CN107342814A - A kind of neural net equalizer based on visible light communication - Google Patents
A kind of neural net equalizer based on visible light communication Download PDFInfo
- Publication number
- CN107342814A CN107342814A CN201710602325.0A CN201710602325A CN107342814A CN 107342814 A CN107342814 A CN 107342814A CN 201710602325 A CN201710602325 A CN 201710602325A CN 107342814 A CN107342814 A CN 107342814A
- Authority
- CN
- China
- Prior art keywords
- visible light
- module
- light communication
- neural net
- mrow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004891 communication Methods 0.000 title claims abstract description 43
- 230000001537 neural effect Effects 0.000 title claims abstract description 32
- 230000005540 biological transmission Effects 0.000 claims abstract description 14
- 230000005622 photoelectricity Effects 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 210000002569 neuron Anatomy 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 13
- 230000007935 neutral effect Effects 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 230000003321 amplification Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 210000004218 nerve net Anatomy 0.000 claims 2
- 238000001514 detection method Methods 0.000 claims 1
- 238000001914 filtration Methods 0.000 claims 1
- 230000003287 optical effect Effects 0.000 claims 1
- 230000008054 signal transmission Effects 0.000 claims 1
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/11—Arrangements specific to free-space transmission, i.e. transmission through air or vacuum
- H04B10/114—Indoor or close-range type systems
- H04B10/116—Visible light communication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
- H04L25/03006—Arrangements for removing intersymbol interference
Abstract
The invention discloses a kind of neural net equalizer based on visible light communication, including visible light communication transmitting subsystem, visible light communication transmission subsystem and the visible light communication receiving subsystem being sequentially connected;Visible light communication transmitting subsystem includes:Data acquisition module, data coding module, LED drive module and LED emitter part;One end of data coding module is connected with data acquisition module;The other end of the data coding module is connected with one end of LED drive module;The other end of LED drive module is connected with LED emitter part;Visible light communication receiving subsystem includes:Photoelectricity testing part, receiving circuit module, neural net equalizer and data decoder module;One end of receiving circuit module is connected with photoelectricity testing part;The other end of receiving circuit module is connected with one end of neural net equalizer;One section of the other end of neural net equalizer and data decoder module is connected.Have the advantages that system transfer rate is high.
Description
Technical field
The present invention relates to a kind of visible light communication technology, more particularly to a kind of neutral net based on visible light communication is balanced
Device.
Technical background
In recent years, the semiconductor illumination technique for being described as " green illumination " develops rapidly.Illuminated with traditional incandescent lamp etc.
Light source is compared, and LED has the advantages that low-power consumption, long lifespan, size are small, green.At the same time, LED has more modularity
The advantages such as energy is good, response sensitivity is high.Signal is loaded on LED with the high frequency of human eye None- identified and is transmitted, and then is urged
Illumination and technology --- the visible light communication of communicating integral can be realized by bearing one.
Compared with traditional infrared and radio communication, it is seen that optic communication have transmission power it is high, without electromagnetic interference, without Shen
Please frequency spectrum resource and information confidentiality the advantages that.However, the problem of many is still suffered from visible light communication, wherein maximum
One of challenge be the limited modulation bandwidths of LED.In general fluorescent material LED modulation bandwidths only have several megahertzs, VLC data transfers
Speed is restricted.For promoting transmission rate, except expanding bandwidth from LED structure, the design of drive circuit;Can be with
System overall bandwidth is improved by different modulation systems.But but substantially increase the complicated journey of visible light communication system
Degree.
The content of the invention
In order to overcome the disadvantages mentioned above of prior art and deficiency, led to it is an object of the invention to provide one kind based on visible ray
The neural net equalizer of letter, the neural net equalizer overcome the intersymbol caused by the limitation of LED modulation bandwidths and done
The problem of disturbing, while system complexity is reduced, the message transmission rate of system is improved, realizes that the high speed of VLC systems is led to
Letter.
The purpose of the present invention is achieved through the following technical solutions:A kind of neural net equalizer based on visible light communication,
Visible light communication system is can be applied to, the visible light communication system includes visible light communication transmitting subsystem 10, it is seen that light leads to
Believe transmission subsystem 20 and visible light communication receiving subsystem 30.The visible light communication transmitting subsystem 10 includes data acquisition
Module 11, data coding module 12, LED drive module 13 and LED emitter part 14.
Further, the data acquisition module 11 is responsible for the collection of primary signal and is transferred to data coding module 12;
The data coding module 12 is responsible for the coded treatment of data, and data after coding are transferred into LED drive module 13;It is described
LED drive module 13 produces driving current and drives LED emitter part 14 to produce visible light signal.
The transmission subsystem 20 is free space.
The receiving subsystem 30 includes photoelectricity testing part 31, receiving circuit module 32, the He of neural net equalizer 33
Data decoder module 34.Further, the visible light signal that the photoelectricity testing part 31 sends LED emitter part 14 is changed
For electric signal, and it is transferred to receiving circuit module 32.Further, described one end of receiving circuit module 32 and photoelectricity testing part
31 are connected, and the other end of the receiving circuit module is connected with the one end of neural net equalizer 33;Further, it is described to receive electricity
Road module 32 includes amplification circuit module 321, filter circuit module 322 and AD analog-to-digital conversion modules 323;Further, it is described
Amplification circuit module 321 is amplified to visible light signal, high-frequency noise of the filter circuit module 322 to received signal
Filtered out, the AD analog-to-digital conversion modules 323 convert analog signals into data signal, and are transferred to neural net equalizer
33.Further, the neural net equalizer 33 includes neural network input layer 331, neutral net hidden layer 332, nerve
Network output layer 333;The neutral net hidden layer 332, it is made up of multiple neurons 3321;The neuron 3321 is parallel,
And each neuron 3321 is connected with all taps of neural network input layer 331, the neural net equalizer 33 is responsible for
Equalization processing is carried out to signal, and the data after processing are transferred to the decoding of data decoder module 34 and obtain desired signal.
Further, the input of the neuron (3321) can be described with output relation by relationship below:
In formula, z (k) is the output of the neuron (3321);wi,j(k) it is connection i-th of neuron of input layer (331)
Output signal ui(k) weight coefficient between the input signal of j-th of the neuron of hidden layer (332), wherein, j=1,
2 ..., N represents a total of N number of hidden layer node;Each constant bjIt is the deviation of i-th of hidden layer, also referred to as thresholding;f
{ } is the activation primitive of hidden layer node.
Further, described neuron balanced device 33, learning training is carried out using backpropagation BP algorithm, including it is following
Step:
Step 1:Initialize the threshold value of neuron balanced device;
Step 2:Specify input vector x (n) and output vector d (n);
Step 3:Reality output vector y (n) is calculated according to input vector, then calculates cost function E (n);
Step 4:If E ()) it is more than designated value, according to formula
Update the threshold value of neuron balanced device, return to step 32;Otherwise, neuron equalizer training is completed.
In formula, ωij(n) the connection weighted value of n-th training, ω are representedij(n+1) connection for representing (n+1)th training adds
Weights, γ represent learning rate,Expression is differentiated.
Traditional visible light communication visible light communication system due to the restriction of light emitting diode (LED) modulation bandwidth
Transmission rate, therefore, ability of the present invention based on Neural Network Based Nonlinear mapping, proposes a kind of nerve based on visible light communication
Network equalizer, classification recovery is carried out to the signal for producing intersymbol interference due to LED narrow bandwidths, so as to be carried out to LED channels
Compensation, recover impairment signal, realize channel equalization.
Compared with prior art, the present invention has advantages below and beneficial effect:
1st, it is used as channel equalizer by the use of artificial neural network, it is only necessary to neutral net is trained using training data,
And channel circumstance need not be analyzed, make realizing for system simpler.
2nd, using the powerful nonlinear characteristic of neutral net, can effectively solve the intersymbol caused by LED bandwidth limits
Interference problem, greatly improve the transmission rate of VLC systems.
3rd, increase the transmission rate of VLC systems with LED processing technologys without using the modulation-demodulation technique of complexity, reduce
The transmission rate of system is improved while the cost of system.
Brief description of the drawings
Fig. 1 is the visible light communication system theory diagram of the present invention.
Fig. 2 is the receiving circuit module block diagram of the present invention.
Fig. 3 is the structure chart of the neural net equalizer of the present invention.
Fig. 4 is the schematic diagram of the neural network node of the present invention.
Fig. 5 is the BP algorithm of neural network schematic diagram of the present invention.
Embodiment
With reference to example and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are unlimited
In this.
Embodiment
As shown in figure 1, a kind of neural net equalizer based on visible light communication, applied to visible light communication system, institute
Stating visible light communication system includes visible light communication transmitting subsystem 10, it is seen that optic communication transmission subsystem 20 and visible light communication
Receiving subsystem 30.The visible light communication transmitting subsystem 10 includes data acquisition module 11, data coding module 12, LED
Drive module 13 and LED emitter part 14.
The data acquisition module 11 is responsible for the collection of primary signal and is transferred to data coding module 12;The data are compiled
Code module 12 is responsible for the coded treatment of data, and data after coding are transferred into LED drive module 13;The LED drives mould
Block 13 produces driving current and drives LED emitter part 14 to produce visible light signal.
The transmission subsystem 20 is free space.
The receiving subsystem 30 includes photoelectricity testing part 31, receiving circuit module 32, the He of neural net equalizer 33
Data decoder module 34.The visible light signal that LED emitter part 14 is sent is converted to electric signal by the photoelectricity testing part 31,
And it is transferred to receiving circuit module 32.Described one end of receiving circuit module 32 is connected with photoelectricity testing part 31, described to receive electricity
The other end of road module is connected with the one end of neural net equalizer 33;As shown in Fig. 2 the receiving circuit module 32 includes amplification
Circuit module 321, filter circuit module 322 and AD analog-to-digital conversion modules 323;The amplification circuit module 321 is believed visible ray
Number it is amplified, the filter circuit module 322 filters out to the high-frequency noise of received signal, the AD analog-to-digital conversions mould
Block 323 converts analog signals into data signal, and is transferred to neural net equalizer 33;The neural net equalizer 33 is negative
Duty carries out equalization processing to signal, and the data after processing are transferred into the decoding of data decoder module 34 and obtain required letter
Number.
As shown in figure 3, the neural net equalizer 33 includes neural network input layer 331, neutral net hidden layer
332, neutral net output layer 333;The neutral net hidden layer 332, it is made up of multiple neurons 3321;The neuron
3321 is parallel, and each neuron 3321 is connected with all taps of neural network input layer 331,
As shown in figure 4, the input of the neuron (3321) can be described with output relation by relationship below:
In formula, z (k) is the output of the neuron (3321);wi,j(k) it is connection i-th of neuron of input layer (331)
Output signal ui(k) weight coefficient between the input signal of j-th of the neuron of hidden layer (332), wherein, j=1,
2 ..., N represents a total of N number of hidden layer node;Each constant bjIt is the deviation of i-th of hidden layer, also referred to as thresholding;f
{ } is the activation primitive of hidden layer node.
As shown in figure 5, described neuron balanced device 33, using backpropagation BP algorithm progress learning training, including with
Lower step:
Step 1:Initialize the threshold value of neuron balanced device;
Step 2:Specify input vector x (n) and output vector d (n);
Step 3:Reality output vector y (n) is calculated according to input vector, then calculates cost function E (n);
Step 4:If E (n) is more than designated value, according to formula
Update the threshold value of neuron balanced device, return to step 32;Otherwise, neuron equalizer training is completed.
In formula, ωij(n) the connection weighted value of n-th training, ω are representedij(n+1) connection for representing (n+1)th training adds
Weights, γ represent learning rate,Expression is differentiated.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (5)
1. a kind of neural net equalizer based on visible light communication, it is characterised in that including the visible light communication being sequentially connected
Launch subsystem (10), visible light communication transmission subsystem (20) and visible light communication receiving subsystem (30);The visible ray
Communication transmitting subsystem (10) includes:Data acquisition module (11), data coding module (12), LED drive module (13) and LED
Ballistic device (14);One end of the data coding module (12) is connected with data acquisition module (11);The data encoding mould
The other end of block (12) is connected with (13) one end of LED drive module;The other end of the LED drive module (13) is sent out with LED
Emitter part (14) is connected;The visible light communication transmission subsystem (20) is free space;The visible light communication receives subsystem
System (30) includes:Photoelectricity testing part (31), receiving circuit module (32), neural net equalizer (33) and data decoder module
(34);One end of the receiving circuit module (32) is connected with photoelectricity testing part (31);The receiving circuit module (32)
The other end is connected with the one end of neural net equalizer (33);The other end of the neural net equalizer (33) decodes with data
One section of module is connected;The receiving circuit module (32) includes amplification circuit module (321) the filter circuit mould being sequentially connected
Block (322) and AD analog-to-digital conversion modules (323);
The data acquisition module (11) gathers primary signal and by data coding module (12) control after coded treatment
LED drive module (13) processed produces driving current, driving LED emitter part (14) transmitting visible light signal;The Photoelectric Detection
Device (31) receives LED emitter part (14) visible light signal for sending, and will be seen that optical signal be converted to electric signal transmission to
Receiving circuit module (32);The amplification circuit module (321) of the receiving circuit module is used to amplify the electric signal received,
Filter circuit module (322) is used for high-frequency noise interference filtering, and AD analog-to-digital conversion modules (323) are used to change analog signal
For data signal, and it is transferred to neural net equalizer (33);The neural net equalizer (33), utilizes the original of grader
Reason, balanced recovery is carried out to reception signal, then the reception signal after recovery is decoded to obtain by data decoder module (34)
To required data.
