Application of Improved Kohonen SOFM Neural Network to Radar Signal Sorting
Kohonen neural network is capable of self-organizing and recognizingclustering center, which is used in many artificial intelligence (AI) fields. One electronic support measures (ESM) system must sort the received radar pulses to cells with same features by pulse parameters, such as radio frequency (RF), angle of arrival (AOA), pulse width (PW), Pulse Repetition Interval(PRI), etc. Kohonen SOFM algorithm is one valid method for clustering, which can be used to accomplish such radar pulses sorting. Considering the variety character of pulses parameters which is the character of modern radar system, a new definition of “distance” in the SOFM neural net is proposed in this paper, which decreases the effect of large variety range of special parameter among them. This paper employs the “distance” to improve the clustering capability in such special environments. The computer simulation shows the validity of these improvements.
KeywordsOutput Layer Input Pattern Radar System Radar Signal Radar Pulse
Unable to display preview. Download preview PDF.
- 1.Chan, Y.T., Chan, F., Hassan, H.E.: Performance Evaluation of ESM Deinterleaving using TOA Analysis. In: The 14th International Conference on Microwave, Radar and Wireless Communications, Gdansk, Poland, May 2002, vol. 2, pp. 341–350 (2002)Google Scholar
- 3.Kohonen, T.: Self-Organization and associative memory. Springer, Heidelberg (1984-1988)Google Scholar
- 4.Nasrabadi, N.M., Feng, Y.: Vector quantization of images based upon the Kohonen self-organizing feature maps. In: IEEE Inter. Conf. on Neural Networks, San Diego, pp. 1101–1108 (1988)Google Scholar
- 6.Bradrun, D.S.: Reducing transmission error effects using a self-organizing network. In: Int. Joint. Conf. on Neural Networks, June 18-22, 1989, Washington (1989)Google Scholar