TY - GEN
T1 - Making real-time predictions of people's irregular movement in a metropolitan scale under disaster situations
AU - Yabe, Takahiro
AU - Sekimoto, Yoshihide
AU - Kanasugi, Hiroshi
AU - Kashiyama, Takehiro
PY - 2015
Y1 - 2015
N2 - In this paper, we present our method of accurately predicting people's movement under disaster situations in a metropolitan scale. Recently many studies have suggested methods on predicting the daily movement of the people from various datasets. However because of the lack of accumulated data and irregular behaviors of people in emergency, people movement pre-diction under disaster situations has been challenging. Our method com-bines multi agent simulation which uses heterogeneous characteristics of people in the behavioral model, and real-time observation data. We verified the effectiveness of our method by experimenting it on the Great East Japan Earthquake, and also showed that the hourly update of the optimum param-eters of the model was effective in keeping a high prediction accuracy. Also, the number of people bound for each destination matched the survey results carried out by different research, supporting the accuracy of the method.
AB - In this paper, we present our method of accurately predicting people's movement under disaster situations in a metropolitan scale. Recently many studies have suggested methods on predicting the daily movement of the people from various datasets. However because of the lack of accumulated data and irregular behaviors of people in emergency, people movement pre-diction under disaster situations has been challenging. Our method com-bines multi agent simulation which uses heterogeneous characteristics of people in the behavioral model, and real-time observation data. We verified the effectiveness of our method by experimenting it on the Great East Japan Earthquake, and also showed that the hourly update of the optimum param-eters of the model was effective in keeping a high prediction accuracy. Also, the number of people bound for each destination matched the survey results carried out by different research, supporting the accuracy of the method.
UR - http://www.scopus.com/inward/record.url?scp=84991110399&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84991110399&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84991110399
T3 - CUPUM 2015 - 14th International Conference on Computers in Urban Planning and Urban Management
BT - CUPUM 2015 - 14th International Conference on Computers in Urban Planning and Urban Management
PB - CUPUM
T2 - 14th International Conference on Computers in Urban Planning and Urban Management, CUPUM 2015
Y2 - 7 July 2015 through 10 July 2015
ER -