2. the neural net equalizer according to claim 1 based on visible light communication, it is characterised in that:The nerve net
Network balanced device (33) is docked using multilayer perceptron structure and is carried out equilibrium treatment, neural net equalizer (33) bag by signal
Include neural network input layer (331), neutral net hidden layer (332) and neutral net output layer (333).
3. the neural net equalizer according to claim 2 based on visible light communication, it is characterised in that:The nerve net
Network input layer (331) has set of stall tap;The neutral net hidden layer (332) has several neurons (3321);
Parallel, and each neuron (3321) and neural network input layer (331) is all for several described neurons (3321)
Tap is connected.
4. the neural net equalizer according to claim 3 based on visible light communication, it is characterised in that neuron
(3321) input and the relational expression of output relation be:
<mrow>
<mi>z</mi>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>f</mi>
<mo>{</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</msubsup>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>k</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
<mo>}</mo>
<mo>,</mo>
</mrow>
In formula, z (k) is the output of the neuron (3321);wi,j(k) it is the defeated of connection i-th of neuron of input layer (331)
Go out signal ui(k) weight coefficient between the input signal of j-th of the neuron of hidden layer (332), wherein, j=1,2 ..., N
Represent a total of N number of hidden layer node;Each constant bjIt is the deviation of i-th of hidden layer, also referred to as thresholding;F { } is hidden
Activation primitive containing node layer.
5. the neural net equalizer according to claim 2 based on visible light communication, it is characterised in that:The neuron
Balanced device (33) carries out learning training using backpropagation BP algorithm, and the backpropagation BP algorithm specifically includes following steps:
Step 1, the threshold value for initializing neuron balanced device;
Step 2, specify input vector x (n) and output vector d (n);
Step 3, according to input vector calculate reality output vector y (n), then calculate cost function E (n);
If step 4, E (n) are more than designated value, according to formula Renewal
The threshold value of neuron balanced device, return to step 32;Otherwise, neuron equalizer training is completed;
In formula, ωij(n) the connection weighted value of n-th training, ω are representedij(n+1) the connection weighted value of (n+1)th training is represented,
γ represents learning rate,Expression is differentiated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710602325.0A CN107342814A (en) | 2017-07-21 | 2017-07-21 | A kind of neural net equalizer based on visible light communication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710602325.0A CN107342814A (en) | 2017-07-21 | 2017-07-21 | A kind of neural net equalizer based on visible light communication |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107342814A true CN107342814A (en) | 2017-11-10 |
Family
ID=60217385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710602325.0A Pending CN107342814A (en) | 2017-07-21 | 2017-07-21 | A kind of neural net equalizer based on visible light communication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107342814A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108494710A (en) * | 2018-03-30 | 2018-09-04 | 中南民族大学 | Visible light communication MIMO anti-interference noise-reduction methods based on BP neural network |
CN111342896A (en) * | 2020-03-02 | 2020-06-26 | 深圳市南科信息科技有限公司 | Self-coding algorithm based on convolutional neural network and MIMO visible light communication system thereof |
CN111917471A (en) * | 2020-09-09 | 2020-11-10 | 西安工程大学 | Free space visible light communication system and communication performance optimization algorithm thereof |
CN113225131A (en) * | 2021-04-28 | 2021-08-06 | 中山大学 | Blind detection method of underwater visible light communication system |
CN113271146A (en) * | 2021-05-14 | 2021-08-17 | 中车青岛四方机车车辆股份有限公司 | Visible light communication method, device and system and computer readable storage medium |
WO2021169735A1 (en) * | 2020-02-29 | 2021-09-02 | 珠海复旦创新研究院 | Single-input multiple-output vehicle lamp networking system based on deep neural network |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105007118A (en) * | 2015-06-10 | 2015-10-28 | 重庆邮电大学 | Neural network equalization method used for indoor visible light communication system |
CN105099553A (en) * | 2015-08-31 | 2015-11-25 | 华南理工大学 | Visible light communication receiving method and system based on neural network |
CN207835454U (en) * | 2017-07-21 | 2018-09-07 | 华南理工大学 | A kind of neural net equalizer based on visible light communication |
