Situation Assessment Approach Based on a Hierarchic Multi-timescale Bayesian Network

In this paper, situation assessment in the battle field is described by the modular Bayesian network, and a method is proposed for adaptive situation assessment using a hierarchic Bayesian Networks. For different levels, district network structures are adopted to infer situation and adaptively update parameters of network with different timescale. Specially, dynamic Bayesian networks are utilized in the lower level networks, taking full advantage of the direct measurement of sensors and improving the robustness of the assessment system. A simulation is provided to indicate how to structure the network model, infer situation and update parameters for hierarchic Bayesian networks. The simulation results illustrate the validity of the proposed method.