TY - GEN
T1 - A learning based approach for social force model parameter estimation
AU - Wan, Zhiqiang
AU - Hu, Xuemin
AU - He, Haibo
AU - Guo, Yi
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/6/30
Y1 - 2017/6/30
N2 - Understanding human behavior is crucial for planning evacuation strategies when an emergency occurs. The social force model, which is a successful quantitative model, has been widely used in investigating human behavior. In this paper, we propose a gradient descent based parameter optimization method to learn the parameters of the social force model from experimental data. Although the original social force model has achieved great success, it does not consider the fact that the response of humans to that happening in front of them is stronger than that happening behind them. In order to model the directional dependency of the interactive force, we propose a modified social force model. Experimental results demonstrate the effectiveness of the modified model.
AB - Understanding human behavior is crucial for planning evacuation strategies when an emergency occurs. The social force model, which is a successful quantitative model, has been widely used in investigating human behavior. In this paper, we propose a gradient descent based parameter optimization method to learn the parameters of the social force model from experimental data. Although the original social force model has achieved great success, it does not consider the fact that the response of humans to that happening in front of them is stronger than that happening behind them. In order to model the directional dependency of the interactive force, we propose a modified social force model. Experimental results demonstrate the effectiveness of the modified model.
UR - http://www.scopus.com/inward/record.url?scp=85030981106&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85030981106&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2017.7966368
DO - 10.1109/IJCNN.2017.7966368
M3 - Conference contribution
AN - SCOPUS:85030981106
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 4058
EP - 4064
BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
T2 - 2017 International Joint Conference on Neural Networks, IJCNN 2017
Y2 - 14 May 2017 through 19 May 2017
ER -