-
2017
- 2017-07-21 CN CN201710602325.0A patent/CN107342814A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105007118A (en) * | 2015-06-10 | 2015-10-28 | 重庆邮电大学 | Neural network equalization method used for indoor visible light communication system |
CN105099553A (en) * | 2015-08-31 | 2015-11-25 | 华南理工大学 | Visible light communication receiving method and system based on neural network |
CN207835454U (en) * | 2017-07-21 | 2018-09-07 | 华南理工大学 | A kind of neural net equalizer based on visible light communication |
Non-Patent Citations (1)
Title |
---|
关伟鹏等: "基于神经网络的可见光通信接收系统的研究", 《中国激光》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108494710A (en) * | 2018-03-30 | 2018-09-04 | 中南民族大学 | Visible light communication MIMO anti-interference noise-reduction methods based on BP neural network |
WO2021169735A1 (en) * | 2020-02-29 | 2021-09-02 | 珠海复旦创新研究院 | Single-input multiple-output vehicle lamp networking system based on deep neural network |
CN111342896A (en) * | 2020-03-02 | 2020-06-26 | 深圳市南科信息科技有限公司 | Self-coding algorithm based on convolutional neural network and MIMO visible light communication system thereof |
CN111917471A (en) * | 2020-09-09 | 2020-11-10 | 西安工程大学 | Free space visible light communication system and communication performance optimization algorithm thereof |
CN111917471B (en) * | 2020-09-09 | 2021-09-28 | 西安工程大学 | Free space visible light communication system and communication performance optimization algorithm thereof |
CN113225131A (en) * | 2021-04-28 | 2021-08-06 | 中山大学 | Blind detection method of underwater visible light communication system |
CN113225131B (en) * | 2021-04-28 | 2022-04-05 | 中山大学 | Blind detection method of underwater visible light communication system |
CN113271146A (en) * | 2021-05-14 | 2021-08-17 | 中车青岛四方机车车辆股份有限公司 | Visible light communication method, device and system and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN207835454U (en) | A kind of neural net equalizer based on visible light communication | |
CN107342814A (en) | A kind of neural net equalizer based on visible light communication | |
Lee et al. | Deep learning framework for wireless systems: Applications to optical wireless communications | |
CN104158632B (en) | For the variable pulse amplitude positions modulation of visible light communication system and bit error rate ameliorative way | |
CN105099553B (en) | A kind of visible light communication method of reseptance and its system based on neuroid | |
CN105007118B (en) | A kind of neutral net equalization methods for indoor visible light communication system | |
CN106921470A (en) | A kind of visible light communication method of reseptance and its reception system based on neuroid | |
CN109905170B (en) | K-DNN-based nonlinear distortion compensation algorithm and visible light communication device | |
CN111786724B (en) | Multi-wavelength LED underwater visible light communication modulation method based on deep learning | |
CN108494710A (en) | Visible light communication MIMO anti-interference noise-reduction methods based on BP neural network | |
CN105049118B (en) | Visible light communication method and its visible light communication system based on dual modulation technology | |
Wang et al. | Experimental study on visible light communication based on LED | |
CN105162517B (en) | Visible light communication method and its visible light communication system based on pulse amplitude regulation and control | |
CN109347555A (en) | A kind of visible light communication equalization methods based on radial basis function neural network | |
CN103957056A (en) | Visible light communication system compatible with intelligent cell phone | |
Ahmed et al. | Experimental demonstration of continuous sensor data monitoring using neural network-based optical camera communications | |
CN108199892B (en) | LoRa terminal maximum transmission rate dynamic prediction method neural network based | |
CN109462437B (en) | Visible light communication system based on spatial synthesis modulation and implementation method | |
CN105046325A (en) | Circuit simulating biological neural network based on similar MOS luminescent devices | |
CN106452580A (en) | Visible light communication coding method compatible with smartphone camera and system thereof | |
CN113141214B (en) | Deep learning-based underwater optical communication misalignment robust blind receiver design method | |
CN105227240A (en) | Based on the industrial communication systems of visible ray | |
CN206728021U (en) | A kind of visible light communication system | |
CN206061004U (en) | Supervising device data transmission system based on Lifi technologies | |
CN106130637A (en) | A kind of LED-based visible light communication system and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171110 |