CN102497343A - Combined modulation recognition method based on clustering and support vector machine - Google Patents
Combined modulation recognition method based on clustering and support vector machine Download PDFInfo
- Publication number
- CN102497343A CN102497343A CN2011103835521A CN201110383552A CN102497343A CN 102497343 A CN102497343 A CN 102497343A CN 2011103835521 A CN2011103835521 A CN 2011103835521A CN 201110383552 A CN201110383552 A CN 201110383552A CN 102497343 A CN102497343 A CN 102497343A
- Authority
- CN
- China
- Prior art keywords
- modulation
- clustering
- support vector
- vector machine
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 50
- 238000010586 diagram Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000005192 partition Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 230000010363 phase shift Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 17
- 239000011159 matrix material Substances 0.000 description 7
- 238000012567 pattern recognition method Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000007476 Maximum Likelihood Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- AHLBNYSZXLDEJQ-FWEHEUNISA-N orlistat Chemical compound CCCCCCCCCCC[C@H](OC(=O)[C@H](CC(C)C)NC=O)C[C@@H]1OC(=O)[C@H]1CCCCCC AHLBNYSZXLDEJQ-FWEHEUNISA-N 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Landscapes
- Digital Transmission Methods That Use Modulated Carrier Waves (AREA)
Abstract
The invention provides a combined modulation recognition method based on clustering and a support vector machine in order to overcome the shortcoming of low modulation recognition rate of a clustering algorithm with a low signal to noise ratio. According to the method, a characteristic parameter of a modulation signal is extracted by using the clustering algorithm according to a phase shift keying/quadrature amplitude modulation (PSK/QAM) mode based on a constellation diagram; and a modulation mode for a signal is recognized through the support vector machine, so that the modulation recognition rate of a system is increased. The method comprises the following steps of: aiming at the PSK/QAM mode based on the constellation diagram, reconstructing the constellation diagram of a receiving signal by using the clustering algorithm; and obtaining an effective function value, which can reflect an outstanding difference of modulation types under different clustering central numbers, as the characteristic parameter input into the support vector machine by constructing an effectiveness evaluation function. In order to overcome the shortcoming that two common algorithms of one to multiple and one to one have high calculation complexity when the support vector machine recognizes multiple types, the support vector machine is trained by adopting a hierarchical algorithm.
Description
Technical Field
The invention relates to an automatic modulation recognition implementation scheme based on clustering and a support vector machine, and belongs to the technical field of communication.
Background
With the development of communication technology, communication signals adopt different modulation methods in a wide frequency band, and the modulation parameters of the signals are different. The automatic modulation identification of the digital signal can determine the modulation mode of the signal under the conditions of various modulation signals and noise interference, and has important functions in the civil and military fields. As the system and modulation pattern of communication signals become more complex and diversified, modulation identification of communication signals becomes more important and urgent.
At present, research methods for automatically identifying modulation modes can be mainly divided into two categories: a maximum likelihood method based on hypothesis testing and a pattern recognition method based on feature extraction. Based on the maximum likelihood method of hypothesis test, the likelihood function of the signal is processed, and the obtained likelihood ratio is compared with a threshold value, so that the modulation recognition function is completed. The pattern recognition method based on feature extraction generally comprises two subsystems, wherein one subsystem is used for extracting feature parameters of signals, and the other subsystem determines the modulation type of the signals by adopting a certain classifier according to the feature parameters of the signals.
The pattern recognition method based on feature extraction is a suboptimal method in theory, but the form is generally simpler and easy to implement, and the near-optimal recognition performance can be achieved under certain conditions. Under the condition of model mismatch, the mode identification method based on feature extraction is more robust than the maximum likelihood method. In the pattern recognition method based on feature extraction, a classifier for modulation recognition mainly comprises an artificial neural network, a support vector machine, a cluster and other pattern recognition methods.
Clustering is an important means in data mining, and is a process of dividing a data set into a plurality of groups or classes, and enabling data objects in the same group to have higher similarity, while data objects in different groups are non-similar. Clustering is currently being studied and applied in many areas, including data mining, statistics, pattern recognition, machine learning, image processing, and market analysis. At present, a clustering algorithm based on distance and a clustering method based on density are used for automatic identification based on a constellation map modulation mode.
The support vector machine is a pattern recognition method developed based on a statistical learning theory, and the basic idea is as follows: firstly, transforming an input space into a high-dimensional feature space through nonlinear transformation, and then solving a linear classification surface in the high-dimensional space, wherein the nonlinear transformation is realized by defining a proper kernel function, and only inner product operation is changed after dimension increasing, and the complexity of the algorithm is not increased along with the increase of the dimension. The SVM theoretically realizes the optimal classification of different classes, has better popularization capability, and can identify the modulation type of the signal according to the characteristic value of the signal.
However, in a conventional modulation recognition algorithm, for example, a modulation recognition algorithm based on clustering, when the signal-to-noise ratio of a received signal is low, the recognition rate of the modulation scheme is low. So that no reliable basis is provided for further processing of the signal, such as proper demodulation, analysis or interference. How to improve the modulation recognition rate of the signal is still one of the problems to be solved in the automatic modulation recognition algorithm.
Disclosure of Invention
The technical problem is as follows:the invention aims to provide a combined modulation identification method based on clustering and a support vector machine, so as to improve the defect that the clustering algorithm has low modulation identification rate at low signal-to-noise ratio. The method is used for extracting characteristic parameters of a modulation signal by using a clustering algorithm aiming at a modulation mode PSK/QAM based on a constellation diagram, and the modulation mode of the signal is identified by a support vector machine classifier. Compared with the method of singly adopting the clustering algorithm, the method can improve the modulation recognition rate of the system, and particularly, the recognition rate of the modulation signal is obviously improved when the signal-to-noise ratio of the received signal is lower.
The technical scheme is as follows:the invention provides an algorithm based on clustering and a support vector machine, which realizes automatic identification of a modulation mode so as to improve the defect that the clustering algorithm has low modulation identification rate at low signal-to-noise ratio. Aiming at a typical modulation mode PSK/QAM based on a constellation diagram, firstly, a clustering algorithm such as K-means clustering is utilized to reconstruct the constellation diagram of a received signal, and then an effectiveness evaluation function is constructed to respectively obtain effectiveness function values capable of reflecting the obvious difference of modulation types when different clustering centers are counted, and the effectiveness function values are used as characteristic parameters input into a support vector machine. In order to overcome the defect of high computational complexity of two algorithms, namely a one-to-more algorithm and a one-to-one algorithm, which are commonly used when the support vector machine identifies multiple classes, a hierarchical algorithm can be adopted to train the support vector machine. And finally, recognizing the modulation mode of the signal by using the trained support vector machine classifier so as to improve the modulation recognition rate of the system to the received signal.
The combined modulation identification method based on clustering and a support vector machine is used for extracting characteristic parameters of a modulation signal by utilizing a clustering algorithm aiming at a modulation mode PSK/QAM based on a constellation diagram, and the modulation mode of the signal is identified by a support vector machine classifier, and the method comprises the following steps:
a. setting a received signal obtained after signal preprocessing
In-phase component of
The orthogonal component is
Wherein in the subscriptRepresents the in-phase component of the signal,
which represents the orthogonal components of the signal,
n is the number of sample points;
b. classifying the sampling points by using a K-means clustering algorithm to obtain a clustering center point
And a first
From sampling point to
Membership of individual cluster centersThereby determining the attribution of each sample point, and reconstructing the constellation diagram of the received signal, wherein，
Is a sample
And a cluster center
The Euclidean distance of (a) is,
，
the value of (2) depends on the order of the modulation mode, if the modulation mode to be identified is BPSK, QPSK, 8PSK, 16QAM, 32QAM and 64QAM
Are 2, 4, 8, 16, 32 and 64, respectively;
c. for each sampling point
Calculating
The value of the one or more of,
wherein
Is a sample point
With the cluster centers to which they are assigned
The average euclidean distance of the other samples in (c),
is a sample point
With all being divided into the k-th cluster center
The average euclidean distance of all the sample points;
d. calculating all the partitions to the ith cluster centerOf the spots in
Average value of (2)
WhereinFor all membership to the cluster center
The number of spots;
e. when the number of clustering centers is K, the evaluation value of the clustering whole division result is obtained
Is defined as all
Mean value of (i)
；
f. By extraction of
Inputting the training support vector machine classifier as a characteristic parameter, and identifying the modulation mode of an input signal;
=2,4,8,16,32,64。
has the advantages that:compared with the method for automatically modulating and identifying by singly adopting a clustering algorithm, the method for jointly modulating and identifying based on the clustering and support vector machine can effectively improve the modulation identification rate of the system, and especially obviously improves the identification rate of a modulation mode when the signal-to-noise ratio of a received signal is low.
Drawings
FIG. 1 System model.
Fig. 2 a hierarchical SVM classifier.
Fig. 3 is a flow of a joint modulation identification algorithm.
Detailed Description
The system model of the joint modulation recognition algorithm based on the clustering and the support vector machine is shown in figure 1. The modulation signal is PSK/QAM based on the modulation mode of a constellation diagram, and the signal is influenced by additive white Gaussian noise and other interference in a channel in the process of propagation. Clustering and neural networks are two main algorithms for modulation recognition at the receiving end.
Clustering is an unsupervised learning process that divides a data set into groups or classes and makes data objects within the same group have a higher degree of similarity, while data objects in different groups are non-similar. Clustering analysis can discover the distribution patterns of data and the valuable correlation links that exist between data attributes. Because the modulation signal can be uniquely expressed by the constellation diagram based on the modulation mode of the constellation diagram, the received signal points can be classified through a clustering algorithm, the received signal constellation diagram is recovered, and further the characteristic parameters reflecting the obvious difference among the modulation types are extracted.
The support vector machine method is proposed from the optimal classification hyperplane under the condition of linear divisibility, firstly, an input space is transformed into a high-dimensional space through nonlinear transformation defined by a kernel function, and then the optimal linear classification hyperplane is solved in the new space. The support vector machine realizes the optimal classification of different classes theoretically and has better popularization capability. Therefore, on the basis of improving the modulation recognition performance of the system, the new combination of the characteristic parameters extracted by the clustering algorithm is used as the input of the support vector machine to train the support vector machine classifier, and then the modulation mode based on the constellation diagram is recognized by the trained support vector machine classifier.
The flow of the joint modulation identification algorithm based on clustering and a support vector machine comprises three parts: firstly, preprocessing the signal, processing the signal at this stage, reconstructing a constellation diagram of the signal by using a clustering algorithm, such as K-means clustering, and then calculating function values of different clustering centers by adopting an effectiveness function to be used as characteristic parameters of an input support vector machine; secondly, training and learning of the support vector machine, wherein a hierarchical algorithm can be adopted to train the support vector machine classifier so as to meet the set precision requirement; and the third is a testing stage, namely, a trained support vector machine classifier is used for identifying the modulation mode. The recognition rate of the system to the modulation mode is effectively improved by combining two pattern recognition algorithms of clustering and a support vector machine.
In the combined modulation identification method based on clustering and a support vector machine, firstly, the characteristic parameters of a modulation signal are extracted based on a clustering algorithm. In the clustering algorithm, firstly, the received signal is preprocessed, and the in-phase component and the orthogonal component of the received signal are obtained through signal preprocessing processes such as carrier frequency down-conversion, low-pass filtering and samplingValue, set as data matrix
. Obtaining a data set through signal preprocessing
Thereafter, a clustering operation, e.g., K-means clustering, may be performed on the sample points in the data set. The K-means clustering algorithm can automatically classify the data objects and obtain a clustering center by optimizing a fuzzy objective function
And degree of membership of each sample point to class centerThereby determining the attribution of the sample points. The FCM clustering problem can be expressed as the following mathematical programming problem with an objective function:
the constraint conditions are as follows:
where N is the data setThe number of the elements in (B). K is the number of cluster centersBecause it is to be identifiedThe modulation signals are: BPSK, QPSK, 8PSK, 16QAM, 32QAM, and 64QAM, with modulation orders of:
therefore, the center of cluster is taken hereinIn total, clustering operation is carried out on six cases respectively.
Is a sample
And a cluster center
The euclidean distance of (c).Is the degree of membership of the jth sample to the ith cluster center,，
. The K-means clustering algorithm can be converted into the following iterative algorithm implementation:
step 1: giving an iteration criterion
And initializing the classification matrix
You, n = 0;
step 2: computing updated membership matrices
：
（3）
And step 3: computing a cluster center matrix
：
And 4, step 4: using matrix norm
ComparisonAnd
if, if
The iteration is stopped, otherwise let k = k +1, going to step 2.
Through the iterative process, the objective function of the formula (1) is optimized, and finally the optimized clustering center and the membership matrix of each sample point to the clustering center can be obtained.
Because the optimal clustering center numbers of the signals with different modulation orders are different, the effective analysis can be carried out on the clustering results obtained when the clustering center numbers are different, and whether the received signal points are divided into K classes is judged to be reasonable or not to obtain the effective function value so as to distinguish different modulation signals in order to obtain the characteristic parameters capable of distinguishing different modulation modes. Different validity functions can be used, for example, the silhouette index algorithm, which is implemented as follows:
1) first for each signal point
Calculate it
The value:
(6)
wherein,
is the jth signal point
With the cluster centers to which they are assigned
The average distance of the other signal points in the spectrum,
is the jth signal point
With all being divided into the k-th cluster center
Average distance of all signal points.
2) Calculating all the partitions to the ith cluster center
Of signal points
Average value of (2)
：
Wherein,
for all membership to the cluster centerThe number of sample points.
3) When the number of clustering centers is K, the evaluation value of the clustering whole division result
Is defined as all
I.e.:
the degree of rationality of the division of the modulation signals into classes K is different for modulation signals of different order, i.e. for different modulation signals
The values are different from one another and can therefore be extracted by extracting the validity functionTo distinguish between different modulation types.
And extracting characteristic parameters of the modulation signals by using a clustering algorithm, sending the characteristic parameters extracted under different receiving signal-to-noise ratios to a support vector machine classifier, and training the support vector machine.
SVMs are proposed from solving the optimal classification surface in a linear separable situation. The optimal classification hyperplane is a plane that is required to separate two types of samples without errors and to maximize the distance between the two types. For two kinds of separable problems, the objective function is:
(9)
solving the formula (9) to obtain the optimal solution
(ii) a Selecting
A positive component of
And calculate accordingly
(ii) a Finally, the decision function is found to be:
(10)
when the support vector machine identifies multiple classes, two algorithms of one-to-many and one-to-one are commonly used. In order to overcome the disadvantage of high computational complexity of one-to-many and one-to-one algorithms, a hierarchical algorithm can be adopted to train the support vector machine at this stage, as shown in fig. 2.
The algorithm flow of the joint modulation identification algorithm based on clustering and a support vector machine is shown in fig. 3. And aiming at a modulation mode PSK/QAM based on a constellation diagram, extracting characteristic parameters of a modulation signal by using a clustering algorithm, sending the characteristic parameters extracted under different receiving signal-to-noise ratios to a support vector machine classifier, and training the support vector machine. After training of the support vector machine classifier is completed, for an unknown modulation signal, when the algorithm based on clustering and the support vector machine provided by the invention is applied to modulation identification, the following steps are required to be sequentially carried out:
1) preprocessing the signal to obtain a data set containing in-phase components and quadrature components of the signal
；
2) For data sets
Performing clustering operation, such as K-means FCM clustering algorithm, to obtain membership matrix of each signal point to clustering center
；
3) And processing the membership matrix by using an effectiveness function to obtain characteristic parameter vectors for distinguishing different modulation modes.
4) And taking the characteristic parameter vector as input, and sending the characteristic parameter vector into a trained support vector machine classifier. The modulation type of the unknown signal can be obtained from the output of the support vector machine, namely, the automatic identification of the modulation mode is realized.
Because the support vector machine classifier has strong pattern recognition capability, the optimal classification of different classes is realized theoretically, and the support vector machine classifier has better popularization capability. Therefore, the clustering algorithm is combined with the support vector machine classifier for automatic identification of the modulation signals, and the modulation identification rate of the system can be effectively improved.
