CN113205000A - Modulation mode identification method based on Cauchy Score polar coordinate diagram - Google Patents
Modulation mode identification method based on Cauchy Score polar coordinate diagram Download PDFInfo
- Publication number
- CN113205000A CN113205000A CN202110375837.4A CN202110375837A CN113205000A CN 113205000 A CN113205000 A CN 113205000A CN 202110375837 A CN202110375837 A CN 202110375837A CN 113205000 A CN113205000 A CN 113205000A
- Authority
- CN
- China
- Prior art keywords
- score
- cauchy
- radio signal
- neural network
- convolutional neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000010586 diagram Methods 0.000 title description 12
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000000694 effects Effects 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 4
- 238000004519 manufacturing process Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 8
- 238000010200 validation analysis Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 230000009466 transformation Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000002474 experimental method Methods 0.000 abstract 1
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Digital Transmission Methods That Use Modulated Carrier Waves (AREA)
Abstract
A modulation mode identification method based on a Cauchy Score polar coordinate graph comprises the following steps: acquiring a radio signal and carrying out Cauchy Score processing on the radio signal; calculating a Cauchy Score polar coordinate graph and manufacturing a training set and a testing set; designing and training a lightweight convolutional neural network; and testing the convolutional neural network and identifying the modulation mode of the radio signal. Experiments prove that the algorithm has a good effect on solving the problem of modulation mode identification under the condition of impulsive noise, and in addition, the lightweight network used in the method has lower calculation complexity, which has important significance on the practical application of the method.
Description
Technical Field
The invention belongs to the technical field of image identification and communication, relates to modulation mode identification of radio signals, and particularly relates to a modulation mode identification method based on a Cauchy Score polar coordinate graph.
Background
Modulation scheme identification is an important step between radio signal detection and demodulation, and the task thereof is to judge the modulation scheme of a radio signal by information already grasped without prior knowledge or insufficient prior knowledge, for example, in uncooperative communication. The technology is widely applied to the fields of cognitive radio, spectrum management, electronic countermeasure and the like. The existing modulation mode identification methods are mainly divided into two types, namely maximum likelihood estimation and signal feature based. The method based on maximum likelihood estimation, which considers the modulation mode identification as a hypothesis testing problem and compares the likelihood function of the signal with a threshold value, can generally obtain a better solution, but has higher computational complexity. The method based on the signal features firstly needs to extract various features of the signals and then sends the features to the classifier for classification, and the method may not obtain an optimal solution, but is easy to practice and relatively low in calculation amount.
In recent years, with the rapid development of artificial intelligence, more and more researchers try to apply the techniques of machine learning and deep learning to the field of signal processing, and a plurality of modulation mode identification methods based on different characteristics and various neural networks are proposed and achieve good effects. However, the existing modulation mode identification method is usually based on a gaussian noise environment, and the method is easy to have performance degradation under the condition of non-gaussian noise, such as impulse noise. Aiming at the problems, the invention provides a modulation mode identification method based on a Cauchy Score polar coordinate graph, and provides a feasible method for solving the problem of modulation mode identification under the condition of impulsive noise.
Disclosure of Invention
The invention provides a modulation mode identification method based on a Cauchy Score polar coordinate graph.
The technical scheme adopted by the invention is as follows:
a: radio signals are acquired and subjected to cauchy Score processing.
A1: a radio signal is acquired.
A2: the radio signal is subjected to cauchy Score processing.
B: and calculating the characteristics of the Cauchy Score polar coordinate graph and manufacturing a training set and a testing set.
B1: and calculating the Cauchy Score polar coordinate graph characteristic of the radio signal.
B2: and fully mixing the characteristics, and forming a training set, a verification set and a test set by the mixed characteristics according to a certain proportion.
C: and designing and training a lightweight convolutional neural network.
C1: and designing a lightweight convolutional neural network.
C2: the convolutional neural network is trained using a training set.
C3: the convolutional neural network is validated using a validation set.
D: and testing the convolutional neural network and identifying the modulation mode of the radio signal.
D1: the convolutional neural network is tested using a test set.
D2: and identifying a radio signal modulation mode.
The invention has the beneficial effects that:
the algorithm has a good effect on solving the problem of modulation mode identification under the condition of impulsive noise, and in addition, the lightweight network used in the method has lower calculation complexity, which has important significance on the practical application of the method.
Drawings
Fig. 1 is a general flowchart of a modulation scheme identification method based on a cauchy Score polar coordinate diagram according to the present invention.
Fig. 2 is a graph of the Score function according to the present invention. The curve corresponding to α ═ 1 is the curve of the cauchy Score function used in the present invention.
FIG. 3 is a polar plot of Cauchy Score according to the present invention. The modulated signals are exemplified by 2ASK, 4ASK, 8ASK, 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, and 64 QAM.
Fig. 4 is a structural diagram of a lightweight convolutional neural network according to the present invention.
Fig. 5 is a diagram of a confusion matrix according to the present invention. The modulated signals are exemplified by 2ASK, 4ASK, 8ASK, 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, 64QAM, 2FSK, and AM.
Fig. 6 is a graph of identification accuracy in accordance with the present invention.
Fig. 7 is a graph of recognition accuracy for various methods in accordance with the present invention. The comparison method adopts a traditional constellation diagram and a polar coordinate diagram as characteristics.
Detailed Description
For the convenience of understanding, the technical solutions in the implementation process of the present invention will be described in detail below with reference to the accompanying drawings of the present invention.
A modulation mode identification method based on a Cauchy Score polar coordinate diagram is shown in a general flow chart of the modulation mode identification method in figure 1, and mainly comprises the following steps:
a: radio signals are acquired and subjected to cauchy Score processing.
The step A specifically comprises the following steps:
a1: a radio signal is acquired. And generating a simulation radio signal through related software, adding impulse noise, or acquiring a real radio signal under the impulse noise condition through equipment such as a receiver. The radio signal model with the impulsive noise added is:
y(t)＝x(t)+v(t)
wherein, x (t) and y (t) are respectively transmitted and received complex signals in continuous time domain, and v (t) is impulse noise subject to Alpha stable distribution. The ratio of signal to Alpha stationary noise (GSNR), which is defined as:
in the formula, PsRepresents the power of the signal, and γ represents the dispersion coefficient of Alpha stationary distributed noise.
A2: the radio signal is subjected to cauchy Score processing. Discretizing and standardizing the acquired radio signals, and respectively carrying out nonlinear mapping on a real part and an imaginary part of the obtained complex sequence by using a Cauchy Score function. The concrete formula of the cauchy Score function is as follows:
ySC(n)＝ρ1(y(n))＝aSC(n)+jbSC(n)
in the formula, aSCAnd bSCRespectively the real and imaginary part, p, of the signalα(. cndot.) is a Score function, whose expression is as follows:
in the formula (f)α(x) Is a probability density function of Alpha stable distribution. When α is 1, the Alpha stability profile degrades to the Cauchy profile, which is f1(x)＝1/[π(1+x2)]And ρ1(x)＝(2x)/(1+x2)。
B: and calculating the characteristics of the Cauchy Score polar coordinate graph and manufacturing a training set and a testing set.
The step B specifically comprises the following steps:
b1: and calculating the Cauchy Score polar coordinate graph characteristic of the radio signal. Respectively taking the real part and the imaginary part after nonlinear mapping as an abscissa and an ordinate, obtaining an ordinal pair (rho, theta) by calculating a polar coordinate, respectively taking rho and theta as the abscissa and the ordinate of a rectangular coordinate system, and calculating the Korea polar coordinate graph characteristics corresponding to the radio signals one by one according to the sampling time n.
B2: the above features are fully mixed, and the mixed features are combined into a training set, a verification set and a test set according to a certain proportion, wherein the proportion is generally 6: 2: 2.
the plot of the Score function according to the present invention is shown in fig. 2. The curve corresponding to α ═ 1 is the curve of the cauchy Score function used in the present invention.
The polar plot of Cauchy Score according to the present invention is shown in FIG. 3. The modulated signals are exemplified by 2ASK, 4ASK, 8ASK, 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, and 64 QAM.
C: and designing and training a lightweight convolutional neural network.
The step C specifically comprises the following steps:
c1: and designing a lightweight convolutional neural network. Based on the ShuffleNet V2 network, the lightweight convolutional neural network is built by reducing the number of the convolutional layers and the number of the input and output channels.
Fig. 4 shows a structural diagram of a lightweight convolutional neural network according to the present invention.
C2: the convolutional neural network is trained using a training set. The convolutional neural network described by C1 is trained using a training set containing the cauchy Score polar plot and the corresponding labels as inputs. In the training process, batch normalization processing is carried out by using BatchNorm2d, nonlinear transformation is introduced by using a ReLU activation function, the sample fitting degree is evaluated by using a cross entropy loss function, the training process is optimized by using an RMSprop algorithm, and the learning rate is set to be 0.01.
C3: the convolutional neural network is validated using a validation set. And taking the verification set as the input of the convolutional neural network C1 to verify the classification effect.
D: and testing the convolutional neural network and identifying the modulation mode of the radio signal.
The step D specifically comprises the following steps:
d1: the convolutional neural network is tested using a test set. And selecting a network with higher training accuracy and verification accuracy for the test set, and testing the classification effect of the network.
D2: and identifying a radio signal modulation mode. And taking the Couchy Score polar coordinate graph characteristic of the radio signal with an unknown modulation mode as the input of the convolutional neural network C1 to obtain the prediction result of the radio signal modulation mode, and drawing a confusion matrix and an accuracy curve based on the result so as to measure the classification effect of the lightweight convolutional neural network on each modulation signal under the condition of impulsive noise.
The confusion matrix diagram according to the invention is shown in fig. 5. The modulation signal takes 2ASK, 4ASK, 8ASK, 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, 64QAM, 2FSK and AM as examples, the value of the Alpha stable distribution noise characteristic index is α ═ 1.2, the value range of the generalized signal-to-noise ratio is GSNR ∈ [ -5,15] dB, the real label represents the actual debugging mode of the signal, and the prediction label represents the predicted modulation mode of the signal.
The recognition accuracy graph according to the present invention is shown in fig. 6.
The recognition accuracy curves of the different methods involved in the present invention are shown in fig. 7. The comparison method adopts a traditional constellation diagram and a polar coordinate diagram as characteristics.
Claims (6)
1. A modulation identification method based on a Cauchy Score polar coordinate graph is characterized by comprising the following steps:
a: acquiring a radio signal and carrying out Cauchy Score processing on the radio signal;
a1: acquiring a radio signal;
a2: performing Cauchy Score processing on the radio signal;
b: calculating the characteristics of the Kexi Score polar coordinate graph and manufacturing a training set and a test set;
b1: calculating the polar coordinate graph characteristics of the Cauchy Score of the radio signal;
b2: fully mixing the characteristics, and forming a training set, a verification set and a test set by the mixed characteristics according to a certain proportion;
c: designing and training a lightweight convolutional neural network;
c1: designing a lightweight convolutional neural network;
c2: training the convolutional neural network by using a training set;
c3: validating the convolutional neural network using a validation set;
d: testing the convolutional neural network and identifying the modulation mode of the radio signal;
d1: testing the convolutional neural network using a test set;
d2: and identifying a radio signal modulation mode.
2. The modulation identification method based on the polar coordinate graph of cauchy Score as claimed in claim 1, wherein the step a of acquiring the radio signal and performing cauchy Score processing on the radio signal specifically comprises the steps of:
a1: acquiring a radio signal; generating a simulation radio signal through related software, adding impulse noise, or acquiring a real radio signal under the condition of the impulse noise through equipment such as a receiver;
a2: performing Cauchy Score processing on the radio signal; discretizing and standardizing the acquired radio signals, and respectively carrying out nonlinear mapping on a real part and an imaginary part of the obtained complex sequence by using a Cauchy Score function.
3. The modulation identification method based on the Cauchy Score polar coordinate graph according to claim 1, wherein B said calculating the Cauchy Score polar coordinate graph features and making the training set and the testing set specifically comprises:
b1: and calculating the Cauchy Score polar coordinate graph characteristic of the radio signal. Respectively taking the real part and the imaginary part after nonlinear mapping as an abscissa and an ordinate, obtaining an ordinal pair (rho, theta) by calculating the polar coordinates of the real part and the imaginary part, respectively taking the rho and the theta as the abscissa and the ordinate of a rectangular coordinate system, and calculating the Kouchi Score polar coordinate graph characteristics corresponding to the radio signals one by one according to the sampling time n;
b2: fully mixing the characteristics, and forming a training set, a verification set and a test set by the mixed characteristics according to a certain proportion; the proportion of training, validation and test sets is typically: 6: 2: 2.
4. the modulation identification method according to claim 1, wherein the modulation identification method based on Cauchy Score polar coordinate graph,
c, designing and training the lightweight convolutional neural network specifically comprises the following steps:
c1: designing a lightweight convolutional neural network; on the basis of a ShuffleNet V2 network, the lightweight convolutional neural network is built by reducing the number of the convolutional layers and the number of input and output channels;
c2: training the convolutional neural network by using a training set;
c3: the convolutional neural network is validated using a validation set. And taking the verification set as the input of the convolutional neural network C1 to verify the classification effect.
5. The modulation identification method according to claim 4, wherein the modulation identification method based on Cauchy Score polar coordinate graph,
the step comprising C2 includes:
the convolutional neural network described by C1 is trained using a training set containing the cauchy Score polar plot and the corresponding labels as inputs. In the training process, batch normalization processing is carried out by using BatchNorm2d, nonlinear transformation is introduced by using a ReLU activation function, the sample fitting degree is evaluated by using a cross entropy loss function, the training process is optimized by using an RMSprop algorithm, and the learning rate is set to be 0.01.
6. The modulation identification method based on the polar coordinate graph of cauchy Score as claimed in claim 1, wherein the step D of testing the convolutional neural network and identifying the radio signal modulation mode specifically comprises the steps of:
d1: testing the convolutional neural network using a test set; selecting a network with higher training accuracy and verification accuracy for the test set, and testing the classification effect of the network;
d2: identifying a radio signal modulation mode; and taking the Couchy Score polar coordinate graph characteristic of the radio signal with an unknown modulation mode as the input of the convolutional neural network C1 to obtain the prediction result of the radio signal modulation mode, and drawing a confusion matrix and an accuracy curve based on the result so as to measure the classification effect of the lightweight convolutional neural network on each modulation signal under the condition of impulsive noise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110375837.4A CN113205000A (en) | 2021-04-07 | 2021-04-07 | Modulation mode identification method based on Cauchy Score polar coordinate diagram |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110375837.4A CN113205000A (en) | 2021-04-07 | 2021-04-07 | Modulation mode identification method based on Cauchy Score polar coordinate diagram |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113205000A true CN113205000A (en) | 2021-08-03 |
Family
ID=77026384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110375837.4A Pending CN113205000A (en) | 2021-04-07 | 2021-04-07 | Modulation mode identification method based on Cauchy Score polar coordinate diagram |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113205000A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090290631A1 (en) * | 2008-05-20 | 2009-11-26 | Matsushita Electric Industrial Co., Ltd. | Methods and apparatus for reducing modulation signal bandwidth in polar modulation transmitters |
| CN105785324A (en) * | 2016-03-11 | 2016-07-20 | 西安电子科技大学 | MGCSTFT-based chirp signal parameter estimation method |
| CN107358156A (en) * | 2017-06-06 | 2017-11-17 | 华南理工大学 | The feature extracting method of Ultrasonic tissue characterization based on Hilbert-Huang transform |
| CN109309640A (en) * | 2018-09-08 | 2019-02-05 | 苏州大学 | Fanaticism format identification method based on machine learning |
| US20200327397A1 (en) * | 2019-04-12 | 2020-10-15 | Motorola Solutions, Inc. | Systems and methods for modulation classification of baseband signals using multiple data representations of signal samples |
| CN112346004A (en) * | 2020-11-20 | 2021-02-09 | 江苏师范大学 | Multi-signal classification algorithm based on generalized covariance of score function |
| CN113052081A (en) * | 2021-03-26 | 2021-06-29 | 江苏师范大学 | Modulation mode identification method based on Cauchy Score constellation diagram |
| CN113518049A (en) * | 2021-04-13 | 2021-10-19 | 江苏师范大学 | Modulation identification method based on fractional low-order polar coordinate and deep learning |
-
2021
- 2021-04-07 CN CN202110375837.4A patent/CN113205000A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090290631A1 (en) * | 2008-05-20 | 2009-11-26 | Matsushita Electric Industrial Co., Ltd. | Methods and apparatus for reducing modulation signal bandwidth in polar modulation transmitters |
