|Robustness Enhancement Of Distribution Based Binary Discriminative Features For Modulation Classification|
|Zhechen Zhu, Asoke K. Nandi, Muhammad Waqar Aslam|
In this paper, we propose distribution based binary discriminative features and a novel feature enhancement process for automatic modulation classiﬁcation. The new features exploit the signal distribution mismatch between two modulations. Signal distributions on I-Q segments, amplitude and phase, are considered to produce a comprehensive feature set for improved robustness. Logistic regression is used to reduce feature dimension and enhance classiﬁcation robustness. To accomplish multi-class classiﬁcation, a class oriented feature space is created for the K-nearest neighbours classiﬁer. The test results show that the proposed method is able to achieve excellent performance in simulated environments.