Unlock instant, AI-driven research and patent intelligence for your innovation.

Modulation method identification method based on amplitude and spectral amplitude characteristics

A modulation method identification and spectrum amplitude technology, which is applied in modulation type identification, modulation carrier system, digital transmission system, etc., can solve the problems of identification performance relying on manual extraction, poor identification performance, and less information on the difference between characterization categories, and achieve simple structure , improve accuracy, and store parameters with less memory.

Active Publication Date: 2021-04-13
XIDIAN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method mainly solves the problem that the recognition performance of the traditional pattern recognition method based on feature extraction is too dependent on artificially extracted features. Can learn some features of the sample, and the recognition performance is poor, especially at low signal-to-noise ratio

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Modulation method identification method based on amplitude and spectral amplitude characteristics
  • Modulation method identification method based on amplitude and spectral amplitude characteristics
  • Modulation method identification method based on amplitude and spectral amplitude characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The modulation mode recognition method based on amplitude and spectrum amplitude features first preprocesses the sample signal to obtain a discrete sequence, then extracts the signal amplitude and spectrum amplitude to obtain samples, then trains a one-dimensional convolutional neural network, and finally uses the trained one-dimensional The convolutional neural network identifies the modulation mode, which specifically includes the following steps:

[0036] Step 1. Obtain a sample:

[0037]First generate the sample signal, the sample signal contains BPSK signal, QPSK signal, 2ASK signal, 4FSK signal, 16QAM signal, 64QAM signal, MSK signal, DSB signal and FM signal, and then the receiving end receives 130,000 sample signals, and respectively 130,000 samples The signal is processed, and 130,000 row vectors H and 130,000 labels are obtained; the method of obtaining the row vector H of each sample signal is: the receiving end samples the signal to obtain a discrete sequenc...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a method for identifying a modulation mode based on amplitude and spectrum amplitude characteristics. The specific steps are as follows: 1. Acquire samples: the receiving end receives N sample signals and processes them respectively, and obtains N row vectors H and N labels; The method of obtaining the row vector H is as follows: the receiving end samples the signal to obtain the discrete sequence, extracts the amplitude of the discrete sequence to obtain the row vector A; performs Fourier transform on the discrete sequence to obtain the spectrum sequence, and extracts the amplitude of the spectrum sequence to obtain the row vector F FT ; Merge row vector A and row vector F horizontally FT The row vector H is obtained; the method of obtaining the label is: apply the one-hot coding rule to encode the modulation mode of the signal to obtain the label; N row vectors H and N labels are used to form samples; 2. Construct a one-dimensional convolutional neural network; 3. Using samples to train the one-dimensional convolutional neural network; 4. Applying the trained one-dimensional convolutional neural network to identify the modulation mode of the signal; the invention has high recognition accuracy, good anti-noise performance and strong robustness.

Description

[0001] (1) Technical field: [0002] The invention relates to a method for identifying a modulation mode, in particular to a method for identifying a modulation mode based on amplitude and frequency spectrum amplitude features. [0003] (two), background technology: [0004] In the communication system, the transmitting end converts the baseband signal into a form suitable for transmission in the channel through modulation, and the receiving end needs to demodulate the signal. In cooperative communication, the sending and receiving parties pre-agreed on the modulation method, modulation parameters, carrier frequency, etc. used for communication. In some cases, pilot sequences are also sent in advance to help the receiving end complete carrier synchronization, symbol synchronization, and channel estimation. In a non-cooperative communication environment, there are few known communication parameters at the receiving end, so the receiving end must first complete operations such as...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L27/00G06N3/04
CPCH04L27/0012G06N3/045
Inventor 高明黄凤杰李靖潘毅恒廖覃明
Owner XIDIAN UNIV