| CN105785324A (en) * | 2016-03-11 | 2016-07-20 | 西安电子科技大学 | MGCSTFT-based chirp signal parameter estimation method |
| CN107358156A (en) * | 2017-06-06 | 2017-11-17 | 华南理工大学 | The feature extracting method of Ultrasonic tissue characterization based on Hilbert-Huang transform |
| CN109309640A (en) * | 2018-09-08 | 2019-02-05 | 苏州大学 | Fanaticism format identification method based on machine learning |
| US20200327397A1 (en) * | 2019-04-12 | 2020-10-15 | Motorola Solutions, Inc. | Systems and methods for modulation classification of baseband signals using multiple data representations of signal samples |
| CN112346004A (en) * | 2020-11-20 | 2021-02-09 | 江苏师范大学 | Multi-signal classification algorithm based on generalized covariance of score function |
| CN113052081A (en) * | 2021-03-26 | 2021-06-29 | 江苏师范大学 | Modulation mode identification method based on Cauchy Score constellation diagram |
| CN113518049A (en) * | 2021-04-13 | 2021-10-19 | 江苏师范大学 | Modulation identification method based on fractional low-order polar coordinate and deep learning |
Non-Patent Citations (4)
| Title |
|---|
| SHENGYANG LUAN等: "Automatic Modulation Classification Based on Cauchy-Score Constellation and Lightweight Network Under Impulsive Noise", 《IEEE WIRELESS COMMUNICATIONS LETTERS》, vol. 10, no. 11, 19 August 2021 (2021-08-19), pages 2509, XP011886946, DOI: 10.1109/LWC.2021.3105978 * |
| 杨伟超: "Alpha稳定分布噪声下通信信号调制识别研究", 《中国博士学位论文全文数据库 (信息科技辑)》, no. 2013, 15 January 2013 (2013-01-15), pages 136 - 18 * |
| 栾声扬: "有界非线性协方差与相关熵及在无线定位中的应用", 《中国博士学位论文全文数据库 (工程科技Ⅱ辑)》, no. 2018, 15 August 2018 (2018-08-15), pages 031 - 4 * |
| 金艳 等: "α稳定分布噪声中基于最优核时频分析的跳频信号参数估计", 《系统工程与电子技术》, vol. 37, no. 05, 31 May 2015 (2015-05-31), pages 985 - 991 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163282B (en) | Modulation mode identification method based on deep learning | |
| Bu et al. | Adversarial transfer learning for deep learning based automatic modulation classification | |
| Wang et al. | Data-driven deep learning for automatic modulation recognition in cognitive radios | |
| CN110855591A (en) | QAM and PSK signal intra-class modulation classification method based on convolutional neural network structure | |
| Yang et al. | Deep learning aided method for automatic modulation recognition | |
| CN112039820B (en) | Communication signal modulation and identification method for quantum image group mechanism evolution BP neural network | |
| CN112364729A (en) | Modulation identification method based on characteristic parameters and BP neural network | |
| CN110113288A (en) | A kind of design and demodulation method of the ofdm demodulator based on machine learning | |
| CN114567528B (en) | Communication signal modulation mode open set recognition method and system based on deep learning | |
| Zhang et al. | Open set recognition of communication signal modulation based on deep learning | |
| CN113378644B (en) | Method for defending signal modulation type recognition attack based on generation type countermeasure network | |
| CN114422311B (en) | Signal modulation recognition method and system combining deep neural network and expert priori features | |
| CN112749633B (en) | Separate and reconstructed individual radiation source identification method | |
| Sun et al. | Digital signal modulation recognition algorithm based on vggnet model | |
| Ma et al. | Modulation classification method based on deep learning under non-Gaussian noise | |
| CN115186712A (en) | Modulated signal identification method and system | |
| CN114980122A (en) | Small sample radio frequency fingerprint intelligent identification system and method | |
| He et al. | Deep learning-based automatic modulation recognition algorithm in non-cooperative communication systems | |
| CN115913850B (en) | Open set modulation identification method based on residual error network | |
| Cai et al. | The performance evaluation of big data-driven modulation classification in complex environment | |
| CN116680608A (en) | Signal modulation identification method based on complex graph convolutional neural network | |
| CN113052081B (en) | Modulation mode identification method based on Cauchy Score constellation diagram | |
| CN113205000A (en) | Modulation mode identification method based on Cauchy Score polar coordinate diagram | |
| CN113518049B (en) | Modulation identification method based on fractional low-order polar coordinates and deep learning | |
| CN108777604A (en) | A kind of wavelength division multiple access UWB multi-user detection method based on gauss hybrid models cluster |
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 |