Data processing for automatic modulation classification of wireless signals

Abstract

Systems and methods for classifying a modulation scheme of a wireless signal are described. In some embodiments, a system receives a wireless signal modulated based on a modulation scheme having a constant modulus. The system can generate a resampled signal from the wireless signal based on features extracted from the wireless signal and perform blind equalization on the resampled signal based on a constant modulus criterion to generate an equalized signal. Then, the system can cause a modulation classifier to classify the received wireless signal to a modulation scheme from a plurality of predetermined modulation schemes based on the equalized signal. By preconditioning the wireless signal to reduce feature variability imparted by a propagation channel onto the wireless signal, the system can increase the classification accuracy of the modulation classifier.

Description

FIELD OF THE DISCLOSURE[0001]The present disclosure relates generally to systems and methods for classifying a modulation scheme of wireless signals and in particular, processing the wireless signals to improve the accuracy of automatic modulation classifiers.BACKGROUND OF THE DISCLOSURE[0002]Modulation classifiers can classify wireless signals to a modulation scheme used to embed data within the wireless signals. For example, a modulation classifier may identify that a particular wireless signal embeds data using frequency shift keying (FSK), which is an example modulation scheme. An automatic modulation classifier can automatically identify the modulation scheme of a received wireless signal based on characteristics of the received signal. The automatic modulation classifier may allow for a universal receiver capable of processing wireless signals according to a plurality of modulation schemes instead of requiring the use of multiple receivers each capable of processing a specific...

AI Technical Summary

Benefits of technology

The patent text discusses the problem of current modulation classifiers being inaccurate in identifying the type of modulation used in wireless signals. To address this issue, the patent proposes a method where a constant modulus criterion is used to blind equalize the signal, reducing data complexity and variability. This allows for improved accuracy in identifying different modulation schemes.

Problems solved by technology

As discussed above, current modulation classifiers have reduced accuracy in classifying modulation schemes of a wireless signal in highly-variable, complex channels.

Images