Journal of System Simulation ›› 2018, Vol. 30 ›› Issue (3): 785-792.doi: 10.16182/j.issn1004731x.joss.201803003

Previous Articles     Next Articles

A Model for Battlefield Situation Change Rate Prediction Based on Deep Learning

Tao Jiuyang1,2, Wu Lin1, Wang Chi1, Chu Junda1, Liao Ying1, Zhu Feng1   

  1. 1.Joint Operations College, National Defense University, Beijing 100091, China;
    2.Army Engineering University of PLA, Nanjing 210007, China
  • Received:2018-01-07 Online:2018-03-08 Published:2019-01-02

Abstract: To measure and estimate the uncertainty of the battlefield situation is of great significance for the commanders to plan the reconnaissance mission and reduce the risk of decision-making. Based on Shannon's information theory, firstly, methods and a model on measurement of situation change rate are proposed. Secondly, a scene with two-dimensional grid elements maneuvering is established, based on deep learning, the prediction method for maneuvering trend is explored. It is proved that cross entropy is equivalent to situation change rate. Finally, with the increase of the objective uncertainty, situation change rate and the accuracy of the forecast is analyzed. It is deduced that there is an upper limit on the prediction accuracy based on the learning model, and the upper limit is inversely proportional to the situation change rate.

Key words: information theory, situation awareness, deep learning, shannon entropy

CLC Number: