CN114978840B - Physical layer safety and high-spectrum efficiency communication method in wireless network - Google Patents
Physical layer safety and high-spectrum efficiency communication method in wireless network Download PDFInfo
- Publication number
- CN114978840B CN114978840B CN202210518460.8A CN202210518460A CN114978840B CN 114978840 B CN114978840 B CN 114978840B CN 202210518460 A CN202210518460 A CN 202210518460A CN 114978840 B CN114978840 B CN 114978840B
- Authority
- CN
- China
- Prior art keywords
- data
- deep neural
- neural network
- network
- wireless network
- 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
- 238000004891 communication Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000001228 spectrum Methods 0.000 title abstract description 23
- 238000013528 artificial neural network Methods 0.000 claims abstract description 47
- 238000005516 engineering process Methods 0.000 claims abstract description 27
- 238000013461 design Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 23
- 230000005540 biological transmission Effects 0.000 claims description 16
- 239000013256 coordination polymer Substances 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000005562 fading Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/26—Systems using multi-frequency codes
- H04L27/2601—Multicarrier modulation systems
- H04L27/2626—Arrangements specific to the transmitter only
-
- 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
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/26—Systems using multi-frequency codes
- H04L27/2601—Multicarrier modulation systems
- H04L27/2626—Arrangements specific to the transmitter only
- H04L27/2627—Modulators
- H04L27/2628—Inverse Fourier transform modulators, e.g. inverse fast Fourier transform [IFFT] or inverse discrete Fourier transform [IDFT] modulators
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/26—Systems using multi-frequency codes
- H04L27/2601—Multicarrier modulation systems
- H04L27/2647—Arrangements specific to the receiver only
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/26—Systems using multi-frequency codes
- H04L27/2601—Multicarrier modulation systems
- H04L27/2647—Arrangements specific to the receiver only
- H04L27/2649—Demodulators
- H04L27/265—Fourier transform demodulators, e.g. fast Fourier transform [FFT] or discrete Fourier transform [DFT] demodulators
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Discrete Mathematics (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a physical layer safety and high-spectrum efficiency communication method in a wireless network, and belongs to the technical field of communication. The invention provides a design scheme of MIFC in a transmitting link, detects a media sequence number, a cutting media sequence number and a rotation position signal of MIFC-based wireless network communication in a receiving link through a trained deep neural network, and the MIFC technology simultaneously maps media sequence number bits, cutting media sequence number bits and rotation position bits and performs feature coding by using the trained deep neural network, thereby breaking through the concept of improving frequency spectrum efficiency and traditional physical layer safety by modulation, having the characteristics of simple design, high frequency spectrum efficiency and strong safety performance, and being very suitable for low-computation force sensing equipment such as the Internet of vehicles, the satellite Internet of things, the ocean Internet of things and the like to safely transmit big data.
Description
Technical Field
The invention belongs to the technical field of communication, and relates to the technologies of physical layer safety, high spectral efficiency modulation, deep learning, feature extraction and encoding, feature recovery and decoding and OFDM (Orthogonal Frequency Division Multiplexing).
Background
With the continuous deepening of the exploration, development and utilization degree of resources by adopting wireless sensor networks by human beings, the requirements on the quality, the speed, the safety and the like of information transmission in various wireless (acoustic, optical and electric) environments are increasingly raised in the fields of military, business and civil use. In order to meet the full coverage of communication, wireless networks based on acoustic, optical and electric media are widely used as supplements to wired networks in air-to-ground sea information transmission, such as: the underwater acoustic communication technology solves the problems of acquisition, analysis and comprehensive utilization of underwater resource detection information; the visible light communication technology enables air users to use terminal equipment without electromagnetic interference to the aircraft; the radio network solves the problem of transmission of data acquired by the sensor in severe environments where the trace is rare. However, open wireless transmission channels and scarce spectrum resources make large data transmission technologies in wireless networks more challenging. In order to improve the spectrum utilization rate and spectrum efficiency in a wireless network, reduce the complexity of detection and design of equipment and enhance the safety of data, researchers at home and abroad propose a series of physical layer safety and high-spectrum efficiency communication modes such as index modulation, spread spectrum, cooperative interference and the like. Although the existing communication technology has incomparable advantages in terms of spectrum efficiency and security, the problem of enhancing data security communication and further reducing the complexity of equipment while improving the spectrum efficiency is faced, and scientific researchers who study the security and high-spectrum efficiency communication of a physical layer of a wireless network are generally focused. Media Index Feature Coding (MIFC) is a more spectrally efficient, computationally less complex, and safer communication technique than existing communication methods that combine techniques with high spectral efficiency and security. Therefore, the MIFC technology is firstly proposed and introduced into the wireless network, so that the high design complexity of an index modulation and cooperative interference scheme is avoided, and particularly, the integrated reliability of the traditional transmitting link combination design and the design complexity of a receiving link decoding part are simplified, thereby improving the wireless network communication safety and the frequency spectrum efficiency in a time-varying channel environment and fully embodying the superior performance of the wireless network communication safety and the frequency spectrum efficiency.
