Abstract
We describe extracting people significant places for mobility analysis from a real-world large scale dataset collected by mobile operator. The total data consisted of 9.2 billion GPS points including approximately 1.5 million individual user trajectories accumulated for a year. We conducted the experiments on the dataset by using stay point extraction and density based cluster to extracting significant places from a sparse dataset. We also proposed an approach to derive types of locations especially home and work place by using classification features and inference model. The relevant features including ranking in clusters, number of days that data appeared, night time, and day time were identified and evaluated. Several inference models are evaluated in the experiment. With limited number of ground truth data, Random Forest model could achieve 99.2% accuracy for inferring home and work location. Additionally, Spatial Population Census were employed to indirectly compare the classification results with ground truth. Furthermore, to enable real-world application, we presented a technique to utilize Hadoop/Hive, a cloud computing platform, allowing full-scale data processing. As a result, the proposed method is able to discover home and work locations of users with positive results after checking the census. In addition, by using Hadoop platform, an extraction process is able to perform on the whole dataset with only about 1.53 days compared with a single application which took 32.73 days.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ashbrook, D., Starner, T.: Using GPS to learn significant locations and predict movement across multiple users. Pers. Ubiquitous Comput. 7, 275–286 (2003). https://doi.org/10.1007/s00779-003-0240-0
Zhou, C., Frankowski, D., Ludford, P., et al.: Discovering personally meaningful places. ACM Trans. Inf. Syst. 25, 12–es (2007). https://doi.org/10.1145/1247715.1247718
Liao, L., Patterson, D.J., Fox, D., Kautz, H.: Building personal maps from GPS data. Annal. New York Acad. Sci. 1093, 249–65 (2006). https://doi.org/10.1196/annals.1382.017
Zheng, Y, et al.: Mining interesting location and travel sequences from GPS trajectories. In: Proceedings of WWW, Madrid, Spain, pp. 791–800. ACM Press (2009)
Montoliu, R., Blom, J., Gatica-Perez, D.: Discovering places of interest in everyday life from smartphone data. Multimed. Tools Appl. (2012). https://doi.org/10.1007/s11042-011-0982-z
Kirmse, A., Bellver, P., Shuma, J.: Extracting patterns from location history. In: Proceedings of ACM SIGSPATIAL, Chicago, USA, pp. 397–400 (2011)
Jinnan, Y., Sheng, W.: Studies on application of cloud computing techniques in GIS. In: Proceedings of IGASS 2010, China, pp. 492–495 (2010)
Buyya, R., Yeo, C., Venugopal, S., et al.: Cloud computing and emerging IT platforms: vision, hype, and reality for delivering computing as the 5th utility. Future Gener. Comput. Syst. 25, 599–616 (2009). https://doi.org/10.1016/j.future.2008.12.001
Hadoop Project: http://hadoop.apache.org/
Hive Project: http://hive.apache.org/
Thusoo, A., Sarma, J., Jain, N., et al.: Hive—a petabyte scale data warehouse using hadoop. In: Proceedings of ICDE 2010, pp. 996–1005 (2010)
Witayangkurn, A., Horanont, T., Shibasaki, R.: Performance comparisons of spatial data processing techniques for a large scale mobile phone dataset. In: Proceedings of the 3rd International Conference on Computing for Geospatial Research and Applications—COMGeo’12 1 (2012). https://doi.org/10.1145/2345316.2345346
Acknowledgements
The work described in this paper was conducted at Shibasaki Laboratory with an agreement from Zenrin Data Com to use mobile phone dataset of personal navigation service users for the research. This work was supported by GRENE (Environmental Information) project of MEXT (Ministry of Education, Culture, Sports, Science and Technology).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Witayangkurn, A., Horanont, T., Nagai, M., Shibasaki, R. (2018). Large Scale Mobility Analysis: Extracting Significant Places Using Hadoop/Hive and Spatial Processing. In: Theeramunkong, T., Skulimowski, A., Yuizono, T., Kunifuji, S. (eds) Recent Advances and Future Prospects in Knowledge, Information and Creativity Support Systems. KICSS 2015. Advances in Intelligent Systems and Computing, vol 685. Springer, Cham. https://doi.org/10.1007/978-3-319-70019-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-70019-9_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70018-2
Online ISBN: 978-3-319-70019-9
eBook Packages: EngineeringEngineering (R0)