Incorporating MNL Model into Random Forest for Travel Mode Detection

Mode choice models have been used widely to forecast the relative probabilities of using available travel modes. These depend on mode-related and traveler-related characteristics. On the other hand, smartphones are increasingly being used to collect sensors’ data relating to trips made after selection of a suitable mode. Such sensors’ data may be correlated with the decision-making process of travelers regarding travel mode selection. Discrete Choice Modelling is used to simulate this decision-making process by computing utilities of various travel alternatives, and then calculating their respective probabilities of being selected. In this paper, multinomial logit (MNL) mode choice model is utilized to enhance the prediction capacity of supervised learning algorithm, i.e., Weighted Random Forest. To make the procedure less energy-intensive, Global Positioning System (GPS) data were used only to locate the origin and destination of any trip to be incorporated in the mode choice model. Afterwards only accelerometer data were utilized in feature selection for the learning algorithm. One tenth of the classified data was used to train the algorithm whereas the rest was used to test it. Results suggested that with incorporation of MNL, the overall prediction accuracy of the learning algorithm was increased from 93.75% to 99.08%.

• Record URL:
  https://doi.org/10.22581/muet1982.2103.04
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/02547821
• Authors:
  • Shafique, Muhammad Awais
  • Hato, Eiji
• Publication Date: 2021-7

Language

• English

Media Info

• Media Type: Digital/other
• Features: References; Tables;
• Pagination: pp 496-501
• Serial:
  • Mehran University Research Journal of Engineering & Technology
  • Volume: 40
  • Issue Number: 3
  • Publisher: Mehran University of Engineering and Technology
  • ISSN: 0254-7821
  • EISSN: 2413-7219
  • Serial URL: https://publications.muet.edu.pk/index.php/muetrj/index
• Publication flags:

  Open Access (libre)

Subject/Index Terms

• TRT Terms: Algorithms; Choice models; Data collection; Forecasting; Global Positioning System; Machine learning; Mode choice; Multinomial logits; Smartphones
• Subject Areas: Highways; Planning and Forecasting; Public Transportation;

Filing Info

• Accession Number: 01778916
• Record Type: Publication
• Files: TRIS
• Created Date: Aug 10 2021 5:24PM