Multi-wavelength LED underwater visible light communication modulation method based on deep learning

A technology of visible light communication and deep learning, which is applied in the field of multi-wavelength LED underwater visible light communication modulation based on deep learning, and can solve the problems that cannot meet the requirements of non-negative real signals at the same time

Active Publication Date: 2020-10-16
SUN YAT SEN UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention overcomes the existence of existing underwater modulation methods that cannot simultaneously meet the non-negative real signal requirements of VLC based on intensity modulation and direct detection, keeps the average optical

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
  • Multi-wavelength LED underwater visible light communication modulation method based on deep learning
  • Multi-wavelength LED underwater visible light communication modulation method based on deep learning
  • Multi-wavelength LED underwater visible light communication modulation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] Such as figure 1 As shown, the present invention provides a multi-wavelength LED underwater visible light communication modulation method based on deep learning, comprising the following steps:

[0075] S1: Construct a communication system using multiple different wavelengths and based on deep learning autoencoders, that is, constructing a MW-AAE system;

[0076] S2: Construct a deep learning neural network and train the neural network;

[0077] S3: Modulate through the neural network in the transmitter, and send each frame of data according to the result of frame design;

[0078] S4: The receiver receives the data and performs frame synchronization operation to obtain the output of the SNR estimator;

[0079] S5: After normalizing the output of the SNR estimator, perform a uniform quantization operation on each value, and output noise power information;

[0080] S6: The neural network of the receiver takes the noise power information output by the SNR estimator as i...

Embodiment 2

[0084] More specifically, on the basis of Embodiment 1, the MW-AAE scheme designed in the present invention is applied to short-distance underwater VLC diffuse link scenarios in open sea water bodies and offshore water bodies. The underwater VLC simulation results under different turbulence intensities, different distances and different water bodies show that the MW-AAE scheme designed by the present invention has better performance under the same spectral efficiency than existing schemes in most underwater environments. BER performance.

[0085] The system block diagram of the MW-AAE scheme designed by the present invention is as figure 2 shown. Note that for ease of understanding, figure 2 It is only a specific embodiment of the solution designed by the present invention. In fact, the solution designed by the present invention can also use multiple LEDs of different wavelengths other than red, green and blue for communication.

[0086] A. Underwater multi-wavelength VLC...

Embodiment 3

[0147] More specifically, as a specific embodiment of the scheme designed in the present invention, N can be taken as LED = 3, λ 1 =625nm,λ 2 =525nm,λ 3 =470nm; 3 LEDs and 3 photodetectors are arranged in a straight line, the straight lines formed by the LEDs and the straight lines formed by the photodetectors are parallel to each other, and the centers of every two adjacent LEDs and every two adjacent photoelectric detectors The distance between the detector centers is equal, denoted as l 0 .

[0148] In the specific implementation process, the frame header Barker code can be used; the frame length can be 4×10 -6 s; set figure 2 The transmitter's buffer and the receiver's buffer in , so that the input of the receiver neural network is used when the symbol to be demodulated is modulated by the transmitter neural network same.

[0149] based on image 3 And the neural network structure shown in formula (11)-(18) is trained. Use the loss function shown in Equation...

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

According to the multi-wavelength LED underwater visible light communication modulation method based on deep learning provided by the invention, a plurality of LEDs with different wavelengths are used, and based on a deep learning neural network, self-adaptive modulation and demodulation are carried out by using channel and noise power information estimated by a receiver; through training, the non-negative real signal requirement of VLC based on intensity modulation and direct detection can be met, the average optical power of the constellation diagram of the transmitter can be kept constant,the method can automatically adapt to different underwater channel characteristics, and better BER performance can be achieved in most underwater environments under the same spectral efficiency compared with an existing scheme.

Description

technical field [0001] The present invention relates to the technical field of visible light communication, and more specifically, to a multi-wavelength LED underwater visible light communication modulation method based on deep learning. Background technique [0002] With the continuous exploration of the ocean by humans, underwater wireless communication technology has become increasingly important. There are mainly three types of carriers for underwater wireless communication, sound waves, radio frequency (Radio Frequency, RF) bands, and light waves. The most widely used underwater wireless communication technology is underwater acoustic communication. However, the data rate supported by underwater acoustic communication is low and the delay is high [1] H. Kaushal and G. Kaddoum, “Underwater optical wireless communication,” IEEE Access, vol.4, pp.1518-1547, Apr.2016. Underwater wireless communication based on electromagnetic waves in the RF frequency band can provide hig...

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
IPC IPC(8): H04B10/116H04B10/50H04B10/079H04B10/54H04B10/516H04B13/02H04L1/00G06N3/08
CPCG06N3/08H04B10/07953H04B10/07955H04B10/116H04B10/502H04B10/516H04B10/54H04B13/02H04L1/0057H04L1/0059H04L1/007
Inventor 江明杨子贤
Owner SUN YAT SEN 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