CN111970078B - Frame synchronization method for nonlinear distortion scene - Google Patents
Frame synchronization method for nonlinear distortion scene Download PDFInfo
- Publication number
- CN111970078B CN111970078B CN202010821398.0A CN202010821398A CN111970078B CN 111970078 B CN111970078 B CN 111970078B CN 202010821398 A CN202010821398 A CN 202010821398A CN 111970078 B CN111970078 B CN 111970078B
- Authority
- CN
- China
- Prior art keywords
- frame synchronization
- vector
- sequence
- output
- online
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 35
- 238000005259 measurement Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- SYTBZMRGLBWNTM-UHFFFAOYSA-N flurbiprofen Chemical compound FC1=CC(C(C(O)=O)C)=CC=C1C1=CC=CC=C1 SYTBZMRGLBWNTM-UHFFFAOYSA-N 0.000 claims 1
- 238000004891 communication Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04J—MULTIPLEX COMMUNICATION
- H04J3/00—Time-division multiplex systems
- H04J3/02—Details
- H04J3/06—Synchronising arrangements
- H04J3/0602—Systems characterised by the synchronising information used
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Synchronisation In Digital Transmission Systems (AREA)
Abstract
The invention discloses a frame synchronization method of a nonlinear distortion scene, which comprises the following steps: collecting N t A sequence of M N long samples y i (1) ,y i (2) ,…y i (M) ,i＝1,2,…,N t (ii) a Weighted superposition to obtain a superposed sample sequence y i (S) ,i＝1,2,…,N t (ii) a For the superimposed sample sequence y i (S) Preprocessing to obtain synchronization metrics
i＝1,2,…,N t (ii) a Constructing an ELM-based network, and constructing a tag T according to a frame synchronization deviation value of a received signal i ,i＝1,2,…,N t Learning network parameters; learning to obtain frame synchronization offset estimation value by using learning-obtained ELM network model
The invention can improve the frame synchronization performance under the nonlinear distortion scene, and compared with the traditional correlation method, the frame synchronization performance of the invention is greatly improved.
Description
Technical Field
The invention relates to the technical field of wireless communication frame synchronization, in particular to a frame synchronization method for a nonlinear distortion scene.
Background
As one of the important components in a communication system, the performance of the frame synchronization method is good and bad, which directly affects the performance of the whole wireless communication system. However, the wireless communication system inevitably has nonlinear distortion, such as high-efficiency power amplifier distortion, analog-to-digital or digital-to-analog converter distortion, and distortion caused by two-way imbalance of I/Q, etc. In addition, in the next generation wireless communication system (e.g. 6G system), in order to avoid the transceiver being too expensive, low cost and low resolution devices (e.g. power amplifier, AD sampler) are required, which causes the non-linear distortion to be particularly prominent. The traditional frame synchronization method (such as the correlation method) and the time-new frame synchronization method mostly do not consider the nonlinear distortion scene, so that the method is difficult to be applied under the nonlinear distortion condition. Machine learning has excellent learning ability for nonlinear distortion, however, frame synchronization techniques based on machine learning have little research and do not achieve good synchronization performance, and improvement is urgently needed.
Therefore, the invention utilizes a machine learning method and develops interframe correlation prior information to form a frame synchronization method for improving the error probability performance of frame synchronization. At a receiving end, firstly, carrying out weighted superposition preprocessing on frames, developing interframe correlation prior information, and preliminarily capturing frame synchronization measurement characteristics; then, an ELM frame synchronization network is constructed, and the estimation of frame synchronization deviation is trained off line; and finally, estimating the frame synchronization offset on line by combining the preprocessed ELM network parameters with the learned ELM network parameters. Aiming at wireless communication scenes with nonlinear distortion, such as 5G and 6G systems, the method can improve the error probability performance of the frame synchronization and promote the intelligent processing level of the frame synchronization, brings a plurality of implementable schemes for intelligent frame synchronization research, and has great significance.
Disclosure of Invention
Compared with the traditional related synchronization method, the method combines multi-frame weighted superposition and an ELM network, and effectively improves the frame synchronization performance under the nonlinear distortion system.
The specific invention scheme is as follows:
a frame synchronization method for a nonlinear distortion scene comprises the following steps:
(a) collecting N t M frames of N long sample sequences y i (1) ,y i (2) ,…y i (M) ,i＝1,2,…,N t ；
(b) For y i (1) ,y i (2) ,…y i (M) Carrying out weighted superposition to obtain a superposed sample sequence y i (S) ,i＝1,2,…,N t
(c) For the superimposed sample sequence y i (S) Preprocessing to obtain standard measurement vector
(d) Constructing an ELM network, and constructing a tag T according to the frame synchronization deviation value of the received signal i ,i＝1,2,…,N t Learning network parameters;
(e) learning to obtain frame synchronization offset estimation value by using learning-obtained ELM network model
Further, the obtaining of the M frames of N-long sample sequence of step (a) may be represented as:
wherein M and N are set according to engineering experience.
Further, the method step (b) the weighted overlap-add is represented as:
y i (S) ＝μ 1 y i (1) +μ 2 y i (2) +…+μ M y i (M) ；
the mu i I is 1,2, …, and M is a weighting coefficient; and setting according to the received signal-to-noise ratio of each frame.
Further, the pretreatment step in step (c) of the method is:
(c1) one-time training superposition sample sequence y (S) Middle observation length of N s Observation sequence of
And length N s Training sequence of
After 'cross-correlation operation' is carried out, the 'cross-correlation measurement' gamma is obtained t Namely:
the observation length is N s Setting according to engineering experience;
the t represents the initial index position of the observed superposition sequence, and t belongs to [1, K ]]For example, t-1 denotes a sequence y of samples from the superposition (S) Begins to observe N s A long sample sequence;
denotes y (S) Middle t to t + N s -1 element;
the K is N-N s +1, representing the size of the search window;
(c2) measured by K correlations
Constructing a metric vector
To N t Individual measurement vector gamma i Normalization processing is carried out to obtain a standard measurement vector
Namely:
said N is t According to the engineering experience setting, the | | | gamma i | represents the measurement vector γ i Frobenius norm of (1).
Further, the network model and parameters in step (d) are:
the ELM network model comprises 1 input layer, 1 hidden layer and 1 output layer, wherein the number of nodes of the input layer is K, and the number of nodes of the hidden layer is K
The number of nodes of an output layer is K, a hidden layer adopts sigmoid as an activation function, and preprocessed standard measurement vectors are integrated
As an input;
and m is set according to engineering experience.
Further, the step (d) of constructing the tag comprises the steps of:
according to the synchronization deviation value tau i ,i＝1,2,…,N t Forming a set of tags
The label T i ,i＝1,2,…,N t According to the synchronization deviation value tau i Obtained by one-hot coding, i.e.
Said tau i From the received signal y i And determining, and collecting according to a statistical channel model or according to an actual scene by combining the existing method or equipment.
Further, the offline training process of step (d) specifically includes the following steps:
(d1) generating weights from random distributions
And bias
Sequentially combining the standard metric vectors
Input ELM network, hidden layerOutput the output
Expressed as:
the σ (-) represents an activation function sigmoid;
(d2) from N t Individual metric vector
Obtained N t A hidden layer output H i Constructing hidden layer output matrices
Obtaining output weight according to hidden layer output matrix H and label set T constructed in step (a3)
The above-mentioned
Moore-Penrose pseudoinverse representing H;
(d3) model parameters W, b and β are saved.
Further, the on-line operation process of the step (e) comprises the following steps:
(e1) receiving M frames of N long online sample sequences y online (1) ,y online (2) ,…,y online (M) Performing superposition preprocessing according to the steps (b) and (c) to obtain an online standard measurement vector
Will be provided with
The vector is sent to an ELM network model to learn an output vector
Expressed as:
(e2) finding the index position of the maximum of the squared magnitude in the output vector O, i.e. the frame synchronization estimate
The beneficial effects of the invention are: the frame synchronization performance under the nonlinear distortion system is improved.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a flowchart of ELM network offline training;
fig. 3 is a diagram of an on-line operation process of the ELM network.
Detailed Description
The technical solutions of the present invention are further described in detail below with reference to the accompanying drawings, but the scope of the present invention is not limited to the following.
As shown in fig. 1, a method for frame synchronization of a non-linear distortion scene includes the following steps:
(a) collecting N t M frames of N long sample sequences y i (1) ,y i (2) ,…y i (M) ，i＝1,2,…,N t ；
Specifically, the obtaining of the M frames of N-long sample sequence in step (a) of the method may be represented as:
wherein M and N are set according to engineering experience.
(b) To y i (1) ,y i (2) ,…y i (M) Carrying out weighted superposition to obtain a superposed sample sequence y i (S) ，i＝1,2,…,N t
Specifically, the weighted overlap-add of the method step (b) can be expressed as:
y i (S) ＝μ 1 y i (1) +μ 2 y i (2) +…+μ M y i (M) ；
the mu i I is 1,2, …, and M is a weighting coefficient; and setting according to the received signal-to-noise ratio of each frame.
Example 1: the weighting coefficients are set as follows:
suppose that M is 3 and the signal-to-noise ratio of the 3-frame signal is alpha respectively 1 ,α 2 ,α 3 ，
(c) For the superimposed sample sequence y i (S) Preprocessing to obtain synchronization metrics
Specifically, the pretreatment step in step (c) of the method is:
(c1) one-time training superposition sample sequence y (S) Middle observation length of N s Observation sequence of
And length N s Training sequence of
After the "cross-correlation operation" is performed,obtaining a 'cross-correlation metric' gamma t Namely:
the observation length is N s Setting according to engineering experience;
the t represents the initial index position of the observed superposition sequence, and t belongs to [1, K ]]For example, t-1 denotes a sequence y of samples from the superposition (S) First element of (2) begins to observe N s A long sample sequence;
denotes y (S) Middle t to t + N s -1 element;
the K is N-N s +1, representing the size of the search window;
(c2) measured by K correlations
Constructing a metric vector
To N t Individual measurement vector gamma i Normalization processing is carried out to obtain a standard measurement vector
Namely:
said N is t According to the engineering experience setting, the | | | gamma i | represents the measurement vector γ i Frobenius norm of (1).
(d) Constructing an ELM network, and constructing a tag T according to the frame synchronization deviation value of the received signal i ,i＝1,2,…,N t Learning network parameters;
in an embodiment of the present application, the network model and parameters in step (d) of the method are:
the ELM network model comprises 1 input layer, 1 hidden layer and 1 output layer, wherein the number of nodes of the input layer is K, and the number of nodes of the hidden layer is K
The number of nodes of an output layer is K, a hidden layer adopts sigmoid as an activation function, and preprocessed standard measurement vectors are integrated
As an input;
and m is set according to engineering experience.
Specifically, the step (d) of the method for constructing the tag comprises the following steps:
according to the synchronization deviation value tau i ,i＝1,2,…,N t Forming a set of tags
The label T i ,i＝1,2,…,N t According to the synchronization deviation value tau i Obtained by one-hot coding, i.e.
Said tau i From the received signal y i And determining, and collecting according to a statistical channel model or according to an actual scene by combining the existing method or equipment.
Example 2: the label in step (d) is exemplified as follows:
let N be 64, τ i ＝5，N t ＝10 5 ，
Training labels:
as shown in fig. 2, in the embodiment of the present application, the offline training process of step (d) of the method specifically includes the following steps:
(d1) generating weights from random distributions
And bias
Sequentially combining the standard metric vectors
Input to ELM network, hidden layer output
Expressed as:
the σ (-) represents an activation function sigmoid;
(d2) from N t Individual metric vector
Obtained N t A hidden layer output H i Constructing hidden layer output matrices
According to the hidden layer output matrix H and the label set T constructed in the step (d), the output weight is obtained
The above-mentioned
Moore-Penrose pseudoinverse representing H;
(d3) model parameters W, b and β are saved.
(e) ELM network obtained by learningLearning the network model to obtain the estimated value of frame synchronization shift
As shown in fig. 3, in the embodiment of the present application, specifically, the online operation process of step (e) includes the following steps:
(e1) receiving M frames of N long online sample sequences y online (1) ,y online (2) ,…,y online (M) Performing superposition preprocessing according to the steps (b) and (c) to obtain an online standard measurement vector
Will be provided with
The vector is sent to an ELM network model to learn an output vector
Expressed as:
(e2) finding the index position of the maximum of the squared amplitudes in the output vector O, i.e. the frame synchronization estimate
It is to be understood that the embodiments described herein are for the purpose of assisting the reader in understanding the manner of practicing the invention and are not to be construed as limiting the scope of the invention to such particular statements and embodiments. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (2)
1. A frame synchronization method for a nonlinear distortion scene is characterized by comprising the following steps:
(a) collecting N t M frames of N long sample sequences y i (1) ,y i (2) ,…y i (M) ,i＝1,2,…,N t ；
The sequence of samples N long for M frames is represented as:
wherein M and N are set according to engineering experience;
(b) for y i (1) ,y i (2) ,…y i (M) Carrying out weighted superposition to obtain a superposed sample sequence y i (S) ,i＝1,2,…,N t
The weighted overlap-add is represented as:
y i (S) ＝μ 1 y i (1) +μ 2 y i (2) +…+μ M y i (M) ；
