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

Activities

  1. A utilitarian notion of responsibility for sustainability
  2. Responding ASAP? The Role of Age in Dealing with Availability and Response Expectations
  3. Eine Podiumsdiskussion zu Fracking
  4. Negotiating normativity: discourses of (non) belonging and (non) coincidences in the context of transnational adoption
  5. German Teaching and Learning Materials - Lifelong Learning and Competency-Based Instruction
  6. 'Can you play a new CD,please?' Speech act representation in EFL textbooks: An interlanguage pragmatic appraisal (Universität Gießen, invited talk)
  7. What if Civilization Collapses? Management Scholarship in and for Deep Adaption
  8. Can we solve the climate crisis? Contributions from artS, technology and science
  9. WK ORG Workshop - WK ORG 2019
  10. How to make use of evidence based management in entrepreneurship: The example of Personal Initiative Training
  11. Effective working hours and wages: the case of downward adjustment via paid absenteeism
  12. Collective Decisions
  13. “Visual Rhetoric as a three-dimensional practice”
  14. Licht im Dunkeln 2005
  15. 5th European Conference of Apidology - EurBee 2012
  16. Reactivity on a student-centered recording system – a video-based longitudinal study in primary education
  17. Tolerating and inducing temporal asynchronicity in complex innovation journeys
  18. Personal care products as source for micropollutants in Greywater-Identification, quantification and on-site treatment
  19. Sustainability Reporting on the World Wide Web: Developments in Germany
  20. Applied Vegetation Science (Zeitschrift)
  21. Universität Zürich
  22. Deferred Compensation Schemes, Fairness Concerns, and Employment of Older Workers
  23. Forschungspraxis und Selbstsorge in Sensitive Research
  24. Biological Oxidation of Iron with Various Oxidants.
  25. Purpuseful Work Symposium