ABSTRACT
The frequency and intensity of natural disasters has significantly increased over the past decades and this trend is predicted to continue. Facing these possible and unexpected disasters, accurately predicting human emergency behavior and their mobility will become the critical issue for planning effective humanitarian relief, disaster management, and long-term societal reconstruction. In this paper, we build up a large human mobility database (GPS records of 1.6 million users over one year) and several different datasets to capture and analyze human emergency behavior and their mobility following the Great East Japan Earthquake and Fukushima nuclear accident. Based on our empirical analysis through these data, we find that human behavior and their mobility following large-scale disaster sometimes correlate with their mobility patterns during normal times, and are also highly impacted by their social relationship, intensity of disaster, damage level, government appointed shelters, news reporting, large population flow and etc. On the basis of these findings, we develop a model of human behavior that takes into account these factors for accurately predicting human emergency behavior and their mobility following large-scale disaster. The experimental results and validations demonstrate the efficiency of our behavior model, and suggest that human behavior and their movements during disasters may be significantly more predictable than previously thought.
Supplemental Material
- E. Cho, S. A. Myers, and J. Leskovec. Friendship and mobility: User movement in location-based social networks, Proc. of ACM SIGKDD, (2011), pp. 1082--1090. Google ScholarDigital Library
- X. Song, Q. Zhang, Y. Sekimoto, T. Horanont, S. Ueyama, and R. Shibasaki. Modeling and Probabilistic Reasoning of Population Evacuation During Large-scale Disaster, Proc. of ACM SIGKDD, (2013), pp. 1231--1239. Google ScholarDigital Library
- X. Lu, L. Bengtssona, and P. Holme. Predictability of population displacementafter the 2010 Haiti earthquake, Proc. of the National Academy of Sciences of USA (PNAS), 109 (2012), pp. 11576--11581.Google Scholar
- Japanese Cabinet Secretariat,http://www.cas.go.jp/.Google Scholar
- R. Hoetzlein. Visual communication in Times of crisis: the Fukushima Nuclear Accident, Leonardo Journal of Arts, Science and Technology, 45 (2012), pp. 113--118.Google Scholar
- P. Tan, M. Steinbach, and V. Kumar, Introduction to Data Mining,Addison Wesley, (2005). Google ScholarDigital Library
- J. Ye, Z. Zhu, and H. Cheng. What's Your Next Move: User Activity Prediction in Location-based Social Networks, Proc. of SIAM International Conference on Data Mining (SDM), (2013).Google ScholarCross Ref
- W. Zucchini, and I. L. MacDonald. Hidden Markovmodels for time series: an introduction using R,Chapman and Hall, London, (2009).Google Scholar
- L. E. Baum, T. Petrie, G. Soules, and N. Weiss. A maximization technique occurring in the statistical analysis of probabilistic functions of markov chains, The Annals of Mathematical Statistics, (1970), pp. 164--171.Google ScholarCross Ref
- G. Schwarz. Estimating the dimension of a model, The Annals of Statistics, (1978), pp. 461--464.Google ScholarCross Ref
- A. Doucet, S.J. Godsill, and C. Andrieu.On sequential Monte Carlo sampling methods for Bayesian filtering, Statistics and Computing, (2000), pp. 197--208. Google ScholarDigital Library
- X. Song, Q. Zhang, Y. Sekimoto, T. Horanont, S. Ueyama, and R. Shibasaki. An Intelligent System for Large-scale Disaster Behavior Analysis and Reasoning, IEEE Intelligent Systems, 28 (2013), pp. 35--42. Google ScholarDigital Library
- Y. Sekimoto, R. Shibasaki, H. Kanasugi, T. Usui and Y. Shimazaki. Reconstructing People Flow Recycling Large-Scale Social Survey Data, IEEE Pervasive Computing, (2011), pp. 27--35. Google ScholarDigital Library
- L. Wei, Y. Zheng, and W. Peng. Constructing Popular Routes from Uncertain Trajectories, Proc. of ACM SIGKDD, (2012), pp. 195--203. Google ScholarDigital Library
- X. Song, Q. Zhang, Y. Sekimoto, and R. Shibasaki. Intelligent System for Urban Emergency Management During Large-scale Disaster, Proc. of AAAI Conference on Artificial Intelligence (AAAI), (2014).Google Scholar
- M. L. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming, Wiley-Interscience, (1994). Google ScholarDigital Library
- B. D. Ziebart, A. Maas, J.A. Bagnell, and A. K. Dey. Navigate Like a Cabbie: Probabilistic Reasoning from Observed Context-Aware Behavior, Proc. of Ubicomp., (2008), pp. 322--331. Google ScholarDigital Library
- B. D. Ziebart, A. Maas, J.A. Bagnell, and A. K. Dey. Maximum Entropy Inverse Reinforcement Learning, Proc. of AAAI Conference on Artificial Intelligence (AAAI), (2008), pp. 1433--1438. Google ScholarDigital Library
- R. Simmons, B. Browning, Y. Zhang, and V. Sadekar. Learning to predict driver route and destination intent, Proc. Intelligent Transportation Systems Conference, (2006), pp. 127--132.Google ScholarCross Ref
- MC. Gonzalez, CA. Hidalgo, and AL. Barabasi. Understanding individual humanmobility patterns, Nature, 453 (2008), pp. 779--782.Google ScholarCross Ref
- M. Moussaid, S. Garnier, G. Theraulaz, and D. Helbing. Collective information processing and pattern formation in swarms, flocks, and crowds, Top Cogn. Sci., 1 (2009), pp. 469--497.Google ScholarCross Ref
