Volume II-4/W2
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-4/W2, 193-198, 2015
https://doi.org/10.5194/isprsannals-II-4-W2-193-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., II-4/W2, 193-198, 2015
https://doi.org/10.5194/isprsannals-II-4-W2-193-2015
© Author(s) 2015. This work is distributed under
the Creative Commons Attribution 3.0 License.

  14 Jul 2015

14 Jul 2015

DYNAMIC TRIP ATTRACTION ESTIMATION WITH LOCATION BASED SOCIAL NETWORK DATA BALANCING BETWEEN TIME OF DAY VARIATIONS AND ZONAL DIFFERENCES

N. W. Hu1 and P. J. Jin2 N. W. Hu and P. J. Jin
  • 1Department of Civil and Environmental Engineering, Rutgers, the State University of New Jersey, CoRE 736, 96 Frelinghuysen Road, Piscataway, NJ 08854-8018, USA
  • 2Department of Civil and Environmental Engineering, Rutgers, the State University of New Jersey, CoRE 613, 96 Frelinghuysen Road, Piscataway, NJ 08854-8018, USA

Keywords: Dynamic Trip Attraction, Time of Day, Location Based Social Networking, Big Data

Abstract. The emergence of location based social network (LBSN) services make it accessible and affordable to study individuals’ mobility patterns in a fine-grained level. Via mobile devices, LBSN enables the availability of large-scale location-sensitive data with spatial and temporal context dimensions, which is capable of the potential to provide traffic patterns with significantly higher spatial and temporal resolution at a much lower cost than can be achieved by traditional methods. In this paper, the Foursquare LBSN data was applied to analyze the trip attraction for the urban area in Austin, Texas, USA. We explore one time-dependent function to validate the LBSN’s data with the origin-destination matrix regarded as the ground truth data. The objective of this paper is to investigate one new validation method for trip distribution. The results illustrate the promising potential of studying the dynamic trip attraction estimation with LBSN data for urban trip pattern analysis and monitoring.