Modulation mode identification method based on deep learning

A modulation mode recognition and modulation mode technology, applied in character and pattern recognition, instruments, biological neural network models, etc., can solve the problem of low recognition accuracy, and achieve the effect of enhancing learning effect and avoiding poor learning effect.

Active Publication Date: 2019-08-23
XIDIAN UNIV
View PDF4 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies in the above-mentioned prior art, and provide a modulation method recognition method based on deep learning, which is used to solve the technical problem of low recognition accuracy existing in the prior art

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 mode identification method based on deep learning
  • Modulation mode identification method based on deep learning
  • Modulation mode identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0033] refer to figure 1 , the present invention comprises the following steps:

[0034] Step 1) Get training set and test set:

[0035] Step 1a) The embodiment of the present invention adopts 200,000 modulated signals contained in the shared sample set RadioML2016.10a, the SNR value range of the modulated signal is (-20,18), and the interval between adjacent SNRs is 2 , the number of signal-to-noise ratios is 20, and the 10 modulation methods are BPSK, QPSK, 8PSK, 16QAM, 64QAM, BFSK, PAM4, CPFSK, SSB, and AM-DSB. Each modulation method contains 1000 signals with the same signal-to-noise ratio. Modulation signals, each modulation method contains 20000 modulation signals.

[0036] Step 1b) Sampling each modulation signal at 128 points to obtain 200,000 sampling signals with a length of 128, and normalizing each sampling signal. The no...

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 invention provides a modulation mode identification method based on deep learning, which is used for solving the problem of low identification accuracy in the prior art, and comprises the following implementation steps of: (1) obtaining a training set and a test set; (2) establishing a neural network NNs; (3) dividing the training set into a plurality of sub-training sets based on the signal-to-noise ratio, and respectively training the neural network NNs by using the sub-training sets to obtain a plurality of trained neural networks; and (4) evaluating the signal-to-noise ratio snr of theto-be-tested modulation signal, selecting an applicable trained neural network according to the interval where the snr is located, and identifying the modulation mode of the to-be-tested modulation signal. When the neural network NNs are trained, the internal relation and rule of the sample data and the sample labels of all the sub-training sets can be accurately found, the learning effect of theneural network NNs is enhanced, the recognition accuracy is improved, and meanwhile self-adaptive modulation mode recognition based on the signal-to-noise ratio is achieved. The method can be used inthe fields of modulation mode identification and the like in non-cooperative communication.

Description

technical field [0001] The invention belongs to the field of communication technology, and relates to a modulation mode identification method based on deep learning, in particular to a modulation mode identification method based on signal-to-noise ratio segmented training neural network, which can be used in the identification of modulation modes in non-cooperative communication and other fields . Background technique [0002] In the wireless transmission system, the transmitter moves the spectrum of the baseband signal to a higher carrier frequency through modulation, so that the spectrum of the modulated signal matches the band-pass characteristics of the channel to improve transmission performance. The modulation methods of the signal are various. For example, analog modulation methods include amplitude modulation (AM), double sideband (DSB), and single sideband (SSB), and digital modulation methods include amplitude shift keying (Amplitude Shift Keying, ASK), frequency s...

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 Applications(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/045G06F18/214
Inventor 高明黄凤杰潘毅恒廖覃明李静刘刚
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap