A Knowledge Engineering Method for Track Initiation in Complex Conditions

In a complex environment radar plot is often changing dramatically, non-uniform, discontinuous, uncertain and containing lots of false alarms. It is difficult for tracking system to form tracks in such complex environment. Traditional track formation methods can not accurately determine the size of track initiation gate and select specific initiation criteria. In this paper, an intelligent information processing method is proposed to solve track initiation in complex environments. The track initiation is considered as a progress of plot identification, classification and fuzzy information processing. According to the integration and fusion of neural network (NN), fuzzy reasoning (FR) and expert system (ES) technology, an intellectualized track initiation knowledge reasoning system is constructed which can realize structural, functional, algorithmic and hierarchical complementation. Further more the adaptive robust learning algorithm and the weighted synthesis reasoning algorithm are used in this system. Real data experiment shows that the proposed knowledge engineering method can effectively solve track initiation problem in complex conditions.

[1]  Li-Min Fu,et al.  Knowledge-based connectionism for revising domain theories , 1993, IEEE Trans. Syst. Man Cybern..

[2]  Changjun Yu,et al.  Research on NFE Model of Multi-Sensor Information Fusion , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[3]  Yue Jin,et al.  A Study of Intelligent Decision-Making System Based on Neural Networks and Expert System , 2008, 2008 International Conference on Cyberworlds.

[4]  Sankar K. Pal,et al.  Rough fuzzy MLP: knowledge encoding and classification , 1998, IEEE Trans. Neural Networks.

[5]  Oscar Castillo,et al.  An intelligent hybrid approach for industrial quality control combining neural networks, fuzzy logic and fractal theory , 2004, Inf. Sci..