Evaluation of Zones in Himeji City for Foreign Tourists Using Support Vector Machines

  • Naotake Kamiura University of Hyogo
  • Teijiro Isokawa University of Hyogo
  • Satoru Hakukawa University of Hyogo
Keywords: Foreign tourists, Himeji City, Support vector machines, Tourism evaluation


In this paper, we present a method of evaluating zones in Himeji City, Japan, from the viewpoint of sight scene resources, to promote the tourism for foreigners visiting that city. Our method is based on the data classification conducted by support vector machines (SVMs for short). We prepare data presented to discrimination models constructed by SVM learning from tourist numbers totaled by country. In other words, the element value in the data equals the number of the tourists departing from some country and visiting some zone in Himeji City. Our model judges whether a zone of one square kilometer is worth a visit for the tourists departing from each of the following countries: France, United Kingdom (UK for short), Germany, Spain, Singapore, Australia, and United States of America (USA for short). It is established, from experimental results, that our method achieves substantially high averaged values on recall, precision, and F-measure when data to train our model are prepared from numbers of the tourists departing from six countries out of the above seven ones considered to be of importance in terms of tourism promotion.


Numbers of tourists visiting Japan and Japanese Nationals Departing from Japan, https://www.mlit.go.jp/kankocho/siryou/toukei/in_out.html (in Japanese), Dec. 27, 2021(Final reference time).

The value of travel consumption of inbound tourists in fiscal 2019, https://www.mlit.go.jp/kankocho/siryou/toukei/content/001335741.pdf (in Japanese), Dec. 27, 2021 (Final

reference time).

https://www.mlit.go.jp/common/001270416.pdf (in Japanese), pp.2-31-2.36, Dec. 27, 2021(Final reference time).

Business Policy of Public Interest Incorporated Association, Himeji Convention Bureau for Tourism in fiscal 2019, https://himeji-kanko.jp/pdf/bureau/r01-keikaku.pdf (in Japanese), Dec. 27, 2021 (Final reference time).

V. N. Vapnik, Statistical Learning Theory, Wiley, New York, p.281, 1998.

C. Cortes and V. Vapnik,“Support Vector networks,” Machine Learning, Vol. 20, pp. 273-297, 1995.

On Practical Application of Spatial Statistics for Mobile Terminals, https://www.nttdocomo.co.jp/binary/pdf/info/notice/page/130906_00.pdf (in Japanese) Dec. 27, 2021 (Final reference time).

T. Onoda, Science of the Intellect - Support Vector Machine (in Japanese), Ohmsha, Ltd., p. 130, 2007.

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research 12, 2011, pp.2825-2830.

C. C. Chang and C-J. Lin, “LIBSVM: A Library for Support Vector Machines,” ACM Transactions on Intelligent Systems and Technology, https://doi.org/10.1145/1961189.1961199, Vol. 2, No. 3, 2011, pp.3-5.

R. Story, “Folium,” https://python-visualization.github.io/folium, 2013, (Dec. 27, 2021 : Final reference time).

Technical Papers