Combining clustering and SVM for automatic modulation classification

In this paper, we propose a new modulation classification method based on the combination of clustering and Support Vector Machine (SVM), in which a new algorithm is introduced to extract key features. To recognise signals modulated based on constellation diagram, such as MPSK and MQAM; K-means clustering is adopted for recovering constellation under different number of clusters. Silhouette index is employed as a cluster validity measure to extract key features that discriminate between different modulation types. Then hierarchical SVM classifier is designed to recognise modulation types according to the key features extracted. Simulation results show that the classification rates of the algorithm proposed in this paper are much higher than those of clustering algorithm.