Comparing two hybrid neural network models to predict real-world bus travel time

Research output: Journal contributionsConference article in journalResearch

Authors

  • Thummaporn Nimpanomprasert
  • Lin Xie
  • Natalia Kliewer
In order to enhance the efficiency and reliability of bus transportation systems, it is important to predict travel time precisely in the planning phase. With the precise prediction of bus travel times, the cost can be reduced for bus companies, such as from planning fixed buffer times between trips, while a better service can be provided for passengers. In this study, historical bus travel data from a bus line of the HOCHBAHN bus company in Germany in 2019 are used for the analysis. We develop two neural network models, namely multilayer perceptrons and a long short-term memory neural network, for predicting the bus travel time between timepoints for a trip occurring at a given time of day, on a given day of the week, and in given weather conditions. Both neural networks are combined with a genetic algorithm and a Kalman filter to improve accuracy. The genetic algorithm is implemented to tune the neural network parameters, such as the number of hidden layers and neurons in a hidden layer, while the Kalman filter algorithm is used to adjust the travel time prediction for the next trip using the latest bus operation information. In the experiment, we test our models month by month and split data for each month into three parts: the data of the first two weeks for training, one week for validation and the last week for prediction. The experiment results show that the hybrid model is powerful for predicting the bus travel time. In particular, the combination of the multilayer perceptrons with the genetic algorithm and Kalman filter provides the best travel time prediction (with an improvement of 56.2% compared with the planned bus travel time from the bus company). In order to make a recommendation for bus companies to plan vehicles with more accurate bus travel times, we test our hybrid models with larger training sets to predict the travel times e.g. in August. However, due to the structure of the planning problem, the plan for buses should be estimated before a new month begins. We cannot consider the real information during the planning, therefore we apply our hybrid models without the Kalman filter and they provide on average about 26% improvement compared with the planned travel time.
Original languageEnglish
JournalTransportation Research Procedia
Volume62
Pages (from-to)393-400
Number of pages8
ISSN2352-1457
DOIs
Publication statusPublished - 01.01.2022

Bibliographical note

Funding Information:
The authors want to greatly thank HOCHBAHN for providing us with data for the analysis. This work is a contribution to the “Robust integrated vehicle scheduling, crew scheduling and rostering in public bus transit” project, which is funded by the German Research Foundation grants KL 2152/7-1 and LX 156/2-1.

Publisher Copyright:
© 2022 Elsevier B.V.. All rights reserved.

    Research areas

  • Informatics
  • Business informatics - bus travel time predication, multilayer perceptions, long short-term memory neutral network, genetic algorithm, Kalmann filter

Documents

DOI

Recently viewed

Publications

  1. Quantum computing
  2. Validation of Inspection Frameworks and Methods
  3. Audio-Hacks
  4. Exploring the efficacy of metabarcoding and non-target screening for detecting treated wastewater
  5. Differences of Four Work-Related Behavior and Experience Patterns in Work Ability and Other Work-Related Perceptions in a Finance Company
  6. Estimated substitution elasticities of a nested CES production function approach for Germany
  7. THE PARALLAX OF INDIVIDUATION
  8. Phase Shift APOD and POD Control Technique in Multi-Level Inverters to Mitigate Total Harmonic Distortion
  9. Exploring the Uncanny-Valley-Effect in Affective Human-Robot Interaction
  10. Spatio-Temporal Convolution Kernels
  11. Effects of maize roots on aggregate stability and enzyme activities in soil
  12. Octanol-Water Partition Coefficient Measurement by a Simple 1H NMR Method
  13. Gaussian trajectories in motion control for camless engines
  14. Optical 3D laser measurement system for navigation of autonomous mobile robot
  15. User Authentication via Multifaceted Mouse Movements and Outlier Exposure
  16. Implementation of a Blended-Learning Course as Part of Faculty Development
  17. Adaptive capacity and learning to learn as leverage for social-ecological resilience
  18. The Framework for Inclusive Science Education
  19. Gamma GAMM applied on tree growth data
  20. Joint Proceedings of Scholarly QALD 2023 and SemREC 2023 co-located with 22nd International Semantic Web Conference ISWC 2023
  21. Complementing AAI at the meso level
  22. A Process Perspective on Organizational Failure
  23. Fallstudie
  24. From Enterprise Architecture to Business Ecosystem Architecture