CN112291005A - Bi-LSTM neural network-based receiving end signal detection method - Google Patents

Bi-LSTM neural network-based receiving end signal detection method Download PDF

Info

Publication number
CN112291005A
CN112291005A CN202010844031.0A CN202010844031A CN112291005A CN 112291005 A CN112291005 A CN 112291005A CN 202010844031 A CN202010844031 A CN 202010844031A CN 112291005 A CN112291005 A CN 112291005A
Authority
CN
China
Prior art keywords
neural network
lstm
lstm neural
receiving end
signal
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
Application number
CN202010844031.0A
Other languages
Chinese (zh)
Inventor
朱勇合
龚晨
李上宾
徐正元
罗江华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology of China USTC
Original Assignee
University of Science and Technology of China USTC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Science and Technology of China USTC filed Critical University of Science and Technology of China USTC
Priority to CN202010844031.0A priority Critical patent/CN112291005A/en
Publication of CN112291005A publication Critical patent/CN112291005A/en
Pending legal-status Critical Current

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • 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
    • H04B10/60—Receivers
    • H04B10/61—Coherent receivers
    • H04B10/612—Coherent receivers for optical signals modulated with a format different from binary or higher-order PSK [X-PSK], e.g. QAM, DPSK, FSK, MSK, ASK
    • 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
    • H04B10/60—Receivers
    • H04B10/61—Coherent receivers
    • H04B10/616—Details of the electronic signal processing in coherent optical receivers
    • H04B10/6163—Compensation of non-linear effects in the fiber optic link, e.g. self-phase modulation [SPM], cross-phase modulation [XPM], four wave mixing [FWM]

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Nonlinear Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Optical Communication System (AREA)

Abstract

The invention discloses a receiving end signal detection method based on a Bi-LSTM neural network, which comprises the steps of firstly constructing a Bi-directional long-time and short-time memory neural network Bi-LSTM; the original data sent by the transmitting end and the processed signal data received by the receiving end are used as a training data set of the constructed Bi-LSTM neural network; training the Bi-LSTM neural network by using the training data set to obtain trained network parameters; and placing the receiving end at different positions to receive signals with different signal-to-noise ratios at different sampling rates, inputting the received signals into the trained Bi-LSTM neural network, and performing real-time signal detection to obtain corresponding original data. The method adopts a bidirectional long-short time neural network model to realize the signal detection of the receiving end, and can effectively inhibit the intersymbol interference and the nonlinear distortion, thereby improving the visible light communication performance.

