Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Identifying intermediary modes from GPS data
  • Publication Type:
    Conference presentation
  • Publication Sub Type:
  • Authors:
    Bolbol A, CHENG T, Tsapakis I, Skarlatidou A
  • Date:
  • Status:
  • Name of Conference:
    Annual Meeting of the Association of American Geographers
  • Conference place:
    Seattle, USA
  • Conference start date:
  • Conference finish date:
  • Keywords:
    Spatiotemporal behaviour, travel mode, GIS, GPS, classification
Travel behaviour is a very interesting yet complex activity that happens everyday. It is quite challenging to model due to its complexity, diversity and size of the data. Understanding this kind of activity is important for applications like strike responses, tourist activity and environmental issues. Some research attempts to infer the Travel Mode from positional data such as GPS tracks in order to achieve this understanding. However, these attempts have shortcomings such as dismissing the stationary mode as a mode on its own, rather than an intermediary pause of motion within other modes. This leads to higher errors due to velocity values confusion, and to difficulty to assign other modes based on the logical probability of mode sequences. Another problem is the high confusion between both the walking mode and the stationary modes. That is due to the similarity of velocity values for both modes. In this work, we attempt to identify walking and stationary modes out of a GPS data session. We focus on these two specific modes due to their high frequency of occurrence within most GPS track sessions. That is also because they are considered to be the intermediate transitional modes between other types of mode within a typical GPS trip. We use a combined Spatio-temporal and spatial clustering method to identify the stationary mode. On the other hand; we use Support Vector Classification (SVC) to separate the walking mode. The results reveal an accuracy of (89%) for identifying the stationary mode, and (90%) accuracy for the walking mode.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Dept of Civil, Environ &Geomatic Eng
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by