CN113518049A - Modulation identification method based on fractional low-order polar coordinate and deep learning - Google Patents
Modulation identification method based on fractional low-order polar coordinate and deep learning Download PDFInfo
- Publication number
- CN113518049A CN113518049A CN202110394895.1A CN202110394895A CN113518049A CN 113518049 A CN113518049 A CN 113518049A CN 202110394895 A CN202110394895 A CN 202110394895A CN 113518049 A CN113518049 A CN 113518049A
- Authority
- CN
- China
- Prior art keywords
- deep learning
- order
- fractional low
- signal
- fractional
- 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.)
- Granted
Links
- 238000013135 deep learning Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000004519 manufacturing process Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 8
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000005094 computer simulation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/0012—Modulated-carrier systems arrangements for identifying the type of modulation
-
- 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
Abstract
A modulation identification method based on fractional low-order polar coordinates and deep learning comprises the following steps: collecting signals and performing fractional low-order processing on the signals; calculating the characteristics of fractional low-order polar coordinates and manufacturing a training set and a test set; constructing and training a lightweight deep learning network; and testing the deep learning network and carrying out signal modulation identification. The method provided by the invention covers a wide range of signal types, can obviously improve the identification accuracy of the signal modulation mode under the condition of pulse noise interference, and meanwhile, the light deep learning network can obviously reduce the calculation cost in the training and using processes.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to a modulation identification method based on fractional low-order polar coordinates and deep learning. The method takes the fractional low-order polar coordinate as the characteristic, takes the deep learning network as the classifier, and efficiently and accurately realizes the modulation mode identification of various signals under the condition of pulse noise interference.
Background
As an intermediate link between signal reception and signal demodulation, signal modulation scheme identification is an indispensable important step. With the development of wireless communication technology, factors such as the type of signal, transmission mode, transmission environment, etc. are becoming more and more diverse and complex. As an important research topic in the military and civil fields, signal modulation scheme identification is increasingly gaining prominence in tasks such as communication reconnaissance, electronic interference, electronic countermeasure, abnormal signal identification, and the like. This requires researchers to develop more efficient, accurate, and widely applicable methods for signal modulation identification.
In the past, the traditional signal modulation identification method based on the characteristics generally selects different types of characteristics in a manual mode. Many technicians determine the type of signal modulation method based on their own experience by observing information such as the spectrum of the signal. This subjective factor is too much affected and labor and time costs are high, and new methods are urgently needed to fill these defects.
Since Hinton et al in the early century proposed the deep neural network algorithm, many excellent networks and algorithms such as CNN, AlexNet, google net, VGGNet, ResNet, etc. have been introduced in the field of deep learning, and they are widely used in the fields of computer vision, image processing, etc. In the prior art, as represented by a ResNet (Residual Network), the accuracy and timeliness of a deep learning Network for executing a classification and identification task are both greatly superior to those of a traditional manual-based discrimination method. In addition, by means of the networks, the defect that the traditional method excessively depends on manual experience and subjective judgment in the task of signal modulation identification can be greatly reduced. However, although many methods for signal modulation identification based on deep learning networks have been developed, the current methods and technologies have not been able to simultaneously solve two main problems often involved in such methods, namely: non-gaussian noise conditions and a lightweight deep learning network.
Disclosure of Invention
In order to solve the problems of low accuracy, few types of identification signals, high calculation cost, poor timeliness and the like of the conventional signal modulation identification method under the condition that signals are interfered by impulse noise, the invention provides a modulation identification method based on fractional low-order polar coordinates and deep learning. The invention firstly provides a concept of fractional low-order polar coordinates capable of suppressing impulse noise, which is typical non-Gaussian noise. Then a lightweight deep learning network with low calculation cost is constructed, and finally a modulation identification method based on fraction low-order polar coordinates and deep learning is provided. From the perspective of pattern recognition, the fractional low-order polar coordinate is a feature and serves as the input of a network, and the lightweight deep learning network is a classifier and realizes classification recognition of various signals. Experiments prove that the method provided by the invention can obviously improve the accuracy of signal identification interfered by impulse noise, and meanwhile, the light deep learning network can obviously reduce the calculation cost in the training and using processes.
The scheme of the invention is as follows:
a modulation identification method based on fractional low-order polar coordinates and deep learning comprises the following steps:
a: collecting signals and performing fractional low-order processing on the signals;
b: calculating the characteristics of fractional low-order polar coordinates and manufacturing a training set and a test set;
c: constructing and training a lightweight deep learning network;
d: and testing the deep learning network and identifying a signal modulation mode.
Further, the step a comprises:
a1: collecting signals of different modulation modes interfered by pulse noise: collecting enough signals interfered by impulse noise from the nature through computer simulation or by utilizing a receiving device, and describing the non-Gaussian noise by Alpha stable distribution; the strength of the impulsive noise is measured by adopting a generalized signal-to-noise ratio, which is defined as the following formula:
GSNR＝10log10(Ps/Pn)
in the above formula, PsRepresenting the power of the signal, PnGeneralized power, P, representing noisenγ denotes the scale parameter of Alpha stable distribution;
a2: and (3) performing fractional low order processing on the acquired signals: and carrying out fractional low-order processing on the acquired signals by utilizing a fractional low-order mapping function, wherein a specific formula is as follows:
yFLO(n)＝(y(n))<p-1>
＝ρFLO(n)exp(jθFLO(n))
where n represents a discrete time variable corresponding to a sampling time, y (n) represents a sampled signal sequence, and yFLO(n) represents the signal sequence after fractional low order processing, pFLORepresenting the polar path of the signal, thetaFLOWhich represents the polar angle of the signal and,<·>representing a fractional low order operator, the fractional low order function satisfies the following relation:
z<p-1>＝|z|p-2z*,z∈￡
in the formula, z represents a complex number in a complex field, and the upper corner mark represents a conjugate operator.
Further, the step B includes:
b1: calculating the fractional low-order polar coordinate characteristics of the signals after fractional low-order processing: by polar angle theta of the signalFLOAs abscissa, the polar diameter ρ of the signalFLOAs a vertical coordinate, extracting fractional low-order polar coordinate features corresponding to the signals one by one according to the sampling time n;
b2: fully mixing the above characteristics, and forming a training set, a verification set and a test set by the mixed characteristics according to a certain proportion: the fractional low-order polar coordinate characteristics obtained in the step B1 are disturbed and fully mixed, and then m is taken as the basis1:m2:m3The proportions of (a) and (b) respectively constitute a training set, a verification set and a test set. M is1:m2:m3＝6:2:2。
5. The modulation identification method based on fractional low-order polar coordinate and deep learning of claim 3, wherein the step C comprises:
c1: constructing a lightweight deep learning network by adopting fewer convolution layers;
c2: training the training set obtained in the step B2 by taking the cross entropy as a loss function and RMSprop as a network optimizer in the training process, and setting the learning rate to be 0.01 to update the modulus parameters;
c3: the features in the verification set are used as the input of the deep learning network in step C1, and are verified.
Further, the step D includes:
d1: testing the features in the test set as the input of the deep learning network in C1;
d2: taking the fractional low-order polar coordinate characteristics of the signal with unknown modulation mode as the input of the deep learning network in the step C1, and obtaining the recognition results of different signal modulation modes after model training
Compared with the prior art, the invention has the beneficial technical effects that:
the method solves the problem that the accuracy of the existing modulation mode identification method is reduced under the typical non-Gaussian noise interference environment that the signal is subjected to the impulsive noise. Meanwhile, the invention relates to a plurality of signal modulation modes, solves the problems of high calculation cost, poor timeliness and the like commonly existing in a deep learning network, and realizes efficient and accurate identification of the plurality of signal modulation modes.
Drawings
Fig. 1 is a modulation identification method based on fractional low-order polar coordinates and deep learning according to the present invention.
Figure 2 is a graph of a fractional low order mapping function in accordance with the present invention. The 5 curves correspond to the fractional lower-order parameters p of 1.1, 1.3, 1.5, 1.7 and 1.9 respectively.
Fig. 3 is a fractional low order polar plot of signals in accordance with the present invention. For example, when the fractional low-order function parameter p is 1.2, 1.5, and 1.8, fractional low-order polar coordinate feature maps of 6 signal modulation schemes, such as 2PSK, 4PSK, 8PSK, 16QAM, 32QAM, and 64QAM, are listed.
Fig. 4 is a block diagram of a deep learning network according to the present invention.
Fig. 5 is a graph of recognition accuracy for different methods under different noise conditions in accordance with the present invention. Wherein, the values of the parameters p related to the fractional low-order polar coordinates are respectively 1.1, 1.3 and 1.5, and the original polar coordinates are adopted as the characteristics of the comparison group.
Detailed Description
To assist understanding, the following description of the embodiments of the present invention will be provided in detail with reference to the accompanying drawings.
A modulation identification method based on fractional low-order polar coordinate and deep learning is disclosed, a flow chart of main steps of which is shown in figure 1, and specifically comprises the following steps:
a: and collecting signals and performing fractional low-order processing on the signals.
The step A specifically comprises the following steps:
a1: and collecting enough signals of different modulation modes interfered by the pulse noise.
The classical non-gaussian noise is characterized by a computer simulation or by the reception device collecting a sufficient amount of signals disturbed by the impulsive noise from nature and by an Alpha stationary distribution. When the Alpha stable distribution characteristic index α <2, the second moment of the noise does not converge, so that the signal-to-noise ratio (SNR) cannot be used to measure the intensity of the noise, and therefore, the generalized signal-to-noise ratio (GSNR) is used to measure the intensity of the impulsive noise, which is defined as:
GSNR＝10log10(Ps/Pn)
in the above formula, PsRepresenting the power of the signal, PnGeneralized power, P, representing noisenγ denotes the scale parameter of Alpha stable distribution. The collected signal types comprise AM, FM, MSK, 2ASK, 2PSK, 4PSK, 8PSK, 16QAM, 32QAM and 64 QAM. The generalized signal-to-noise ratio coverage ranges from-5 dB to +15 dB.
A2: and performing fractional low-order processing on the acquired signals.
And carrying out fractional low-order processing on the acquired signals by utilizing a fractional low-order mapping function, wherein a specific formula is as follows:
yFLO(n)＝(y(n))<p-1>
＝ρFLO(n)exp(jθFLO(n))
where n represents a discrete time variable corresponding to a sampling time, y (n) represents a sampled signal sequence, and yFLO(n) represents a signal sequence processed by fractional low-order (FLO), ρFLORepresenting the polar path of the signal, thetaFLOWhich represents the polar angle of the signal and,<·>representing a fractional low order operator, the fractional low order function satisfies the following relation:
z<p-1>＝|z|p-2z*,z∈￡
in the formula, z represents a complex number in a complex field, and the upper corner mark represents a conjugate operator.
A graph of a fractional low-order mapping function to which the present invention relates is shown in fig. 2. The 5 curves correspond to parameters p of 1.1, 1.3, 1.5, 1.7 and 1.9, respectively.
B: and calculating the characteristics of fractional low-order polar coordinates and manufacturing a training set and a test set.
The step B specifically comprises the following steps:
b1: and calculating the fractional low-order polar coordinate characteristics of the signals subjected to fractional low-order processing.
By polar angle theta of the signalFLOAs abscissa, the polar diameter ρ of the signalFLOAnd as a vertical coordinate, extracting the fractional low-order polar coordinate characteristics corresponding to the signals one by one according to the sampling time n. The signal type of the feature, the generalized signal-to-noise ratio range, matches the signal collected in step a 1.
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.
The fractional low-order polar coordinate characteristics obtained in the step B1 are disturbed and fully mixed, and then m is taken as the basis1:m2:m3The proportions of (a) and (b) respectively constitute a training set, a verification set and a test set. Typically, the ratio is set to m1:m2:m3＝6:2:2。
The fractional low-order polar characteristic diagram of step B1 of the present invention is shown in fig. 3. Taking the values of the parameters p related to the fractional low-order mapping function equal to 1.2, 1.5 and 1.8 as examples, the fractional low-order polar coordinate feature diagrams of 6 signal modulation modes, namely 2PSK, 4PSK, 8PSK, 16QAM, 32QAM and 64QAM, are listed.
C: and constructing and training a lightweight deep learning network.
The step C specifically comprises the following steps:
c1: and constructing a lightweight deep learning network.
In order to reduce the calculation and time cost of training, a light deep learning network is constructed by adopting fewer convolution layers, so that the problem of overhigh calculation cost in the training process of the traditional deep learning network is solved.
C2: the deep learning network is trained using a training set.
The training set obtained in step B2 is used as input and trained. In the training process, cross entropy (cross entropy) is used as a loss function, RMSprop is used as a network optimizer, the learning rate is set to be 0.01, and updating of the modulus parameter is achieved.
C3: the deep learning network is validated using a validation set.
The features in the verification set are used as the input of the deep learning network in step C1, and are verified.
The structure diagram of the deep neural network according to the present invention is shown in fig. 4, and specific network structure parameter settings are labeled in fig. 4.
D: and testing the deep learning network and carrying out signal modulation identification.
The step D specifically comprises the following steps:
d1: the deep learning network is tested using a test set.
The features in the test set are tested as input to the deep learning network in C1.
D2: and carrying out signal modulation identification.
And D, taking the fractional low-order polar coordinate characteristics of the signal with the unknown modulation mode as the input of the deep learning network in the step C1, and obtaining the recognition results of different signal modulation modes after model training.
Table 1 shows the classification and identification results of 10 signals interfered by impulse noise, for example, the fractional low-order parameter p is 1.1 under the conditions that α is 1.5 and GSNR is 15 dB.
TABLE 1 identification of signal modulation
Fig. 5 shows an average graph of the recognition accuracy of different signal modulation schemes under different noise conditions. The values of the parameters p related to the fractional low-order polar coordinate are respectively 1.1, 1.3 and 1.5, and the traditional original polar coordinate is adopted as the characteristic in the comparison method.
Claims (6)
1. A modulation identification method based on fractional low-order polar coordinates and deep learning is characterized by comprising the following steps:
a: collecting signals and performing fractional low-order processing on the signals;
b: calculating the characteristics of fractional low-order polar coordinates and manufacturing a training set and a test set;
c: constructing and training a lightweight deep learning network;
d: and testing the deep learning network and identifying a signal modulation mode.
2. The modulation identification method based on fractional low-order polar coordinate and deep learning of claim 1, wherein the step A comprises:
a1: collecting signals of different modulation modes interfered by pulse noise: collecting enough signals interfered by impulse noise from the nature through computer simulation or by utilizing a receiving device, and describing the non-Gaussian noise by Alpha stable distribution; the strength of the impulsive noise is measured by adopting a generalized signal-to-noise ratio, which is defined as the following formula:
GSNR＝10log10(Ps/Pn)
in the above formula, PsRepresenting the power of the signal, PnGeneralized power, P, representing noisenγ denotes the scale parameter of Alpha stable distribution;
a2: and (3) performing fractional low order processing on the acquired signals: and carrying out fractional low-order processing on the acquired signals by utilizing a fractional low-order mapping function, wherein a specific formula is as follows:
yFLO(n)＝(y(n))<p-1>
＝ρFLO(n)exp(jθFLO(n))
where n represents a discrete time variable corresponding to a sampling time, y (n) represents a sampled signal sequence, and yFLO(n) represents the signal sequence after fractional low order processing, pFLORepresenting the polar path of the signal, thetaFLOWhich represents the polar angle of the signal and,<·>representing a fractional low order operator, the fractional low order function satisfies the following relation:
wherein z represents a complex field
One complex number in (1), the upper corner indicates a conjugate operator.
3. The modulation identification method based on fractional low-order polar coordinate and deep learning of claim 1, wherein the step B comprises:
b1: calculating the fractional low-order polar coordinate characteristics of the signals after fractional low-order processing: by polar angle theta of the signalFLOAs abscissa, the polar diameter ρ of the signalFLOAs a vertical coordinate, extracting fractional low-order polar coordinate features corresponding to the signals one by one according to the sampling time n;
b2: fully mixing the above characteristics, and forming training set and test by the mixed characteristics according to a certain proportionCertificate collection and test collection: the fractional low-order polar coordinate characteristics obtained in the step B1 are disturbed and fully mixed, and then m is taken as the basis1:m2:m3The proportions of (a) and (b) respectively constitute a training set, a verification set and a test set.
4. The modulation identification method based on fractional low-order polar coordinate and deep learning of claim 3, wherein m is the same as m1:m2:m3＝6:2:2。
5. The modulation identification method based on fractional low-order polar coordinate and deep learning of claim 3, wherein the step C comprises:
c1: constructing a lightweight deep learning network by adopting fewer convolution layers;
c2: training the training set obtained in the step B2 by taking the cross entropy as a loss function and RMSprop as a network optimizer in the training process, and setting the learning rate to be 0.01 to update the modulus parameters;
c3: the features in the verification set are used as the input of the deep learning network in step C1, and are verified.
6. The modulation identification method based on fractional low-order polar coordinate and deep learning of claim 5, wherein the step D comprises:
d1: testing the features in the test set as the input of the deep learning network in C1;
d2: and D, taking the fractional low-order polar coordinate characteristics of the signal with the unknown modulation mode as the input of the deep learning network in the step C1, and obtaining the recognition results of different signal modulation modes after model training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110394895.1A CN113518049B (en) | 2021-04-13 | 2021-04-13 | Modulation identification method based on fractional low-order polar coordinates and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110394895.1A CN113518049B (en) | 2021-04-13 | 2021-04-13 | Modulation identification method based on fractional low-order polar coordinates and deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113518049A true CN113518049A (en) | 2021-10-19 |
| CN113518049B CN113518049B (en) | 2024-04-26 |
Family
ID=78061491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110394895.1A Active CN113518049B (en) | 2021-04-13 | 2021-04-13 | Modulation identification method based on fractional low-order polar coordinates and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113518049B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205000A (en) * | 2021-04-07 | 2021-08-03 | 江苏师范大学 | Modulation mode identification method based on Cauchy Score polar coordinate diagram |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19814770C1 (en) * | 1998-04-02 | 1999-09-23 | Rohde & Schwarz | Process for the automatic, clock-free detection of signal modulation types |
| DE102010013637A1 (en) * | 2010-04-01 | 2011-10-06 | Rohde & Schwarz Gmbh & Co. Kg | Method for classifying signals according to the type of modulation used |
| CN103326975A (en) * | 2013-07-15 | 2013-09-25 | 西安电子科技大学 | Digital modulation signal identification method under Alpha stable distribution noise |
| CN104052702A (en) * | 2014-06-20 | 2014-09-17 | 西安电子科技大学 | Method for identifying digital modulation signals in presence of complicated noise |
| CN105785324A (en) * | 2016-03-11 | 2016-07-20 | 西安电子科技大学 | MGCSTFT-based chirp signal parameter estimation method |
| CN107135176A (en) * | 2017-07-06 | 2017-09-05 | 电子科技大学 | Figure field communication signal modulate method based on fractional lower-order Cyclic Spectrum |
| CN108282426A (en) * | 2017-12-08 | 2018-07-13 | 西安电子科技大学 | Radio signal recognition recognition methods based on lightweight depth network |
| CN109309640A (en) * | 2018-09-08 | 2019-02-05 | 苏州大学 | Fanaticism format identification method based on machine learning |
| CN110163282A (en) * | 2019-05-22 | 2019-08-23 | 西安电子科技大学 | Modulation Mode Recognition method based on deep learning |
| CN110417694A (en) * | 2019-06-07 | 2019-11-05 | 吉林大学 | A kind of modulation mode of communication signal recognition methods |
| KR102073935B1 (en) * | 2018-12-24 | 2020-02-05 | 충남대학교산학협력단 | Modulation recognition for radil signal |
| CN111259798A (en) * | 2020-01-16 | 2020-06-09 | 西安电子科技大学 | Modulation signal identification method based on deep 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 |
-
2021
- 2021-04-13 CN CN202110394895.1A patent/CN113518049B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19814770C1 (en) * | 1998-04-02 | 1999-09-23 | Rohde & Schwarz | Process for the automatic, clock-free detection of signal modulation types |
| DE102010013637A1 (en) * | 2010-04-01 | 2011-10-06 | Rohde & Schwarz Gmbh & Co. Kg | Method for classifying signals according to the type of modulation used |
| CN103326975A (en) * | 2013-07-15 | 2013-09-25 | 西安电子科技大学 | Digital modulation signal identification method under Alpha stable distribution noise |
| CN104052702A (en) * | 2014-06-20 | 2014-09-17 | 西安电子科技大学 | Method for identifying digital modulation signals in presence of complicated noise |
| CN105785324A (en) * | 2016-03-11 | 2016-07-20 | 西安电子科技大学 | MGCSTFT-based chirp signal parameter estimation method |
| CN107135176A (en) * | 2017-07-06 | 2017-09-05 | 电子科技大学 | Figure field communication signal modulate method based on fractional lower-order Cyclic Spectrum |
| CN108282426A (en) * | 2017-12-08 | 2018-07-13 | 西安电子科技大学 | Radio signal recognition recognition methods based on lightweight depth network |
| CN109309640A (en) * | 2018-09-08 | 2019-02-05 | 苏州大学 | Fanaticism format identification method based on machine learning |
| KR102073935B1 (en) * | 2018-12-24 | 2020-02-05 | 충남대학교산학협력단 | Modulation recognition for radil signal |
| 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 |
| CN110163282A (en) * | 2019-05-22 | 2019-08-23 | 西安电子科技大学 | Modulation Mode Recognition method based on deep learning |
| CN110417694A (en) * | 2019-06-07 | 2019-11-05 | 吉林大学 | A kind of modulation mode of communication signal recognition methods |
| CN111259798A (en) * | 2020-01-16 | 2020-06-09 | 西安电子科技大学 | Modulation signal identification method based on deep learning |
Non-Patent Citations (14)
| Title |
|---|
| CHIEH-FANG TENG ET AL.: "polar feature based deep architectures for automatic modulation classification considering channel fading", 《2018 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP)》 * |
| KAI MA ET AL.: "CNN-based automatic modulation recognition of wireless signal", 《2020 IEEE 3RD INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND COMPUTER AIDED EDUCATION (ICISCAE)》 * |
| PEJMAN GHASEMZADEH ET AL.: "A Novel Deep Learning and Polar Transformation Framework for an Adaptive Automatic Modulation Classification", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》, pages 13245 - 13255 * |
| XIAO YAN ET AL.: "robust modulation classification over α-stable noise using graph-based fractional lower-order cyclic spectrum analysis", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》 * |
| XIAO YAN ET AL.: "Robust Modulation Classification Over α-Stable Noise Using Graph-Based Fractional Lower-Order Cyclic Spectrum Analysis", 《IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY》, pages 2837 - 2844 * |
| XIAODI TIAN ET AL.: "modulation pattern recognition of communication signals based on fractional Low-Order Choi-Williams distribution and convolutional neural network in impulsive noise environment", 《2019 IEEE 19TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY （ICCT）》 * |