the mu i I is 1,2, …, and M is a weighting coefficient set according to the received signal-to-noise ratio of each frame;
(c) for the superimposed sample sequence y i (S) Preprocessing to obtain standard measurement vector
The pretreatment steps are as follows:
(c1) one-time training superposition sample sequence y (S) Middle observation length of N s Observation sequence of
And length N s Training sequence of
After 'cross-correlation operation' is carried out, the 'cross-correlation measurement' gamma is obtained t Namely:
the observation length is N s Setting according to engineering experience;
the t represents the initial index position of the observed superposition sequence, and t belongs to [1, K ]]For example, t-1 denotes a sequence y of samples from the superposition (S) Begins to observe N s A long sample sequence;
denotes y (S) Middle t to t + N s -1 element;
the K is N-N s +1, representing the size of the search window;
(c2) measured by K correlations
Constructing a metric vector
To N t Individual measurement vector gamma i Normalization processing is carried out to obtain a standard measurement vector
Namely:
said N is t According to the engineering experience setting, the | | | gamma i | | denotes the measurement vector γ i Froben of (1)An ius norm;
(d) constructing an ELM network, and constructing a label T according to the frame synchronization deviation value of the received signal i ,i＝1,2,…,N t Obtaining a network model and parameters through an off-line training process;
the steps of constructing the tag are as follows:
according to the synchronisation offset value tau i ,i＝1,2,…,N t Forming a set of tags
The label T i ,i＝1,2,…,N t According to the synchronization deviation value tau i Obtained by one-hot coding, i.e.
Said τ being i From the received signal y i Determining, and collecting according to a statistical channel model or according to an actual scene by combining the existing method or equipment;
the off-line training process specifically comprises the following steps:
(d1) generating weights from random distributions
And bias
Sequentially dividing the standard metric vector
Input to ELM network, hidden layer output
Expressed as:
the σ (-) represents an activation function sigmoid;
(d2) from N t Individual metric vector
Obtained N t A hidden layer output H i Constructing hidden layer output matrices
Obtaining output weight according to hidden layer output matrix H and label set T
The above-mentioned
Moore-Penrose pseudoinverse representing H;
(d3) saving model parameters W, b and beta;
(e) obtaining a frame synchronization offset estimation value through an online operation process by utilizing an ELM network model obtained through learning;
the online operation process comprises the following steps:
receiving M frames of N long online sample sequences y online (1) ,y online (2) ,…,y online (M) Performing superposition preprocessing according to the steps (b) and (c) to obtain an online standard measurement vector
Will be provided with
The vector is sent to an ELM network model to learn an output vector
Expressed as:
(e1) find the index position of the maximum value of the magnitude squared in the output vector O, the formula is as follows:
in the formula
Is the frame synchronization estimate.
2. The method of claim 1, wherein the network model and parameters in step (d) are:
the ELM network model comprises 1 input layer, 1 hidden layer and 1 output layer, wherein the number of nodes of the input layer is K, the number of nodes of the hidden layer is N-mK, the number of nodes of the output layer is K, the hidden layer adopts sigmoid as an activation function, and the preprocessed standard measurement vectors are integrated
As an input;
and m is set according to engineering experience.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010821398.0A CN111970078B (en) | 2020-08-14 | 2020-08-14 | Frame synchronization method for nonlinear distortion scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010821398.0A CN111970078B (en) | 2020-08-14 | 2020-08-14 | Frame synchronization method for nonlinear distortion scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111970078A CN111970078A (en) | 2020-11-20 |
| CN111970078B true CN111970078B (en) | 2022-08-16 |
Family
ID=73387814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010821398.0A Active CN111970078B (en) | 2020-08-14 | 2020-08-14 | Frame synchronization method for nonlinear distortion scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111970078B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112688772B (en) * | 2020-12-17 | 2022-08-26 | 西华大学 | Machine learning superimposed training sequence frame synchronization method |
| CN113112028B (en) * | 2021-04-06 | 2022-07-01 | 西华大学 | Machine learning time synchronization method based on label design |
| CN114096000B (en) * | 2021-11-18 | 2023-06-23 | 西华大学 | Combined frame synchronization and channel estimation method based on machine learning |
