ABSTRACT
Understanding human mobility is important for planning and delivering various services in urban area. An important element for mobility understanding is to understand the context in which the movement takes place. In this direction, we propose a method for identifying significant locations and time periods along a bus route. The significance is based on special characteristics that locations have during specific time periods as determined from their effect of these locations on the movement of the bus. The method extracts discriminative features from the space, time and other selected attributes and then classifies locations and time periods into 5 significance classes. The classes are then rendered in different views for discovering and understanding patterns. The novelty of the method is an explicit consideration of the time dimension at different granularity levels and a visualization that facilitates comparison across the space and time dimensions while avoiding a visual clutter. We demonstrate the applicability of our approach by applying it on a large set of bus trajectories.
- Andrienko, G., Andrienko, N., Hurter, C., Rinzivillo, S., and Wrobel, S. 2013. Scalable Analysis of Movement Data for Extracting and Exploring Significant Places. IEEE Trans. Visual Comput. Graphics 19 (7): 1078 -- 1094. Google ScholarDigital Library
- Barbosa, L., Kormáksson, M., Vieira, M. R., Tavares, R. L., and Zadrozny, B. 2014. Vistradas: Visual analytics for urban trajectory data. In Proceedings of the XV Brazilian Symposium on GeoInformatics (São Paulo, Brazil, 2014).Google Scholar
- Dodge, S., Weibel, R., Ahearn, S. C., Buchin, M., and Miller, J.A. 2016. Analysis of movement data. International Journal of Geographical Information Science 30 (5):825--834. Google ScholarDigital Library
- Dublinked. 2013. Dublin Bus GPS sample data from Dublin City Council (Insight Project). Retrieved: April 11, 2016, from https://data.dublinked.ie/dataset/dublin-bus-gps-sample-data-from-dublin-city-council-insight-projectGoogle Scholar
- Itoh, M., Yokoyama, D., Toyoda, M., Tomita, Y., Kawamura, S., Kitsuregawa, M. 2016. Visual Exploration of Changes in Passenger Flows and Tweets on Mega-City Metro Network. IEEE Trans. Big Data 2 (1): 85--99. Google ScholarCross Ref
- Laube, P. 2014. Computational Movement Analysis. Springer International Publishing. Google ScholarCross Ref
- Liu, H., Gao, Y., Lu, L., Liu, S., Qu, H., and Ni, L. M. 2011. Visual analysis of route diversity. In Proceedings of the IEEE Conference on Visual Analytics Science and Technology (Providence, RI, 2011). IEEE, 171--180. Google ScholarCross Ref
- Lv, M., Chen, L., and Chen, G. 2012. Discovering personally semantic places from GPS trajectories. In Proc. of CIKM "12. ACM, New York, NY, 1552--1556. Google ScholarDigital Library
- Orellana, D., Wachowicz, M., Andrienko, N., and Andrienko, G. 2009. Uncovering Interaction Patterns in Mobile Outdoor Gaming. In Proc. of GEOWS'09. IEEE, 177--182. Google ScholarDigital Library
- Reumers,S., Liu,F., Janssens,D., Cools,M. and Wets,G. (2013). Semantic annotation of global positioning system traces: Activity type inference. Transp. Res. Rec. 2383,35--43. Google ScholarCross Ref
- Zeng, W., Fu, C.-W., Arisona, S., Erath, A., and Qu, H. 2014. Visualizing mobility of public transportation system. IEEE Trans. Visual Comput. Graphics 20 (12): 1833--1842. Google ScholarCross Ref
Index Terms
- A visual and computational analysis approach for exploring significant locations and time periods along a bus route
Recommendations
A visual and computational analysis approach for exploring significant locations and time periods along a bus route
IWCTS '16: Proceedings of the 9th ACM SIGSPATIAL International Workshop on Computational Transportation ScienceUnderstanding human mobility is important for planning and delivering various services in urban area. An important element for mobility understanding is to understand the context in which the movement takes place. In this direction, we propose a method ...
A Novel Visualization Approach for Data-Mining-Related Classification
IV '09: Proceedings of the 2009 13th International Conference Information VisualisationClassification and categorization are common tasks in data mining and knowledge discovery. Visualizations of classification models can create understanding and trust in data mining models. However, existing visualizations are often complex or restricted ...
Exploring trajectory-driven local geographic topics in foursquare
UbiComp '12: Proceedings of the 2012 ACM Conference on Ubiquitous ComputingThe location based social networking services (LBSNSs) are becoming very popular today. In LBSNSs, such as Foursquare, users can explore their places of interests around their current locations, check in at these places to share their locations with ...
Comments