Research Article
Extracting Land-Use Patterns using Location Data from Smartphones
@INPROCEEDINGS{10.4108/icst.urb-iot.2014.257220, author={Kentaro Nishi and Kota Tsubouchi and Masamichi Shimosaka}, title={Extracting Land-Use Patterns using Location Data from Smartphones}, proceedings={The First International Conference on IoT in Urban Space}, publisher={ACM}, proceedings_a={URB-IOT}, year={2014}, month={11}, keywords={data mining land-use patterns spatio-temporal data}, doi={10.4108/icst.urb-iot.2014.257220} }- Kentaro Nishi
Kota Tsubouchi
Masamichi Shimosaka
Year: 2014
Extracting Land-Use Patterns using Location Data from Smartphones
URB-IOT
ICST
DOI: 10.4108/icst.urb-iot.2014.257220
Abstract
This paper proposes an approach to extract area-by-area and daily land-use patterns using location data obtained from users of Yahoo! Japan's smartphone applications. Information used for extracting patterns is extracted from only location data. Temporal transition in the number of people in areas throughout a day are focused to explore land-use patterns.
In the clustering process, an infinite Gaussian mixture model with Dirichlet process mixtures is used, which can be used to discover the appropriate number of patterns. Experiments were conducted in 34 areas over 56 consecutive days. This means 1,904 conditions were studied. The results of our experiments show that our approach successfully extracts land-use patterns using the temporal transition in a population, which match the metadata assigned manually.
The results also reveal that additional features which are estimated only from spatio-temporal data helps us obtain more natural clustering results.