ABSTRACT
Agent-based simulation is useful for studying people's movement in smart environment. Existing agent-based simulations are typically used as offline tools that help system design. They are not dynamically data-driven because they do not utilize any real time sensor data of the environment. In this paper, we present a method that assimilates real time sensor data into an agent-based simulation model. The goal of data assimilation is to provide inference of people's occupancy information in the smart environment, and thus lead to more accurate simulation results. We use particle filters to carry out the data assimilation and present some experiment results, and discuss how to extend this work for more advanced data assimilation in agent-based simulation of smart environment.
- A. Doucet, N. De Freitas, and N. Gordon, Sequential Monte Carlo methods in practice. New York: Springer, 2001.Google ScholarCross Ref
- D. J. Carter and B. Whitehead, "A study of pedestrian movement in a multi-storey office building," Building and Environment, vol. 11, pp. 239--247, 1976.Google ScholarCross Ref
- L. Chenda and P. Barooah, "An integrated approach to occupancy modeling and estimation in commercial buildings," in American Control Conference (ACC), 2010, 2010, pp. 3130--3135.Google Scholar
- N. Shrivastava, R. Mudumbai, U. Madhow, and S. Suri, "Target tracking with binary proximity sensors: fundamental limits, minimal descriptions, and algorithms," presented at the Proceedings of the 4th international conference on Embedded networked sensor systems, Boulder, Colorado, USA, 2006. Google ScholarDigital Library
- R. Tomastik, S. Narayanan, A. Banaszuk, and S. Meyn, "Model-Based Real-Time Estimation of Building Occupancy During Emergency Egress Pedestrian and Evacuation Dynamics 2008," W. W. F. Klingsch, C. Rogsch, A. Schadschneider, and M. Schreckenberg, Eds., ed: Springer Berlin Heidelberg, 2010, pp. 215--224.Google Scholar
- S. Meyn,; A. Surana; Y. Lin; S.M. Oggianu; S. Narayanan; A. Thomas, "A sensor-utility-network method for estimation of occupancy in buildings," Decision and Control, 2009 held jointly with the 2009 28th Chinese Control Conference. CDC/CCC 2009. Proceedings of the 48th IEEE Conference on, pp.1494, 1500, 15--18 Dec.2009 doi:10.1109/CDC.2009.5400442Google Scholar
- T. Bäck, Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms: Oxford University Press, 1996. Google ScholarDigital Library
- V. Long, D. Quang, and K. Nahrstedt, "Jyotish: A novel framework for constructing predictive model of people movement from joint Wifi/Bluetooth trace," Pervasive Computing and Communications (PerCom), 2011 IEEE International Conference on , vol., no., pp.54,62, 21-25 March 2011Google Scholar
Index Terms
- Data assimilation in agent based simulation of smart environment
Recommendations
Behavior Pattern Detection for Data Assimilation in Agent-Based Simulation of Smart Environments
WI-IAT '13: Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 02Agent-based simulation is useful for studying human activity and their interactions in smart environments. Existing agent-based simulations are mostly offline tools that do not utilize real time information of smart environments. In previous work we ...
Dynamic data driven simulation with soft data
DEVS '14: Proceedings of the Symposium on Theory of Modeling & Simulation - DEVS IntegrativeDynamic data driven simulation dynamically assimilates observation data at runtime to improve the simulation results. Typically, the observations are "hard data" that are data collected from sensors. In this paper we consider dynamic data driven ...
Data assimilation technique for social agent-based simulation by using reinforcement learning
DS-RT '18: Proceedings of the 22nd International Symposium on Distributed Simulation and Real Time ApplicationsThis paper presents a data assimilation technique for social agent-based simulation to fit real world data automatically by a reinforcement learning method. We used the hidden Markov model in order to estimate the states of the system during the ...
Comments