Claims (1)
1. A joint modulation identification method based on clustering and a support vector machine is characterized in that the method utilizes a clustering algorithm to extract characteristic parameters of modulation signals aiming at a modulation mode PSK/QAM based on a constellation diagram, and identifies the modulation mode of the signals through a support vector machine classifier, and the method comprises the following steps:
a. setting a received signal obtained after signal preprocessing
In-phase component ofThe orthogonal component is
Wherein in the subscript
Represents the in-phase component of the signal,
which represents the orthogonal components of the signal,
n is the number of sample points;
b. classifying the sampling points by using a K-means clustering algorithm to obtain a clustering center point
And a first
From sampling point to
Membership of individual cluster centers
Thereby determining the attribution of each sample point, and reconstructing the constellation diagram of the received signal, wherein
，
Is a sample
And a cluster center
The Euclidean distance of (a) is,
，
the value of (2) depends on the order of the modulation mode, if the modulation mode to be identified is BPSK, QPSK, 8PSK, 16QAM, 32QAM and 64QAM
Are 2, 4, 8, 16, 32 and 64, respectively;
c. for each sampling point
CalculatingThe value of the one or more of,
wherein
Is a sample point
With the cluster centers to which they are assigned
The average euclidean distance of the other samples in (c),is a sample point
With all being divided into the k-th cluster center
The average euclidean distance of all the sample points;
d. calculating all the partitions to the ith cluster center
Of the spots in
Average value of (2)
Wherein
For all membership to the cluster centerThe number of spots;
e. when the number of clustering centers is K, the evaluation value of the clustering whole division result is obtained
Is defined as allMean value of (i)；
f. By extraction of
Inputting the training support vector machine classifier as a characteristic parameter, and identifying the modulation mode of an input signal;
=2,4,8,16,32,64。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103835521A CN102497343A (en) | 2011-11-25 | 2011-11-25 | Combined modulation recognition method based on clustering and support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103835521A CN102497343A (en) | 2011-11-25 | 2011-11-25 | Combined modulation recognition method based on clustering and support vector machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102497343A true CN102497343A (en) | 2012-06-13 |
Family
ID=46189130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011103835521A Pending CN102497343A (en) | 2011-11-25 | 2011-11-25 | Combined modulation recognition method based on clustering and support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102497343A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104363194A (en) * | 2014-11-04 | 2015-02-18 | 武汉大学 | PSK (phase shift keying) modulation recognition method based on wave form transformation |
| CN105553897A (en) * | 2015-12-11 | 2016-05-04 | 西安电子科技大学 | Dynamic plasma sheath phase shift keying signal decision detection method |
| CN105915479A (en) * | 2016-06-20 | 2016-08-31 | 深圳市统先科技股份有限公司 | Modulation identification method and system based on clustering algorithm |
| CN106021829A (en) * | 2016-07-19 | 2016-10-12 | 中南大学 | Modeling method for nonlinear system for stable parameter estimation based on RBF-ARX model |
| CN106789788A (en) * | 2016-12-26 | 2017-05-31 | 北京邮电大学 | A kind of wireless digital signal Modulation Mode Recognition method and device |
| CN107147600A (en) * | 2017-04-28 | 2017-09-08 | 电子科技大学 | A kind of digital modulation signals demodulator and its demodulation method based on neutral net |
| CN107770108A (en) * | 2017-10-23 | 2018-03-06 | 佛山科学技术学院 | A kind of combined modulation recognition methods of K mean clusters and classification training SVM classifier |
| CN108052956A (en) * | 2017-11-07 | 2018-05-18 | 西安理工大学 | Wireless light communication subcarrier modulation constellation recognition methods under a kind of atmospheric turbulance |
| CN108900460A (en) * | 2018-06-12 | 2018-11-27 | 南京邮电大学 | A kind of robust symbol detection method of the anti-phase noise based on K mean cluster |
| CN109347775A (en) * | 2018-10-22 | 2019-02-15 | 西南交通大学 | A kind of modulation format recognition methods of combined strength fluctuation and phase fluctuation feature |
| CN109495183A (en) * | 2018-10-29 | 2019-03-19 | 武汉邮电科学研究院有限公司 | The tracking and system of constellation dot center in a kind of coherent optical communication system |
| CN110048978A (en) * | 2019-04-09 | 2019-07-23 | 西安电子科技大学 | A kind of signal modulate method |
| CN110166389A (en) * | 2019-06-12 | 2019-08-23 | 西安电子科技大学 | Modulation Identification method based on least square method supporting vector machine |
| CN110191073A (en) * | 2019-06-28 | 2019-08-30 | 华侨大学 | A kind of Modulation Mode Recognition method based on deep learning suitable for scene change |
| CN111444805A (en) * | 2020-03-19 | 2020-07-24 | 哈尔滨工程大学 | Improved multi-scale wavelet entropy digital signal modulation identification method |
| CN111817994A (en) * | 2019-07-25 | 2020-10-23 | 中国人民解放军陆军工程大学 | Modulation identification method and device based on phase difference constellation diagram clustering |
| CN112737992A (en) * | 2020-09-23 | 2021-04-30 | 青岛科技大学 | Underwater sound signal modulation mode self-adaptive in-class identification method |
| CN113518050A (en) * | 2021-06-24 | 2021-10-19 | 华东交通大学 | Modulation identification method, system, readable storage medium and device |
| CN116094886A (en) * | 2023-03-09 | 2023-05-09 | 浙江万胜智能科技股份有限公司 | Carrier communication data processing method and system in dual-mode module |
| CN117955526A (en) * | 2024-03-26 | 2024-04-30 | 昀诺能源科技(江苏)有限公司 | Communication method and device of dual-mode module electric energy meter in power grid and electric energy meter |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008049175A1 (en) * | 2006-10-24 | 2008-05-02 | Katholieke Universiteit Leuven | High discriminating power biomarker diagnosing |
| CN101895494A (en) * | 2010-07-12 | 2010-11-24 | 西安电子科技大学 | Stochastic resonance preprocessing-based digital modulation mode automatic identification method |
-
2011
- 2011-11-25 CN CN2011103835521A patent/CN102497343A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008049175A1 (en) * | 2006-10-24 | 2008-05-02 | Katholieke Universiteit Leuven | High discriminating power biomarker diagnosing |
| CN101895494A (en) * | 2010-07-12 | 2010-11-24 | 西安电子科技大学 | Stochastic resonance preprocessing-based digital modulation mode automatic identification method |
Non-Patent Citations (3)
| Title |
|---|
| LIU AISHENG ET.AL: "Automatic modulation classification based on the combination of clustering and neural network", 《THE JOURNAL OF CHINA UNIVERSITIES OF POSTS AND TELECOMMUNICATIONS》 * |
| XIAOJIE GONG ET.AL: "Collaborative modulation recognition based on SVM", 《NATURAL COMPUTATION,2010 SIXTH INTERNATIONAL CONFERENCE ON》 * |
| 刘爱声等: "多传感器节点分布式协作调制识别算法", 《信号处理》 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104363194A (en) * | 2014-11-04 | 2015-02-18 | 武汉大学 | PSK (phase shift keying) modulation recognition method based on wave form transformation |
| CN105553897B (en) * | 2015-12-11 | 2018-09-25 | 西安电子科技大学 | A kind of dynamic plasma sheath phase shift keyed signal judgement detection method |
| CN105553897A (en) * | 2015-12-11 | 2016-05-04 | 西安电子科技大学 | Dynamic plasma sheath phase shift keying signal decision detection method |
| CN105915479A (en) * | 2016-06-20 | 2016-08-31 | 深圳市统先科技股份有限公司 | Modulation identification method and system based on clustering algorithm |
| CN105915479B (en) * | 2016-06-20 | 2019-03-22 | 深圳市统先科技股份有限公司 | A kind of Modulation Identification method and system based on clustering algorithm |
| CN106021829B (en) * | 2016-07-19 | 2018-11-20 | 中南大学 | A kind of nonlinear system modeling method based on RBF-ARX model stability parameter Estimation |
| CN106021829A (en) * | 2016-07-19 | 2016-10-12 | 中南大学 | Modeling method for nonlinear system for stable parameter estimation based on RBF-ARX model |
| CN106789788A (en) * | 2016-12-26 | 2017-05-31 | 北京邮电大学 | A kind of wireless digital signal Modulation Mode Recognition method and device |
| CN106789788B (en) * | 2016-12-26 | 2019-05-10 | 北京邮电大学 | A kind of wireless digital signal Modulation Mode Recognition method and device |
