An Algorithm of Data Fusion Using Artificial Neural Network and Dempster-Shafer Evidence Theory

A new algorithm of data fusion using neural networks and Dempster-Shafer (D-S) evidence theory is presented in this paper to overcome these faults of data fusion, i.e., low accurate identification, bad stabilization and solution of uncertainty in some ways under multi-sensor environment. In this paper, according to the characteristic of the information obtained from multi-sensor obtained, firstly we divide obtained features into some groups and set up corresponding neural network to every group, meanwhile we introduce a concept of unknown probability to the goals based on the result of credible probability of these goals, secondly we have a fusion of time and space depending on the transpositional result of the neural networks' output by D-S evidence theory. This method has the advantage of both neural and D-S evidence theory, and solves the problem that the general ways of data fusion can not identify the multisensor's uncertainty information of great noise at present. At last simulation shows that the method can effectively improve the rate of the targets' identification and keep great antinoise capacity.