuzzy inference system , 2016, Expert Syst. Appl..

[6]  S. M. T. Fatemi Ghomi,et al.  Airline passenger forecasting using neural networks and Box-Jenkins , 2016, 2016 12th International Conference on Industrial Engineering (ICIE).

[7]  Le Minh Kieu,et al.  Deep learning methods in transportation domain: a review , 2018, IET Intelligent Transport Systems.

[8]  Filipe Moura,et al.  Modelling Passengers’ Activity Choice in Airport Terminal before the Security Checkpoint: The Case of Portela Airport in Lisbon , 2015 .

[9]  Vesna Popovic,et al.  Towards airport passenger experience models , 2010 .

[10]  Mineichi Kudo,et al.  Multidimensional curve classification using passing-through regions , 1999, Pattern Recognit. Lett..

[11]  Abhinav Saxena,et al.  Damage propagation modeling for aircraft engine run-to-failure simulation , 2008, 2008 International Conference on Prognostics and Health Management.

[12]  Carlos F. Gomes,et al.  The effects of service quality dimensions and passenger characteristics on passenger's overall satisfaction with an airport , 2015 .

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Guido Guizzi,et al.  A discrete event simulation to model passenger flow in the airport terminal , 2009 .

[15]  Marc Sanchez Net,et al.  System architecture for tracking passengers inside an airport terminal using RFID , 2018, 2018 IEEE Aerospace Conference.

[16]  Lesley Strawderman,et al.  An analysis of activity scheduling behavior of airport travelers , 2014, Comput. Ind. Eng..

[17]  Yi-Shih Chung,et al.  Air passengers' shopping motivation and information seeking behaviour , 2013 .

[18]  Yang Jie,et al.  Prediction for Air Route Passenger Flow Based on a Grey Prediction Model , 2016, 2016 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC).

[19]  Terrence L. Fine,et al.  Feedforward Neural Network Methodology , 1999, Information Science and Statistics.

[20]  Luca Mantecchini,et al.  An Agent Framework to Support Air Passengers in Departure Terminals , 2018, WOA.

[21]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[22]  Rob J. Hyndman,et al.  Recursive and direct multi-step forecasting: the best of both worlds , 2012 .

[23]  Hong Jiang,et al.  Model of passenger behavior choice under flight delay based on dynamic reference point , 2019, Journal of Air Transport Management.

[24]  Jing Li,et al.  Airport Passenger Flow Forecast Based on the Wavelet Neural Network Model , 2018, ICDLT '18.

[25]  Michael Schultz,et al.  Passenger Dynamics at Airport Terminal Environment , 2010 .

[26]  Luca Mantecchini,et al.  Airport Passenger Arrival Process: Estimation of Earliness Arrival Functions , 2019, Transportation Research Procedia.

[27]  Riccardo Rossi,et al.  How to drive passenger airport experience: a decision support system based on user profile , 2018 .

[28]  E. Torres,et al.  Passenger waiting time in an airport and expenditure carried out in the commercial area , 2005 .

[29]  Peter C. Y. Chen,et al.  LSTM network: a deep learning approach for short-term traffic forecast , 2017 .

[30]  Gianluca Bontempi,et al.  Machine Learning Strategies for Time Series Forecasting , 2012, eBISS.

[31]  Wenbo Ma,et al.  Agent-based model of passenger flows in airport terminals , 2013 .