Deep Learning-based Prediction Method for People Flows and Their Anomalies

Shigeru Takano, Maiya Hori, Takayuki Goto, Seiichi Uchida, Ryo Kurazume, Rin-ichiro Taniguchi

2017

Abstract

This paper proposes prediction methods for people flows and anomalies in people flows on a university campus. The proposed methods are based on deep learning frameworks. By predicting the statistics of people flow conditions on a university campus, it becomes possible to create applications that predict future crowded places and the time when congestion will disappear. Our prediction methods will be useful for developing applications for solving problems in cities.

References

  1. Al Nuaimi, E., Al Neyadi, H., Mohamed, N., and AlJaroodi, J. (2015). Applications of big data to smart cities. Journal of Internet Services and Applications, 6(1):25.
  2. Cheng, B., Longo, S., Cirillo, F., Bauer, M., and Kovacs, E. (2015). Building a big data platform for smart cities: Experience and lessons from santander. In 2015 IEEE International Congress on Big Data, pages 592-599.
  3. Goldstein, M. and Uchida, S. (2016). A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data. PLoS ONE, 11(4).
  4. Kurazume, R., Yamada, H., Murakami, K., Iwashita, Y., and Hasegawa, T. (2008). Target tracking using sir and mcmc particle filters by multiple cameras and laser range finders. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 3838-3844.
  5. LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553):436-444.
  6. Vilajosana, I., Llosa, J., Martinez, B., Domingo-Prieto, M., Angles, A., and Vilajosana, X. (2013). Bootstrapping smart cities through a self-sustainable model based on big data flows. IEEE Communications Magazine, 51(6):128-134.
Download


Paper Citation


in Harvard Style

Takano S., Hori M., Goto T., Uchida S., Kurazume R. and Taniguchi R. (2017). Deep Learning-based Prediction Method for People Flows and Their Anomalies . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 676-683. DOI: 10.5220/0006248806760683


in Bibtex Style

@conference{icpram17,
author={Shigeru Takano and Maiya Hori and Takayuki Goto and Seiichi Uchida and Ryo Kurazume and Rin-ichiro Taniguchi},
title={Deep Learning-based Prediction Method for People Flows and Their Anomalies},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={676-683},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006248806760683},
isbn={978-989-758-222-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Deep Learning-based Prediction Method for People Flows and Their Anomalies
SN - 978-989-758-222-6
AU - Takano S.
AU - Hori M.
AU - Goto T.
AU - Uchida S.
AU - Kurazume R.
AU - Taniguchi R.
PY - 2017
SP - 676
EP - 683
DO - 10.5220/0006248806760683