| YUANYUAN MA ET AL.: "modulation format identification based on constellation diagrams in adaptive optical OFDM systems", 《OPTICS COMMUNICATIONS》 * |
| 刘明骞;李兵兵;石亚云;: "Alpha稳定分布噪声下数字调制识别新方法", 西安电子科技大学学报, no. 06 * |
| 刘明骞等: "认知无线电中非高斯噪声下数字调制信号识别方法", 《通信学报》 * |
| 孙汝峰;刘顺兰;: "Alpha稳定分布噪声下数字调制信号识别", 无线通信技术, no. 01 * |
| 李书恋;郑美芳;杨林森;: "基于卷积神经网络的调制信号识别", 科技经济导刊, no. 27 * |
| 袁兰杰等: "分数阶傅里叶变换(FRFT)用于调制方式识别", 《 电子信息对抗技术》, 15 July 2011 (2011-07-15) * |
| 赵春晖;杨伟超;杜宇;: "采用分数低阶循环谱相干系数的调制识别", 应用科学学报, no. 06 * |
| 钟骥等: "常用数字通信信号调制方式分类的一种新方法", 《电子技术应用》, 31 December 2008 (2008-12-31) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205000A (en) * | 2021-04-07 | 2021-08-03 | 江苏师范大学 | Modulation mode identification method based on Cauchy Score polar coordinate diagram |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113518049B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Data-driven deep learning for automatic modulation recognition in cognitive radios | |
| CN110163282B (en) | Modulation mode identification method based on deep learning | |
| CN110855591B (en) | QAM and PSK signal intra-class modulation classification method based on convolutional neural network structure | |
| CN107979554B (en) | Radio signal Modulation Identification method based on multiple dimensioned convolutional neural networks | |
| CN109274621B (en) | Communication protocol signal identification method based on depth residual error network | |
| CN112702294B (en) | Modulation recognition method for multi-level feature extraction based on deep learning | |
| CN113114599B (en) | Modulation identification method based on lightweight neural network | |
| CN112733811B (en) | Method for identifying underwater sound signal modulation modes based on improved dense neural network | |
| CN110071885A (en) | A kind of deep learning method of discrimination of PSK digital signal subclass Modulation Identification | |
| CN101764786A (en) | MQAM signal recognition method based on clustering algorithm | |
| CN111585922A (en) | Modulation mode identification method based on convolutional neural network | |
| CN113037663B (en) | Improved code element rate estimation method suitable for non-constant envelope signal | |
| CN113518049B (en) | Modulation identification method based on fractional low-order polar coordinates and deep learning | |
| CN112613443A (en) | Robustness communication radiation source intelligent identification method based on deep learning | |
| CN110751201B (en) | SAR equipment task failure cause reasoning method based on textural feature transformation | |
| CN114422310B (en) | Digital quadrature modulation signal identification method based on joint distribution matrix and multi-input neural network | |
| CN115409056A (en) | Automatic modulation identification method for large dynamic signal-to-noise ratio | |
| CN115913849A (en) | Electromagnetic signal identification method based on one-dimensional complex value residual error network | |
| CN113269023B (en) | Modulation identification method based on fractional low-order constellation diagram and deep learning | |
| CN113343796B (en) | Knowledge distillation-based radar signal modulation mode identification method | |
| Liu et al. | An effective radio frequency signal classification method based on multi-task learning mechanism | |
| CN116359851A (en) | Radar active interference detection and identification method and device based on converged network | |
| CN113361569A (en) | Electromagnetic signal modulation type identification model construction method based on time-frequency fusion information | |
| CN113283490A (en) | Channel state information deep learning positioning method based on front-end fusion | |
| Nerandžić et al. | Impact of AWGN estimation on classification performance of AMC algorithms based on higher order cumulants |
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 |