Classification Using a Novel Combined Classifier for Digital Modulations in Digital Television Communication

Abstract

With the rapid development of the communication technology, the communication environment becomes more and more complicated these years. Many signal modulation types are used simultaneously in digital TV communication systems. Therefore, a need arises for modulation classification that can automatically detect the incoming modulation type. In this paper, we propose a new approach for modulation classification, which uses a novel combined classifier based on multi-class support vector machine (SVM) and fuzzy integral to make the classification more suitable and accurate for signals in a wide range of signal to noise rate (SNR). Further, three efficient features with high robustness and less computation are extracted from intercepted signals to classify eleven digital modulation types. The experimental results show that the proposed scheme has the advantages of high accuracy and reliability.