Acta Metallurgica Sinica(English letters) ›› 2011, Vol. 18 ›› Issue (4): 13-19.doi: 10.1016/S1005-8885(10)60077-5

• Wireless • Previous Articles     Next Articles

Automatic modulation classification based on the combination of clustering and neural network

  

  • Received:2010-12-15 Revised:2011-04-07 Online:2011-08-31 Published:2011-08-24
  • Supported by:

    This work was supported by the National Basic Research Program of China (2007CB310607), the National Natural Science Foundation of China (60772062), and the National Science and Technology Key Project (2011ZX03001-006-02, 2011ZX03005-004-03).

Abstract:

In this paper, we propose a new modulation classification method based on the combination of clustering and neural network, in which a new algorithm is introduced to extract key features. In order to recognize modulation types based on the constellation diagram such as phase shift keying (PSK) and quadrature amplitude modulation (QAM), fuzzy C-means (FCM) clustering is adopted for recovering the constellation under different number of clusters. Then cluster validity measure is applied to extract key features which discriminate between different modulation types. The features are sent to neural network so that modulation types can be recognized. In order to conquer the disadvantages of standard back propagation (BP) neural network, conjugate gradient learning algorithm of Polak-Ribiere update is employed to improve the speed of convergence and the performance of modulation recognition. Simulation results show that classification rates of the algorithm proposed in this paper are much higher than those of clustering algorithm.

Key words:

modulation classification, clustering, BP neural network, FCM