Description

Bi-LSTM neural network-based receiving end signal detection method
Technical Field
The invention relates to the technical field of visible light communication, in particular to a receiving end signal detection method based on a Bi-LSTM neural network.
Background
With the increasing demand for transmission bandwidth with a significant increase in the number of mobile devices and users, Visible Light Communication (VLC) has attracted increasing research interest due to its potential high transmission bandwidth, high transmission rate, data security and absence of electromagnetic interference. Various VLC transmission methods have been proposed currently to improve the communication capability.
As an important supplement to Radio Frequency (RF) communication, VLC can be applied to the fields of electromagnetic sensitivity, submarine communication, and the like, and is considered as one of the most important green information technologies, however, visible light communication still faces a few problems, wherein the biggest challenge is the modulation bandwidth of LEDs, and the modulation bandwidth of general phosphor LEDs is only a few megahertz, which severely limits the rate of visible light communication. In order to improve the transmission rate, the bandwidth of the LED is expanded from the structure of the LED and the design of the pre-equalization circuit, and a high-order modulation and multi-carrier transmission scheme may be used, however, the complexity of the receiving end is greatly increased, and when the signal-to-noise ratio is low, the high-order modulation and multi-carrier may cause the influence of the peak-to-average power ratio to be more obvious, and further affect the visible light communication rate.
Disclosure of Invention
The invention aims to provide a receiving end signal detection method based on a Bi-LSTM neural network, which adopts a bidirectional long-time and short-time neural network model to realize receiving end signal detection, and can effectively inhibit intersymbol crosstalk and nonlinear distortion, thereby improving the visible light communication performance.
The purpose of the invention is realized by the following technical scheme:
a receiving end signal detection method based on a Bi-LSTM neural network, the method comprising:
step 1, constructing a Bi-directional long-and-short-term memory neural network Bi-LSTM;
step 2, taking the original data sent by the transmitting end and the processed signal data received by the receiving end as a training data set of the constructed Bi-LSTM neural network;
step 3, training the Bi-LSTM neural network by using the training data set to obtain trained network parameters;
and 4, placing the receiving end at different positions to receive signals with different signal-to-noise ratios, inputting the received signals into the trained Bi-LSTM neural network, and carrying out real-time signal detection to obtain corresponding original data.
According to the technical scheme provided by the invention, the method adopts the bidirectional long-time and short-time neural network model to realize the signal detection of the receiving end, and can effectively inhibit the intersymbol interference and nonlinear distortion, thereby improving the visible light communication performance.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a receiving end signal detection method based on a Bi-LSTM neural network according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an internal structure of a single Bi-LSTM cell according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a signal processing process of visible light communication according to an embodiment of the present invention;
FIG. 4 is a graph illustrating a comparison between the performance and the receiver position of the detection method according to the embodiment of the present invention and the conventional method;
fig. 5 is a graph illustrating a comparison between the performance and the sampling rate of the detection method according to the embodiment of the present invention and the conventional method.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
The following will describe the embodiment of the present invention in further detail with reference to the accompanying drawings, and as shown in fig. 1, a schematic flow chart of a receiving end signal detection method based on a Bi-LSTM neural network provided by the embodiment of the present invention is shown, where the method includes:
step 1, constructing a Bi-directional long-and-short-term memory neural network Bi-LSTM;
in this step, a Bi-directional long-and-short-time memory neural network Bi-LSTM is constructed, and introduced into the receiving end signal detection of the visible light OOK modulation communication system, and a signal vector received by the receiving end is used as an input signal, and a symbol estimation value corresponding to a receiving end sampling value is output through the forward calculation of the Bi-LSTM neural network, where the Bi-LSTM neural network constructed in this example specifically includes:
two Bi-LSTM neural network layers and one layer with N neuron number1The number of the full-connection layer and one layer of neuron is N2The full-connection layer, the full-connection layer with the neuron number of 2, the softmax layer and the classification layer.
In the specific implementation, a single Bi-LSTM neural network layer comprises K Bi-LSTM units, and the number of hidden layers of each Bi-LSTM unit is N3The input dimension is mx 1, and as shown in fig. 2, the internal structure of a single Bi-LSTM unit provided in the embodiment of the present invention is schematically illustrated, where the single Bi-LSTM unit includes an input gate, an output gate, and a forgetting gate, where:
the forgetting gate decides which information should be discarded or retained, and the specific expression is as follows:
ft＝σ(Wf·[ht-1，xt]+bf)
wherein σ (·) represents a sigmoid function; h ist-1And xtRespectively representing the output of the previous time and the input of the current time; wfAnd bfRespectively representing a parameter matrix and a bias matrix of the forgetting gate; f. oftAn output representing a forgetting gate;
the input gate is used for updating the state, and the specific expression is as follows:
it＝σ(Wi·[ht-1，xt]+bi)
wherein, WiAnd biRespectively representing a parameter matrix and an offset matrix of the input gate; i.e. itRepresents the output of the input gate;
the output gate is used for updating the state, and the specific expression is as follows:
ot＝σ(Wo·[ht-1，xt]+bo)
wherein, WoAnd boRespectively representing a parameter matrix and an offset matrix of the output gate; otRepresents the output of the output gate;
the operation process of the single Bi-LSTM unit is represented as:
Figure BDA0002642430120000031
Figure BDA0002642430120000032
ht＝ot×tanh(Ct)
wherein, WcIs a parameter matrix; bcIs a bias matrix; tanh (·) represents a tanh function; h istAn output representing a current time;
Figure BDA0002642430120000033
Ct-1and CtRespectively representing the temporary cell state, the cell state at the previous time and the current timeThe unit cell state at the previous time.
Step 2, taking the original data sent by the transmitting end and the processed signal data received by the receiving end as a training data set of the constructed Bi-LSTM neural network;
in this step, as shown in fig. 3, which is a schematic diagram of a signal processing process of visible light communication according to an embodiment of the present invention, original data sent by a transmitting end is modulated by on-off keying (OOK) to drive an LED, and is transmitted to a receiving end by a light wave;
at the receiving end, the APD receiver performs optical-to-electrical conversion, power amplification and analog-to-digital conversion on the received signal, and then recovers the original binary bit stream through finite impulse response FIR low-pass filtering, average filtering, sliding correlation synchronization and a signal detector, wherein:
Figure BDA0002642430120000041
representing the signal sampling value after FIR low-pass filtering, wherein the sampling frequency is N times of oversampling;
Figure BDA0002642430120000042
representing the signal sampling value after average filtering and normalization processing; N/M represents an average filtering window, wherein N represents the number of samples of a single symbol of a receiver, and M represents the number of samples corresponding to the single symbol of the input Bi-LST neural network;
the characteristic value corresponding to the nth symbol is
Figure BDA0002642430120000043
Yn＝[yn，1，yn，2，...，yn，M]Wherein y isn，kThe kth sample value representing the nth symbol.
In a specific implementation, 15000 sets of data may be collected for neural network training and 2000 sets of data may be collected for cross validation of the neural network.
Step 3, training the Bi-LSTM neural network by using the training data set to obtain trained network parameters;
the network parameters comprise a parameter matrix, a bias matrix and the like of an input gate, an output gate and a forgetting gate;
the process of training the Bi-LSTM neural network specifically comprises the following steps:
and optimizing the Bi-LSTM neural network by adopting an Adam optimizer based on a cross entropy loss function, wherein the specific loss function is expressed as:
Figure BDA0002642430120000044
wherein x isnRepresents the label corresponding to the nth symbol, namely 0 or 1;
Figure BDA0002642430120000045
a predicted value corresponding to the nth symbol is represented; n represents the number of samples of a single symbol by the receiver.
In the specific implementation, the total number of samples is not less than 15000, the proportion of training samples is 0.8, the proportion of cross validation samples is 0.2, the maximum iteration number is 10, the minimum batch is 30, and the learning rate is 0.001.
And 4, placing the receiving end at different positions to receive signals with different signal-to-noise ratios, inputting the received signals into the trained Bi-LSTM neural network, and carrying out real-time signal detection to obtain corresponding original data.
The following describes the process of the method in detail by using a specific example, the example is a receiving end signal detection method in a visible light non-line-of-sight communication system, the 3dB bandwidth of an LED transmitter of the system is 2.01MHz, the modulation rate is 50Mbps, and the specific flow of the example is as follows:
step one, constructing a Bi-directional long-and-short-term memory neural network Bi-LSTM;
in this step, a Bi-directional long-and-short-time memory neural network Bi-LSTM is constructed, and introduced into the receiving end signal detection of the visible light OOK modulation communication system, and a signal vector received by the receiving end is used as an input signal, and a symbol estimation value corresponding to a receiving end sampling value is output through the forward calculation of the Bi-LSTM neural network, where the Bi-LSTM neural network constructed in this example specifically includes:
two Bi-LSTM neural network layers, a full connection layer with the neuron number of 30, a full connection layer with the neuron number of 10, a full connection layer with the neuron number of 2, a softmax layer and a classification layer.
In the specific implementation, a single Bi-LSTM neural network layer comprises 7 Bi-LSTM units, the number of hidden layers of each Bi-LSTM unit is 30, and the input dimension is 7 multiplied by 1.
Step two, the original data sent by the transmitting end and the processed signal data received by the receiving end are used as a training data set of the constructed Bi-LSTM neural network;
in this step, as shown in fig. 3, the original data sent by the transmitting end is modulated by on-off keying (OOK) to drive the LEDs, and is transmitted by the lightwaves to the receiving end through the non-line-of-sight reflective link;
at the receiving end, the APD receiver performs optical-to-electrical conversion, power amplification and analog-to-digital conversion on the received signal, and then recovers the original binary bit stream through finite impulse response FIR low-pass filtering, average filtering, sliding correlation synchronization and a signal detector. Wherein,
Figure BDA0002642430120000051
representing the sampling value of the signal after FIR low-pass filtering, wherein the sampling frequency is 20 times of oversampling;
Figure BDA0002642430120000052
representing the signal sampling value after average filtering and normalization processing; N/M denotes an average filter window, where M is 5 and N is 20; the characteristic value corresponding to the nth symbol is
Figure BDA0002642430120000053
Yn＝[yn，1，yn，2，yn，3，yn，4，yn，5]Wherein y isn，kThe kth sample value representing the nth symbol.
In a specific implementation, 15000 sets of data are collected for neural network training, and 2000 sets of data are collected for cross validation of the neural network.
Step 3, training the Bi-LSTM neural network by using the training data set to obtain trained network parameters;
the specific parameters comprise parameter matrixes, bias matrixes and the like of an input gate, an output gate and a forgetting gate;
in this step, the process of training the Bi-LSTM neural network specifically includes:
and optimizing the Bi-LSTM neural network by adopting an Adam optimizer based on a cross entropy loss function, wherein the specific loss function is expressed as:
Figure BDA0002642430120000054
wherein x isnRepresents the label corresponding to the nth symbol, namely 0 or 1;
Figure BDA0002642430120000061
indicating the predicted value corresponding to the nth symbol and N indicating the number of samples taken by the receiver for a single symbol. The total number of samples is 15000, the training sample ratio is 0.8, the cross validation sample ratio is 0.2, the maximum iteration number is 10, the minimum batch is 30, and the learning rate is 0.001.
And 4, placing the receiving end at different positions to receive signals with different signal-to-noise ratios, inputting the received signals into the trained Bi-LSTM neural network, and carrying out real-time signal detection to obtain corresponding original data.
Fig. 4 is a schematic diagram showing a comparison curve between the detection method provided by the embodiment of the present invention and the conventional method (in the diagram, the LMMSE equalizer, the Volterra equalizer, and the DCO-OFDM) in terms of performance and receiver position, and it can be seen from fig. 4 that: the detection method of the invention obtains the optimal performance and has better generalization at different positions.
Fig. 5 is a schematic diagram illustrating a comparison curve between the performance and the sampling rate of the detection method provided by the embodiment of the present invention and the conventional method (in the diagram, the LMMSE equalizer, the volterra equalizer, and the DCO-OFDM), and it can be seen from fig. 5 that: the detection method provided by the invention obtains the optimal performance under three sampling rates, and has better generalization.
It is noted that those skilled in the art will recognize that embodiments of the present invention are not described in detail herein.
In summary, the detection method according to the embodiment of the present invention effectively suppresses inter-symbol interference and nonlinear effects, and when there is a low signal-to-noise ratio and nonlinear distortion, the transmission rate that cannot be achieved by multi-carrier and high-order modulation is realized by using OOK modulation, without channel estimation, and better performance than that of the conventional equalization algorithm is realized.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (6)

1. A receiving end signal detection method based on a Bi-LSTM neural network is characterized by comprising the following steps:
step 1, constructing a Bi-directional long-and-short-term memory neural network Bi-LSTM;
step 2, taking the original data sent by the transmitting end and the processed signal data received by the receiving end as a training data set of the constructed Bi-LSTM neural network;
step 3, training the Bi-LSTM neural network by using the training data set to obtain trained network parameters;
and 4, placing the receiving end at different positions to receive signals with different signal-to-noise ratios, inputting the received signals into the trained Bi-LSTM neural network, and carrying out real-time signal detection to obtain corresponding original data.
2. The method for detecting a receiving-end signal based on the Bi-LSTM neural network as claimed in claim 1, wherein in step 1, the constructed Bi-LSTM neural network specifically comprises:
two Bi-LSTM neural network layers and one layer with N neuron number1The number of the full-connection layer and one layer of neuron is N2The full-connection layer, the full-connection layer with the neuron number of 2, the softmax layer and the classification layer.
3. The method for detecting the signal of the receiving end based on the Bi-LSTM neural network as claimed in claim 2, wherein a single Bi-LSTM neural network layer comprises K Bi-LSTM units, and the number of hidden layers of each Bi-LSTM unit is N3The input dimension is mx 1, and a single Bi-LSTM cell contains an input gate, an output gate, and a forgetting gate, wherein:
the forgetting gate decides which information should be discarded or retained, and the specific expression is as follows:
ft＝σ(Wf·[ht-1，xt]+bf)
wherein σ (·) represents a sigmoid function; h ist-1And xtRespectively representing the output of the previous time and the input of the current time; wfAnd bfRespectively representing a parameter matrix and a bias matrix of the forgetting gate; f. oftAn output representing a forgetting gate;
the input gate is used for updating the state, and the specific expression is as follows:
it＝σ(Wi·[ht-1，xt]+bi)
wherein, WiAnd biRespectively representing a parameter matrix and an offset matrix of the input gate; i.e. itRepresents the output of the input gate;
the output gate is used for updating the state, and the specific expression is as follows:
ot＝σ(Wo·[ht-1，xt]+bo)
wherein, WoAnd boRespectively representing a parameter matrix and an offset matrix of the output gate; otRepresents the output of the output gate;
the operation process of the single Bi-LSTM unit is represented as:
Figure FDA0002642430110000021
Figure FDA0002642430110000022
ht＝ot×tanh(Ct)
wherein, WcIs a parameter matrix; bcIs a bias matrix; tanh (·) represents a tanh function; h istAn output representing a current time;
Figure FDA0002642430110000023
Ct-1and CtRespectively, the temporary cell state, the cell state at the previous time, and the cell state at the current time.
4. The receiving-end signal detection method based on the Bi-LSTM neural network of claim 1, wherein in step 2, the original data sent by the transmitting end is on-off keying modulated to drive the LEDs and transmitted to the receiving end by the light waves;
at the receiving end, the APD receiver performs optical-to-electrical conversion, power amplification and analog-to-digital conversion on the received signal, and then recovers the original binary bit stream through finite impulse response FIR low-pass filtering, average filtering, sliding correlation synchronization and a signal detector.
5. The receiving-end signal detection method based on the Bi-LSTM neural network as claimed in claim 4,
Figure FDA0002642430110000024
representing the signal sampling value after FIR low-pass filtering, wherein the sampling frequency is N times of oversampling;
Figure FDA0002642430110000025
representing the signal sampling value after average filtering and normalization processing;
N/M represents an average filtering window, wherein N represents the number of samples of a single symbol of a receiver, and M represents the number of samples corresponding to the single symbol of the input Bi-LST neural network;
the characteristic value corresponding to the nth symbol is
Figure FDA0002642430110000028
Yn＝[yn，1，yn，2，...，yn，M]Wherein y isn，kThe kth sample value representing the nth symbol.
6. The method for detecting a receiving-end signal based on the Bi-LSTM neural network as claimed in claim 1, wherein in the step 3, the process of training the Bi-LSTM neural network specifically comprises:
and optimizing the Bi-LSTM neural network by adopting an Adam optimizer based on a cross entropy loss function, wherein the specific loss function is expressed as:
Figure FDA0002642430110000026
wherein x isnA label corresponding to the nth symbol is represented;
Figure FDA0002642430110000027
a predicted value corresponding to the nth symbol is represented; n represents the number of samples of a single symbol by the receiver.
CN202010844031.0A 2020-08-20 2020-08-20 Bi-LSTM neural network-based receiving end signal detection method Pending CN112291005A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010844031.0A CN112291005A (en) 2020-08-20 2020-08-20 Bi-LSTM neural network-based receiving end signal detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010844031.0A CN112291005A (en) 2020-08-20 2020-08-20 Bi-LSTM neural network-based receiving end signal detection method

