Abstract
How to detect and predict the critical situation in large-scale activities is a very important research issue. The existing researches of emergency prediction are mainly focus on the micro events in some specific fields. Applying existing results directly to predict the critical situation in large-scale activity is a big challenge. In this paper, we show a novel method to predict emergency based on historical data analysis. We integrate relevant research results into a unified spatiotemporal model. Firstly, constructing the historical spatiotemporal context time series based on historical activity data. Then, dividing the time series into time period and time window. Finally, exploiting the time series’ spatiotemporal patterns to predict the emergency of current activity. Experimental results show that the proposed method can achieve better prediction of large-scale activity emergencies in a specific venue.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Wang, G.Q., Liu, Y., Yang, P., et al.: Study on decision-making method for complex crisis. Syst. Eng. Theory Pract. 35(10), 2449–2458 (2015)
Qiao, X.J., Li, Y.J., Chang, B., et al.: Modeling on risk analysis of emergency based on fuzzy evidential reasoning. Syst. Eng. Theory Pract. 35(10), 2657–2666 (2015)
Yang, Q., Liu, X.X., Yang, F., et al.: Risk identification double-signal method for unconventional crisis based on immune danger theory. Syst. Eng. Theory Pract. 35(10), 2667–2674 (2015)
Luo, P.Z., Chen, X.: Research on emergency event chain modeling and retrieval. J. Huazhong Univ. Sci. Technol. Nat. Sci. Edn. S1, 440–444 (2015)
Xu, W., Liu, L.Y., Wang, M.M.: Emergency event detection and analysis for emergency management based on cross-media analytics. Syst. Eng. Theory Pract. 35(10), 2550–2556 (2015)
Ye, L., Keogh, E.: Time series shapelets: a new primitive for data mining. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 947–956. ACM (2009)
Ji, C., Zhao, C., Pan, L., et al.: A fast shapelet discovery algorithm based on important data points. Int. J. Web Serv. Res. (IJWSR) 14(2), 67–80 (2017)
Chen, H.L., Gao, X.D.: Research on wavelet-based time series similarity measure and cluster. Stat. Decis. 35(11), 17–22 (2019)
Xu, J., Du, L., Song, C., et al.: Big data service request prediction based on historical behavior time series. In: Proceedings of the 2nd International Conference on Big Data Technologies, pp. 77–81. ACM (2019)
Sindagi, V.A., Patel, V.M.: CNN-based cascaded multi-task learning of high-level prior and density estimation for crowd counting. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1–6. IEEE, (2017)
Ding, Z., Ren, F., Cai, Z., et al.: Urban road congestion condition discrimination research based on vector features. In: IEEE Third International Conference on Data Science in Cyberspace (DSC), pp. 92–98 (2018)
Li, Q., Zhao, X., He, R., et al.: Recurrent prediction with spatio-temporal attention for crowd attribute recognition. IEEE Trans. Circ. Syst. Video Technol. (2019)
Cao, Y., Si, Y., Cai, Z., et al.: Mining spatio-temporal semantic trajectory for groups identification. In: 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), pp. 308–313. IEEE (2018)
Patwardhan, A.: Edge based grid super-imposition for crowd emotion recognition. arXiv preprint arXiv:1610.05566 (2016)
Selvi, S.S.: Crowd recognition system based on optical flow along with SVM classifier. Int. J. Electric. Comput. Eng. 9 (2019). 2088–8708
Acknowledgment
The work was partially supported by the National Key R&D Program of China under grant number 2017YFC0803300, National Natural Science Foundation of China under grant number 91546111 and 91646201, Beijing Municipal Education Commission Science and Technology Program under grant number KZ201610005009 and KM201610005022.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, Z., Ding, Z., Cao, Y. (2021). A Method of Emergency Prediction Based on Spatiotemporal Context Time Series. In: Meng, X., Xie, X., Yue, Y., Ding, Z. (eds) Spatial Data and Intelligence. SpatialDI 2020. Lecture Notes in Computer Science(), vol 12567. Springer, Cham. https://doi.org/10.1007/978-3-030-69873-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-69873-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-69872-0
Online ISBN: 978-3-030-69873-7
eBook Packages: Computer ScienceComputer Science (R0)