| CN117295149B (en) * | 2023-11-23 | 2024-01-30 | 西华大学 | Frame synchronization method and system based on low-complexity ELM assistance |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103222243A (en) * | 2012-12-05 | 2013-07-24 | 华为技术有限公司 | Data processing method and apparatus |
| CN108512795A (en) * | 2018-03-19 | 2018-09-07 | 东南大学 | A kind of OFDM receiver baseband processing method and system based on low Precision A/D C |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252560A (en) * | 2007-11-01 | 2008-08-27 | 复旦大学 | High-performance OFDM frame synchronization algorithm |
| CN102291360A (en) * | 2011-09-07 | 2011-12-21 | 西南石油大学 | Superimposed training sequence based optical OFDM (Orthogonal Frequency Division Multiplexing) system and frame synchronization method thereof |
| ES2593093B1 (en) * | 2015-06-05 | 2017-09-19 | Fundacio Centre Tecnologic De Telecomunicacions De Catalunya | Method and device for frame synchronization in communication systems |
| US9692588B2 (en) * | 2015-07-07 | 2017-06-27 | Samsung Electronics Co., Ltd. | System and method for performing synchronization and interference rejection in super regenerative receiver (SRR) |
| CN106130945B (en) * | 2016-06-02 | 2019-06-28 | 泰凌微电子（上海）有限公司 | Frame synchronization and carrier wave frequency deviation associated detecting method and device |
-
2020
- 2020-08-14 CN CN202010821398.0A patent/CN111970078B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103222243A (en) * | 2012-12-05 | 2013-07-24 | 华为技术有限公司 | Data processing method and apparatus |
| CN108512795A (en) * | 2018-03-19 | 2018-09-07 | 东南大学 | A kind of OFDM receiver baseband processing method and system based on low Precision A/D C |
Non-Patent Citations (2)
| Title |
|---|
| ELM-Based Frame Synchronization in Burst-Mode Communication Systems With Nonlinear Distortion;Chaojin Qing，etc;《IEEE Wireless Communications Letters》;20200221;第2-3页 * |
| 非线性失真场景下基于ELM帧同步改进方法;卿朝进余旺董磊杜艳红唐书海;《科技创新与应用 》;20210208;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111970078A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111970078B (en) | Frame synchronization method for nonlinear distortion scene | |
| CN110971457B (en) | Time synchronization method based on ELM | |
| CN108566257B (en) | Signal recovery method based on back propagation neural network | |
| CN107529222B (en) | WiFi indoor positioning system based on deep learning | |
| CN110336594B (en) | Deep learning signal detection method based on conjugate gradient descent method | |
| CN112688772B (en) | Machine learning superimposed training sequence frame synchronization method | |
| CN113114599B (en) | Modulation identification method based on lightweight neural network | |
| CN114268388B (en) | Channel estimation method based on improved GAN network in large-scale MIMO | |
| CN115577305B (en) | Unmanned aerial vehicle signal intelligent recognition method and device | |
| CN111050315A (en) | Wireless transmitter identification method based on multi-core two-way network | |
| CN108806723A (en) | Baby's audio recognition method and device | |
| CN113807214A (en) | Small target face recognition method based on deit attached network knowledge distillation | |
| CN113762529A (en) | Machine learning timing synchronization method based on statistical prior | |
| CN114759997B (en) | MIMO system signal detection method based on data model double driving | |
| CN115631771A (en) | Sound event detection and positioning method based on combined convolutional neural network | |
| CN114614920B (en) | Signal detection method based on data and model combined driving of learning factor graph | |
| CN111652021A (en) | Face recognition method and system based on BP neural network | |
| CN113343796B (en) | Knowledge distillation-based radar signal modulation mode identification method | |
| CN114070415A (en) | Optical fiber nonlinear equalization method and system | |
| CN113792751B (en) | Cross-domain behavior recognition method, device, equipment and readable storage medium | |
| CN113596757A (en) | Rapid high-precision indoor fingerprint positioning method based on integrated width learning | |
| CN113852434A (en) | LSTM and ResNet assisted deep learning end-to-end intelligent communication method and system | |
| CN114096000B (en) | Combined frame synchronization and channel estimation method based on machine learning | |
| CN118074791B (en) | Satellite communication method and system based on non-orthogonal multiple access and orthogonal time-frequency space modulation | |
| CN115952407B (en) | Multipath signal identification method considering satellite time sequence and airspace interactivity |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20201120 Assignee: Chengdu Tiantongrui Computer Technology Co.,Ltd. Assignor: XIHUA University Contract record no.: X2023510000028 Denomination of invention: A frame synchronization method for nonlinear distortion scenarios Granted publication date: 20220816 License type: Common License Record date: 20231124 |