Publications (1)

Publication Number Publication Date
CN112291005A true CN112291005A (en) 2021-01-29

Family

ID=74420742

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010844031.0A Pending CN112291005A (en) 2020-08-20 2020-08-20 Bi-LSTM neural network-based receiving end signal detection method

Country Status (1)

Country Link
CN (1) CN112291005A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113285902A (en) * 2021-05-19 2021-08-20 南京航空航天大学 Design method of OFDM system detector
CN115314118A (en) * 2022-07-28 2022-11-08 聊城大学 Optical fiber nonlinear compensation method and device
CN115865129A (en) * 2022-12-01 2023-03-28 电子科技大学 Intelligent narrow-band interference elimination method based on denoising autoencoder
CN116131963A (en) * 2023-02-02 2023-05-16 广东工业大学 Fiber link multipath interference noise equalization method based on LSTM neural network
CN116506261A (en) * 2023-06-27 2023-07-28 南昌大学 Visible light communication sensing method and system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105680941A (en) * 2016-02-26 2016-06-15 中国科学技术大学 Underwater LED (Light-Emitting Diode) long distance communication system based on visible light
US20180300608A1 (en) * 2017-04-12 2018-10-18 Yodlee, Inc. Neural Networks for Information Extraction From Transaction Data
US20190130248A1 (en) * 2017-10-27 2019-05-02 Salesforce.Com, Inc. Generating dual sequence inferences using a neural network model
CN110136729A (en) * 2019-03-27 2019-08-16 北京奇艺世纪科技有限公司 Model generating method, audio-frequency processing method, device and computer readable storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105680941A (en) * 2016-02-26 2016-06-15 中国科学技术大学 Underwater LED (Light-Emitting Diode) long distance communication system based on visible light
US20180300608A1 (en) * 2017-04-12 2018-10-18 Yodlee, Inc. Neural Networks for Information Extraction From Transaction Data
US20190130248A1 (en) * 2017-10-27 2019-05-02 Salesforce.Com, Inc. Generating dual sequence inferences using a neural network model
CN110136729A (en) * 2019-03-27 2019-08-16 北京奇艺世纪科技有限公司 Model generating method, audio-frequency processing method, device and computer readable storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YONGHE ZHU: "Indoor Non-line of sight Visible Light Communication with a Bi-LSTM Neural Network", 《2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS WORKSHOPS (ICC WORKSHOPS)》 *
YUE QIU: "A segment-wise reconstruction method based on bidirectional long short term memory for Power Line Interference suppression", 《BIOCYBERNETICS AND BIOMEDICAL ENGINEERING》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113285902A (en) * 2021-05-19 2021-08-20 南京航空航天大学 Design method of OFDM system detector
CN113285902B (en) * 2021-05-19 2023-03-14 南京航空航天大学 Design method of OFDM system detector
CN115314118A (en) * 2022-07-28 2022-11-08 聊城大学 Optical fiber nonlinear compensation method and device
CN115314118B (en) * 2022-07-28 2024-02-20 聊城大学 Optical fiber nonlinear compensation method and device
CN115865129A (en) * 2022-12-01 2023-03-28 电子科技大学 Intelligent narrow-band interference elimination method based on denoising autoencoder
CN115865129B (en) * 2022-12-01 2024-03-29 电子科技大学 Narrowband interference intelligent elimination method based on denoising self-encoder
CN116131963A (en) * 2023-02-02 2023-05-16 广东工业大学 Fiber link multipath interference noise equalization method based on LSTM neural network
CN116506261A (en) * 2023-06-27 2023-07-28 南昌大学 Visible light communication sensing method and system
CN116506261B (en) * 2023-06-27 2023-09-08 南昌大学 Visible light communication sensing method and system

Similar Documents

Publication Publication Date Title
CN112291005A (en) Bi-LSTM neural network-based receiving end signal detection method
Schädler et al. Soft-demapping for short reach optical communication: A comparison of deep neural networks and volterra series
CN109672639B (en) Signal demodulation method based on machine learning
CN109905170B (en) K-DNN-based nonlinear distortion compensation algorithm and visible light communication device
CN110166391B (en) Baseband precoding MSK signal demodulation method based on deep learning under impulse noise
CN113630130B (en) End-to-end digital communication demodulation method
CN103117964A (en) Method and device of detection of signal of 60GHz millimeter wave communication system
CN112598072B (en) Equalization method of improved Volterra filter based on weight coefficient migration of SVM training
CN110311876A (en) The implementation method of underwater sound OFDM receiver based on deep neural network
CN112600618A (en) Attention mechanism-based visible light signal equalization system and method
CN111200470A (en) High-order modulation signal transmission control method suitable for being interfered by nonlinearity
Li et al. IQ symbols processing schemes with LSTMs in OFDM system
CN115765876A (en) Probability shaping signal equalization method based on improved LSTM nonlinear equalizer
Abbasi et al. Deep learning-based list sphere decoding for Faster-than-Nyquist (FTN) signaling detection
CN115834310B (en) LGTransformer-based communication signal modulation identification method
CN114500189B (en) Direct pre-equalization method, system, device and medium for visible light communication
CN101651643A (en) Blind equalization method for wavelet neural network based on space diversity
He et al. Design and implementation of adaptive filtering algorithm for vlc based on convolutional neural network
Zhang et al. An improved end-to-end optical transmission system based on deep learning
Lu et al. An improved one-bit ofdm receiver based on model-driven deep learning
KR102596571B1 (en) Deep learning-assisted index estimator for generalized LED index modulation OFDM in visible light communication
Shi et al. Receiver distortion nornalization method for specific emitter identification
CN114567527A (en) Reconfigurable intelligent surface assisted superposition guidance fusion learning channel estimation method
CN115276818B (en) Deep learning-based optical-load wireless transmission link demodulation method
Feng et al. The design of satellite equalizer based on CNN

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

Application publication date: 20210129

RJ01 Rejection of invention patent application after publication