- J. Hahm and JH. Lee. Human errors in evacuation behavior during a traumatic emergencyusing a virtual fire, Cyberpsychol Behavior, 12 (2009), pp. 98--98.Google Scholar
- JP. Bagrow, DS. Wang, and AL Barabasi. Collective response of human populations tolarge-scale emergencies, Plos ONE, 6 (2011).Google Scholar
- L. Bengtsson, X. Lu, A. Thorson, R. Garfield, J. von Schreeb. Improved responseto disasters and outbreaks by tracking population movements with mobile phone network data: A post-earthquake geospatial study in Haiti, PLoS Medical, 8 (2011).Google Scholar
- CM. Song, ZH. Qu, N. Blumm, and AL. Barabasi. Limits of predictability in human mobility, Science, 327 (2010), pp. 1018--1021.Google ScholarCross Ref
- C. Song, T. Koren, P. Wang, and AL. Barabasi, Modelling the scaling properties of human mobility, Nature Physics, 6 (2010), pp. 818--823.Google ScholarCross Ref
- N. Eagle, A. Pentland, and D. Lazer. Inferring friendship network structure by using mobile phone data, Proc. of the National Academy of Sciences of USA (PNAS), 106 (2009), pp. 15274--15278.Google ScholarCross Ref
- Z. Chen, H. T. Shen and X. Zhou. Discovering Popular Routes from Trajectories, Proc. of IEEE ICDE, (2011), pp. 900--911. Google ScholarDigital Library
- Z. Chen, H.T. Shen, X. Zhou, Y. Zheng and X. Xie. Searching Trajectories by Locations - An Efficiency Study, Proc. of ACM SIGMOD, (2010), pp. 255--266. Google ScholarDigital Library
- F. Giannotti, M. Nanni, D. Pedreschi, F. Pinelli, C. Renso, S. Rinzivillo and R. Trasarti. Unveiling the complexity of human mobility by querying and mining massive trajectory data, The VLDB Journal, 20 (2011), pp. 695--719. Google ScholarDigital Library
- Z. Li, M. Ji, J. Lee, L. Tang, Y. Yu, J. Han, R. Kays. MoveMine: mining moving object databases, Proc. of ACM SIGMOD, (2010), pp. 1203--1206. Google ScholarDigital Library
- J. Yuan, Y. Zheng abd X. Xie. Discovering regions of different functions in a city using human mobility and POIs, Proc. of ACM SIGKDD, (2012), pp. 186--194. Google ScholarDigital Library
- L. Backstrom, E. Sun, and C. Marlow. Find me if you can: improving geographical prediction with social and spatial proximity, Proc. of WWW, (2010), pp. 61--70. Google ScholarDigital Library
- F. Giannotti, M. Nanni, F. Pinelli, and D. Pedreschi. Trajectory pattern mining, Proc. of ACM SIGKDD, (2007), pp. 330--339. Google ScholarDigital Library
- Z. Li, B. Ding, J. Han, R. Kays, and P. Nye. Mining periodic behaviors for moving objects, Proc. of ACM SIGKDD, (2010), pp. 1099--1108. Google ScholarDigital Library
- S. Scellato, A. Noulas, and C. Mascolo. Exploiting place features in link prediction on location-based social networks, Proc. of ACM SIGKDD, (2011), pp. 1046--1054. Google ScholarDigital Library
- Y. Ye, Y. Zheng, Y. Chen, J. Feng, and X. Xie, Mining individual life pattern based on location history, Proc. of MDM, (2009), pp. 1--10. Google ScholarDigital Library
- Y. Zheng, L. Zhang, X. Xie, and W. Y. Ma. Mining interesting locations and travel sequences from GPS trajectories, Proc. of WWW, (2009), pp. 791--800. Google ScholarDigital Library
- Z. Li, B. , J. Han, and R. Kays. Swarm: Mining Relaxed Temporal Moving Object Clusters, Proc. of VLDB, (2010), pp. 723--734. Google ScholarDigital Library
- Y. Xue, R. Zhang, Y. Zheng, X. Xie, J. Huang, Z. Xu. Destination Prediction by Sub-Trajectory Synthesis and Privacy Protection Against Such Prediction, Proc. of IEEE ICDE, (2013), pp. 254--265. Google ScholarDigital Library
- H. Su, K. Zheng, H. Wang, J. Huang and X. Zhou. Calibrating Trajectory Data for Similarity-based Analysis, Proc. of ACM SIGMOD, (2013), pp. 833--844. Google ScholarDigital Library
- J. Yuan, Y. Zheng, X. Xie, G. Sun. T-Drive: Enhancing driving directions with taxi drivers' intelligence, IEEE Transactions on Knowledge and Data Engineering, 25(2013), pp. 220--232. Google ScholarDigital Library
Index Terms
- Prediction of human emergency behavior and their mobility following large-scale disaster
Recommendations
Modeling and probabilistic reasoning of population evacuation during large-scale disaster
KDD '13: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data miningThe Great East Japan Earthquake and the Fukushima nuclear accident cause large human population movements and evacuations. Understanding and predicting these movements is critical for planning effective humanitarian relief, disaster management, and long-...
Prediction and Simulation of Human Mobility Following Natural Disasters
Survey Paper, Special Issue: Intelligent Music Systems and Applications and Regular PapersIn recent decades, the frequency and intensity of natural disasters has increased significantly, and this trend is expected to continue. Therefore, understanding and predicting human behavior and mobility during a disaster will play a vital role in ...
DeepMob: Learning Deep Knowledge of Human Emergency Behavior and Mobility from Big and Heterogeneous Data
Special issue: Search, Mining and their Applications on Mobile DevicesThe frequency and intensity of natural disasters has increased significantly in recent decades, and this trend is expected to continue. Hence, understanding and predicting human evacuation behavior and mobility will play a vital role in planning ...
Comments