Abstract
Electromagnetic spectrum detection is the basis of the next generation wireless communication technology. Wireless signal identification is an important part of electromagnetic spectrum detection and management activities. This paper proposes to extract the distribution features of different modulated signals from the signal I/Q data. A two-dimensional gradient matrix is used to describe the characteristics of the signal classification. The minimum gradient cumulative distance (GCD) estimate between the sample and the model is used as the decision criterion for the signal classification. According to the result of the confusion matrix, the weight of the model is adjusted. Experiments show that the recognition rate of the modulated signal mentioned in this paper can reach 82.75%. The I/Q data sample was extracted under actual engineering conditions involving random noise, and the recognition rate dropped to approximately 79%. Based on the initial model gradient matrix, a reasonable algorithm is set to adjust the weight of the model, which can effectively improve the recognition rate of the modulated signal.
Highlights
The data processed by the system is obtained after the Fast Fourier transform (FFT) block of the I/Q data at the Radio Frequency (RF) end
The data after FFT ignores many features. Therefore8, establishes a convolutional neural network (CNN) based on three features of I/Q, Amplitude/Phase and FFT to realize the recognition of signal modulation
The main contribution of this paper is to study the application of I/Q distribution characteristics in modulation signal recognition
Summary
We propose to implement wireless signal modulation recognition based on I/Q component probability distribution. I/Q component distribution of different modulation signal source We propose to describe the signal features by extracting the I/Q distribution of different modulated signals. After the I/Q data is statistically calculated in the same real part and imaginary part, I/Q component distribution can be expressed as
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
