Dual-mode orthogonal frequency division multiplexing index modulation detection method and device based on deep learning

A technology of index modulation and orthogonal frequency division, which is applied in the field of communication systems to achieve the effect of shortening detection time, maintaining performance and improving detection efficiency

Active Publication Date: 2021-03-26
SHANDONG UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] For the problem that traditional methods cannot better coordinate detection performance and computational complexity, the present invention proposes a dual-mode OFDM index modulation detection method based on deep learning;

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
  • Dual-mode orthogonal frequency division multiplexing index modulation detection method and device based on deep learning
  • Dual-mode orthogonal frequency division multiplexing index modulation detection method and device based on deep learning
  • Dual-mode orthogonal frequency division multiplexing index modulation detection method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] A dual-mode OFDM index modulation detection method based on deep learning, comprising the following steps:

[0076] (1) Data preprocessing: preprocessing the obtained DM-OFDM-IM signal (dual-mode orthogonal frequency division multiplexing index modulation signal) and channel; DM-OFDM-IM signal is divided into several groups, each group has four Carrier, since each group of subcarriers is generated in the same way, a group of subcarriers is selected for processing;

[0077] (2) training DM-OFDM-IM model: the preprocessed data that step (1) obtains is used as the input of DM-OFDM-IM model, carries out the off-line training of DM-OFDM-IM model;

[0078] (3) On-line modulation: The new DM-OFDM-IM signal is modulated online under Rayleigh channel conditions through the trained DM-OFDM-IM model, and the relationship curve between the signal-to-noise ratio and the bit error rate is output.

[0079] The trained DM-OFDM-IM model can detect the bit error rate of the received sig...

Embodiment 2

[0081] According to a deep learning-based dual-mode OFDM index modulation detection method described in Embodiment 1, the difference is that:

[0082] In step (1), the generation process of DM-OFDM-IM signal is as follows:

[0083] In a DM-OFDM-IM system with m input bits, image 3 is a schematic structural diagram of a DM-OFDM-IM system, m input bits are divided into p groups, and each group is composed of g bits, that is, p=m / g;

[0084] Each group of g bits is input into an index selector (serial number selector) and two different constellation mappers, the two different constellation mappers include constellation mapper A and constellation mapper B, and the generation length is l=N / The OFDM sub-block of p, N is the size of the Fast Fourier Transform (FFT); compared with the existing OFDM-IM that only modulates some sub-carriers, all sub-carriers in DM-OFDM-IM are modulated, Improved spectral efficiency; the index selector uses the first g of the g bits of the input 1 bi...

Embodiment 3

[0110] According to a deep learning-based dual-mode OFDM index modulation detection method described in Embodiment 2, the difference is that:

[0111] Such as figure 1 As shown, the DM-OFDM-IM model includes two fully connected layers, including a hidden layer containing Q nodes and an output layer containing g nodes; Find a good balance between efficiency and performance. When the modulation method or the amount of training data changes, the appropriate bit error rate performance can be obtained by adjusting the size of Q. Specifically, the value of Q should be 2 n , when the amount of data is large, the value of Q should be larger, so that a DNN model with better performance can be obtained through training. The activation function used in the hidden layer is the Relu function f Relu (x), as shown in formula (X):

[0112] f Relu (x)=max(0,x)(X)

[0113] The activation function applied at the output layer is the Sigmoid function f Sigmoid (x), as shown in formula (XI)...

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 relates to a dual-mode orthogonal frequency division multiplexing index modulation detection method and device based on deep learning. The dual-mode orthogonal frequency division multiplexing index modulation detection method comprises the following steps: (1) data preprocessing: preprocessing an obtained DMOFDMIM signal and an obtained channel; (2) training a DMOFDMIM model: takingthe preprocessed data obtained in the step (1) as the input of the DMOFDMIM model, and carrying out the offline training of the DMOFDMIM model; and (3) on-line modulation: carrying out on-line modulation on the new DM-OFDM-IM signal under the Rayleigh channel condition through the trained DM-OFDM-IM model. According to the detection and demodulation scheme based on the deep neural network providedby the invention, the bit error rate close to the maximum likelihood detector can be achieved in a relatively short operation time.

Description

technical field [0001] The invention relates to a dual-mode OFDM index modulation detection method and device based on deep learning, which belongs to the technical field of communication systems. Background technique [0002] Orthogonal Frequency Division Multiplexing (OFDM) technology can effectively resist the intersymbol interference caused by the frequency selectivity of wireless channels, and has become the most popular multi-carrier transmission technology in wireless communication. Compared with the traditional OFDM system, Orthogonal Frequency Division Multiplexing Index Modulation (OFDM-IM) can transmit information not only through the signal constellation, but also through the index of OFDM subcarriers, so it has a better bit error rate performance. On the basis of OFDM-IM, dual-mode orthogonal frequency division multiplexing index modulation (DM-OFDM-IM) divides all sub-carriers into several sub-blocks, and all sub-carriers in each sub-block are divided into par...

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): H04B17/309H04L27/26G06N3/08G06N3/04
CPCH04B17/309H04L27/2649G06N3/08G06N3/048G06N3/045
Inventor 周晓天沙威霖马丕明张海霞袁东风
Owner SHANDONG 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