Automatic modulation recognition based on mixed-type features

ABSTRACT

The existing modulation classification method using instantaneous features is poor for low SNRs, and the high-order cumulant features-based modulation recognition algorithm is only applicable to some types of communication modulation signals. To overcome these problems, we propose a mixed features-based modulation recognition algorithm, which refines instantaneous features and high-order cumulant feature, and the back propagation (BP) neural network is adopted as a classifier to perform experiments. The experimental results show that our proposed mixed features-based modulation recognition method can improve the recognition rate for more kinds of signals.

KEYWORDS:

• Modulation recognition
• high-order cumulant
• instantaneous feature
• back propagation (BP) neural network

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported in part by the National Natural Science Foundation of China (61501089), Sichuan Science and Technology Program (2018GZ0213), and Fundamental Research Funds for the Central Universities (ZYGX2018J005).