Disclosure of Invention
The invention aims to design MIFC technology and adopts the MIFC technology to improve the communication safety and the frequency spectrum efficiency of a wireless network.
The technical scheme of the invention is as follows:
a physical layer security and high-spectrum efficiency communication method in a wireless network is provided, wherein the scheme is shown in figure 1, and the specific steps and the details of the steps are as follows:
step 1, designing a wireless network communication transmitting link based on MIFC technology;
step 2, designing a wireless network communication receiving link based on MIFC technology.
In the step 1, since the wireless network communication system adopts the MIFC technology and the MIFC communication technology performs Feature Coding (FC) on the Index Medium (IM), the wireless network communication system has very high spectrum efficiency and security performance, and the schematic diagram is shown in fig. 2. Data transmission link in MIFC communication technology: firstly, dividing information bits of a source into media sequence number bits, cutting the media sequence number bits and rotation position bits, and sending the media sequence number bits and the rotation position bits into an MIFC module; in the MIFC module, media data is selected by using media sequence number bits, and then cut media data is selected by using cut media sequence number bits; and then rotating the selected cutting media data according to the rotation position bits of the cutting media, finally performing feature coding on the rotated cutting media by using a deep neural network, performing IFFT, CP adding and P/S, DAC on the coded data, and sending the coded data to an RF circuit for transmission. The specific steps in the step 1 are summarized as follows:
step 1.1, the source information bits are divided into media sequence number bits (MedSleBits), cut media sequence number bits (MedSplBits) and rotation position bits (RotaPosBits).
Step 1.2, first index media data in a predefined set of media data with MedSlebits, while subjecting the selected media data to 2 according to MedSplbits length M M Cutting for the second time; secondly, the cut media data is indexed by using MedSplBits; then using RotaPosBits to rotate the selected media data of MedSplBits; and finally, the mapped rotating media data is placed into a deep neural network to perform feature coding on the rotating media data.
Step 1.3, the processed feature code data is subjected to IFFT, CP and P/S, DAC and then sent to an RF circuit for transmission.
In the step 2, the wireless network communication is also faced with the problem of difficulty in signal detection due to the variability of the wireless communication channel. The invention adopts the deep neural network to perform the feature coding technology, not only improves the frequency spectrum efficiency and the safety of the system, but also recognizes the features of the rotating media data through the deep neural network, thereby reducing the problem of difficult detection of communication signals (MedSleBits, medSplBits and RotaPosBits), and the schematic diagram is shown in figure 3. Data receiving link in wireless network communication method based on MIFC technology: firstly, performing ADC, S/P, CP removal and FFT on an RF circuit receiving signal; secondly, sending the FFT media data into a deep neural network; finally, the data (MedSleBits, medSplBits and RotaPosBits) processed by the deep neural network are combined. The specific steps in the step 2 are summarized as follows:
step 2.1, the received signal of the RF circuit is processed by ADC, S/P, CP removal and FFT.
Step 2.2, sending the media data after FFT into a deep neural network.
Step 2.3, data (MedSleBits, medSplBits and RotaPosBits) processed by the deep neural network are output.
In step 1.2, the media data may generally use data such as pictures, voice, or text as data for the MedSleBits and MedSplBits indexes. The deep neural network may be any architecture of deep network structure including one of a feed forward type network and a feedback type network, such as a convolutional network, a fully-connected network, a self-coded network, a recursive network, and the like. The deep neural network in the transmitting link is the optimal network after the combined training with the deep neural network in the receiving link.
In step 2.2, the deep neural network in the receiving link may be any deep network structure, including one of a feedforward type network and a feedback type network, such as a convolutional network, a fully-connected network, a self-coding network, a recursive network, and the like. The deep neural network in the receiving link is the optimal network after combined training with the deep neural network in the transmitting link, and the training is divided into three steps: 1. random bit sequence b= [ b ] 1 ,…,b B ]The indexed media data is sent to OFDM (IFFT, CP and P/S) to generate training data after being coded by a deep neural network in a transmission link; 2. a radio channel having training data generated through simulation, wherein radio fading channel simulation data having Rayleigh/Rician distribution can be used as reference [1 ]]Generating; 3. conventional OFDM in data receiving linkAfter the data is processed by the receiving mode (S/P, CP removal and FFT), the real part and the imaginary part are sent into a deep neural network, and the loss function of the training model is defined asWherein->Is an estimate of b. When training meets a certain preset condition, the training model is ended, and the parameters of the deep neural network in the transmitting link and the deep neural network in the receiving link are optimal, so that the deep neural network can be used for wireless network physical layer safety and high-spectrum efficiency communication based on the MIFC technology.
The invention has the advantages and beneficial effects that:
(1) the invention carries out feature coding based on index media data and the deep neural network, breaks through the concept of improving the frequency spectrum efficiency and the safety of the traditional physical layer by traditional modulation, and has the characteristics of simple design, high frequency spectrum efficiency and strong safety performance. (2) The method adopts the deep neural network to simultaneously carry out joint detection on MedSleBits, medSplBits and RotaPosBits, and has the characteristics of simple method, high detection efficiency and the like. (3) The method is very suitable for application scenes of low-computation-force sensing equipment such as the Internet of vehicles, the Internet of things of satellites, the Internet of things of ocean and the like to the safe transmission of big data.
Drawings
FIG. 1 is a schematic diagram of the design of the present invention; wherein fig. 1 (a) is a schematic diagram of a wireless network communication transmission link based on MIFC technology; fig. 1 (b) is a schematic diagram of a wireless network communication receiving link based on MIFC technology.
Fig. 2 is a schematic diagram of a wireless network transmission link MIFC.
Fig. 3 is a schematic diagram of detecting MIFC signals in a receiving link of a wireless network.
Detailed Description
Example 1:
the MIFC-based wireless network communication method uses MIFC technology, not only improves the frequency spectrum efficiency and information security of wireless network communication, but also reduces the detection difficulty of MIFC signals, and the steps and details of the steps are as follows:
step 1, designing a wireless network communication transmitting link based on MIFC technology;
step 2, designing a wireless network communication receiving link based on MIFC technology.
In step 1, since the wireless network communication system adopts the MIFC communication technology, the present invention takes pictures as media data, and takes 32 OFDM subblocks and 128 subcarriers as examples, and the following processing will be performed in the data transmission link:
step 1.1, the source information bit b= [ b ] 1 ,…,b B ]32 groups were grouped according to 3-bit MedSleBits, 2-bit MedSplBits, and 2-bit RotaPosBits and fed into the MIFC module.
Step 1.2, first in a picture set (at least 32 x 2 3 Sheet) indexes any picture according to 32 x 3 bits of MedSlebites every 3 bits (one of eight states of 000, 001, …, 111), namely 32 pictures are indexed by 32 OFDM subblocks, and each selected picture is subjected to 2 simultaneously 2 Dividing; secondly, searching any 1 cutting picture corresponding to 32 x 2 bits of MedSplBits (one of four states of 00, 01, 10 and 11), namely 32 OFDM subBlock indexes 32 cutting pictures; again using 32 x 2 bits RotaPosBits to rotate the selected cut pictures (0 °, 90 °,180 °,270 °) according to each 2 bits (00, 01, 10, 11 states), namely 32 OFDM blocks correspond to 32 rotated cut pictures; finally, sending the 32 rotary cutting pictures into a deep neural network, and generating data after the trained neural network codes
y=[x (1) ,x (2) ,…,x (32) ] (1)
Wherein the method comprises the steps of
x (i) =R2C(f(p;Θ DNN )),i=1,...,32 (2)
Wherein R2C (. Cndot.) represents the real-to-imaginary function, f (p; Θ) DNN ) Representing the picture p according to the trained network parameters Θ DNN Feature encoding is performed.
Step 1.3, the above-mentioned characteristic coded data are fed into OFDM (IFFT, CP and P/S), then fed into RF circuit to send signal according to traditional scheme, i.e. DAC.
In the step 2, the trained deep neural network is adopted to detect MedSleBits, medSplBits and RotaPosBits signals in a wireless network communication system based on MIFC technology, and the following processing is performed on a data receiving link:
step 2.1, the RF circuit receives the signal to carry out ADC, and then the signal is sent to OFDM receiving mode (S/P, CP removal and FFT) processing.
Step 2.2, training the deep neural network to perform data matchingMedSleBits, medSplBits and RotaPosBits detection in (h represents fading channel, w represents white noise), i.e
Wherein C2R (·) represents the real part of the imaginary part transfer function,representing the received data according to the trained network parameters theta DetDNN And performing feature decoding detection. Performing downlink joint training on the deep neural network in the receiving link and the deep neural network in the transmitting link: first step, a random bit sequence b= [ b ] 1 ,…,b B ]The indexed picture data is sent to OFDM (IFFT, CP and P/S) to generate training data after being encoded by a deep neural network in a transmission link; second, the training data is generated and passed through a simulated wireless channel, wherein the simulated wireless fading channel data with Rayleigh/Rician distribution can be obtained by using document [1 ]]Generating; third, after the data receiving link processes the data according to the conventional OFDM receiving mode (S/P, CP removal, FFT), the data is sent into the deep neural network by dividing the real part and the imaginary part, and the loss function of the training model is defined as->Wherein->Is an estimate of b. When the training meets a certain preset condition, the training model is ended, and the parameters (Θ) of the deep neural network in the transmitting link and the deep neural network in the receiving link are calculated DNN And theta (theta) DetDNN ) And the optimal effect is achieved.
Step 2.3, data processed by the deep neural network is output (MedSleBits, medSplBits and RotaPosBits).
Reference is made to:
[1]Junfeng Wang,Xiurong Ma,Jianfu Teng,Yue Cui,“Efficient and accurate simulator for Rayleigh and Rician fading”,Transactions of Tianjin University,vol.18, no.4,pp.243-247,2012。
Claims (4)
1. a method for physical layer security and efficient communication in a wireless network, the method comprising:
step 1, a wireless network communication transmitting link design scheme based on a media index feature coding MIFC technology is adopted;
step 2, wireless network communication receiving link design scheme based on MIFC technology of media index feature coding;
the design in step 1 includes:
step 1.1, dividing information bits into media sequence number bits MedSleBits, cutting media sequence number bits MedSplBits and rotation position bits RotaPosBits;
step 1.2, first index media data in a predefined set of media data with MedSlebits, while subjecting the selected media data to 2 according to MedSplbits length M M Cutting for the second time; secondly, the cut media data is indexed by using MedSplBits; then using RotaPosBits to rotate the selected media data of MedSplBits; finally, the mapped rotating media data is placed into a deep neural network to perform feature coding;
step 1.3, the processed feature code data is subjected to IFFT, CP and P/S, DAC and then sent to an RF circuit for transmission.
2. The method for physical layer security and spectral efficiency communication in a wireless network of claim 1, wherein said designing in step 2 comprises:
step 2.1, performing ADC, S/P, CP removal and FFT processing on the RF circuit receiving signal;
step 2.2, sending the FFT media data into a deep neural network;
step 2.3, output the data MedSleBits, medSplBits processed by the deep neural network and the RotaPosBits.
3. The method of claim 1, wherein in step 1.2, the media data uses picture, voice or text data as data indexed by MedSleBits and MedSplBits; the deep neural network is a deep network structure with any architecture, and comprises one of a feedforward network and a feedback network; the deep neural network in the transmitting link is the optimal network after the combined training with the deep neural network in the receiving link.
4. The method for physical layer security and spectral efficiency communication in a wireless network of claim 2, wherein in step 2.2, the deep neural network in the receiving link is a deep network structure of any architecture, including one of a feed-forward network and a feedback network; the deep neural network in the receiving link is the optimal network after combined training with the deep neural network in the transmitting link, and the training is divided into three steps: 1. random bit sequence b= [ b ] 1 ,…,b B ]The indexed media data is sent to an OFDM system to generate training data after being coded by a deep neural network in a transmission link; 2. allowing the generated training data to pass through the simulated wireless channel; 3. after the data receiving link processes the data according to the conventional OFDM system receiving mode, the real part and the imaginary part are sent into the deep neural network, and the loss function of the training model is defined asWherein->An estimated value for b; when training meets a certain preset condition, the training model is ended, and the parameters of the deep neural network in the transmitting link and the deep neural network in the receiving link are optimized at the moment, so that the method is used for safe and high-spectrum-efficiency communication of a wireless network physical layer based on the MIFC technology;
in the first step, the OFDM system is used for encoding data and processing the data through IFFT, CP adding and P/S; in the third step, the OFDM system receiving mode is used for receiving data and processing the data through S/P, CP removal and FFT.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210518460.8A CN114978840B (en) | 2022-05-13 | 2022-05-13 | Physical layer safety and high-spectrum efficiency communication method in wireless network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210518460.8A CN114978840B (en) | 2022-05-13 | 2022-05-13 | Physical layer safety and high-spectrum efficiency communication method in wireless network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114978840A CN114978840A (en) | 2022-08-30 |
CN114978840B true CN114978840B (en) | 2023-08-18 |
Family
ID=82983029
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210518460.8A Active CN114978840B (en) | 2022-05-13 | 2022-05-13 | Physical layer safety and high-spectrum efficiency communication method in wireless network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114978840B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103065661A (en) * | 2012-09-20 | 2013-04-24 | 中华电信股份有限公司 | Signal detection method for recording medium |
CN109412993A (en) * | 2018-11-27 | 2019-03-01 | 天津理工大学 | A kind of having based on deep learning inhibits the full duplex cognition water sound communication signal detection method of self-interference |
CN112560858A (en) * | 2020-10-13 | 2021-03-26 | 国家计算机网络与信息安全管理中心 | Character and picture detection and rapid matching method combining lightweight network and personalized feature extraction |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020092391A1 (en) * | 2018-10-29 | 2020-05-07 | Board Of Regents, The University Of Texas System | Low resolution ofdm receivers via deep learning |
-
2022
- 2022-05-13 CN CN202210518460.8A patent/CN114978840B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103065661A (en) * | 2012-09-20 | 2013-04-24 | 中华电信股份有限公司 | Signal detection method for recording medium |
CN109412993A (en) * | 2018-11-27 | 2019-03-01 | 天津理工大学 | A kind of having based on deep learning inhibits the full duplex cognition water sound communication signal detection method of self-interference |
CN112560858A (en) * | 2020-10-13 | 2021-03-26 | 国家计算机网络与信息安全管理中心 | Character and picture detection and rapid matching method combining lightweight network and personalized feature extraction |
Non-Patent Citations (1)
Title |
---|
基于卷积神经网络和哈希编码的图像检索方法;龚震霆;陈光喜;任夏荔;曹建收;;智能系统学报(第03期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114978840A (en) | 2022-08-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109412993B (en) | Full-duplex cognitive underwater acoustic communication signal detection method capable of inhibiting self-interference based on deep learning | |
Baeza et al. | A noncoherent multiuser large-scale SIMO system relying on M-ary DPSK and BICM-ID | |
CN106357311A (en) | Detection method of MIMO-OFDM (multiple-input multiple-output-orthogonal frequency division multiplexing) system based on SIM (subcarrier index modulation) | |
CN110324086B (en) | Double-space modulation method for wireless optical communication | |
CN110336614B (en) | Multilayer space pulse modulation method suitable for wireless optical communication | |
CN110602017B (en) | Non-orthogonal multiple access decoding method | |
CN110113288A (en) | A kind of design and demodulation method of the ofdm demodulator based on machine learning | |
CN113381828B (en) | Sparse code multiple access random channel modeling method based on condition generation countermeasure network | |
Wang et al. | A deep learning-based intelligent receiver for improving the reliability of the MIMO wireless communication system | |
CN112215335B (en) | System detection method based on deep learning | |
CN109728824A (en) | A kind of LDPC code iterative decoding method based on deep learning | |
CN1874210A (en) | Method for transmitting and receiving quasi-orthogonal time space group code, transmitter and receiver, and communication system | |
CN102355440A (en) | Underwater acoustic communication method based on very minimum chirp keying modulation | |
CN105656823A (en) | Underwater communication Turbo receiving system and underwater communication Turbo receiving method based on minimum bit error rate criterion | |
CN116074414A (en) | Wireless communication physical layer structure based on deep learning | |
CN114978840B (en) | Physical layer safety and high-spectrum efficiency communication method in wireless network | |
CN110677182A (en) | Communication method based on uplink layered space-time structure SCMA codebook | |
CN112398535B (en) | Method for improving transmission capacity of non-orthogonal multiple access visible light communication based on probability shaping | |
CN110365414A (en) | A kind of enhanced smooth modulating method being suitable for lognormal Turbulence Channels | |
CN110381003B (en) | Multi-user signal detection method aiming at peak-to-average ratio suppression in SCMA-OFDM system | |
CN109167748B (en) | Partial maximum likelihood detection method based on energy sorting | |
CN112073156B (en) | High-dimensional non-orthogonal transmission method | |
CN115189742A (en) | Differential coding assisted machine learning channel state information feedback method and device | |
Zhou et al. | Feasibility analysis of tactical radio station communication behaviors cognition | |
Wang et al. | Dual-mode index modulation aided 3D-OFDM |
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: 20220830 Assignee: TIANJIN KEYVIA ELECTRIC Co.,Ltd. Assignor: TIANJIN University OF TECHNOLOGY Contract record no.: X2024980000176 Denomination of invention: A Physical Layer Security and High Spectral Efficiency Communication Method in Wireless Networks Granted publication date: 20230818 License type: Common License Record date: 20240104 |
|
OL01 | Intention to license declared |