| CN107147600A (en) * | 2017-04-28 | 2017-09-08 | 电子科技大学 | A kind of digital modulation signals demodulator and its demodulation method based on neutral net |
| CN107147600B (en) * | 2017-04-28 | 2020-11-17 | 电子科技大学 | Digital modulation signal demodulator based on neural network and demodulation method thereof |
| CN107770108A (en) * | 2017-10-23 | 2018-03-06 | 佛山科学技术学院 | A kind of combined modulation recognition methods of K mean clusters and classification training SVM classifier |
| CN108052956A (en) * | 2017-11-07 | 2018-05-18 | 西安理工大学 | Wireless light communication subcarrier modulation constellation recognition methods under a kind of atmospheric turbulance |
| CN108900460A (en) * | 2018-06-12 | 2018-11-27 | 南京邮电大学 | A kind of robust symbol detection method of the anti-phase noise based on K mean cluster |
| CN108900460B (en) * | 2018-06-12 | 2020-11-13 | 南京邮电大学 | Anti-phase noise robust symbol detection method based on K-means clustering |
| CN109347775A (en) * | 2018-10-22 | 2019-02-15 | 西南交通大学 | A kind of modulation format recognition methods of combined strength fluctuation and phase fluctuation feature |
| CN109347775B (en) * | 2018-10-22 | 2020-12-18 | 西南交通大学 | Modulation format identification method combining intensity fluctuation and phase fluctuation characteristics |
| CN109495183A (en) * | 2018-10-29 | 2019-03-19 | 武汉邮电科学研究院有限公司 | The tracking and system of constellation dot center in a kind of coherent optical communication system |
| CN109495183B (en) * | 2018-10-29 | 2020-06-23 | 武汉邮电科学研究院有限公司 | Method and system for tracking constellation point center in coherent optical communication system |
| CN110048978A (en) * | 2019-04-09 | 2019-07-23 | 西安电子科技大学 | A kind of signal modulate method |
| CN110166389A (en) * | 2019-06-12 | 2019-08-23 | 西安电子科技大学 | Modulation Identification method based on least square method supporting vector machine |
| CN110166389B (en) * | 2019-06-12 | 2021-06-25 | 西安电子科技大学 | Modulation identification method based on least square support vector machine |
| CN110191073A (en) * | 2019-06-28 | 2019-08-30 | 华侨大学 | A kind of Modulation Mode Recognition method based on deep learning suitable for scene change |
| CN110191073B (en) * | 2019-06-28 | 2021-08-31 | 华侨大学 | Modulation mode identification method based on deep learning and suitable for changing scene |
| CN111817994A (en) * | 2019-07-25 | 2020-10-23 | 中国人民解放军陆军工程大学 | Modulation identification method and device based on phase difference constellation diagram clustering |
| CN111444805A (en) * | 2020-03-19 | 2020-07-24 | 哈尔滨工程大学 | Improved multi-scale wavelet entropy digital signal modulation identification method |
| CN111444805B (en) * | 2020-03-19 | 2023-03-17 | 哈尔滨工程大学 | Improved multi-scale wavelet entropy digital signal modulation identification method |
| CN112737992A (en) * | 2020-09-23 | 2021-04-30 | 青岛科技大学 | Underwater sound signal modulation mode self-adaptive in-class identification method |
| CN113518050A (en) * | 2021-06-24 | 2021-10-19 | 华东交通大学 | Modulation identification method, system, readable storage medium and device |
| CN116094886A (en) * | 2023-03-09 | 2023-05-09 | 浙江万胜智能科技股份有限公司 | Carrier communication data processing method and system in dual-mode module |
| CN116094886B (en) * | 2023-03-09 | 2023-08-25 | 浙江万胜智能科技股份有限公司 | Carrier communication data processing method and system in dual-mode module |
| CN117955526A (en) * | 2024-03-26 | 2024-04-30 | 昀诺能源科技(江苏)有限公司 | Communication method and device of dual-mode module electric energy meter in power grid and electric energy meter |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102497343A (en) | Combined modulation recognition method based on clustering and support vector machine | |
| CN109802905B (en) | CNN convolutional neural network-based digital signal automatic modulation identification method | |
| Jdid et al. | Machine learning based automatic modulation recognition for wireless communications: A comprehensive survey | |
| CN108234370B (en) | Communication signal modulation mode identification method based on convolutional neural network | |
| CN111832417B (en) | Signal modulation pattern recognition method based on CNN-LSTM model and transfer learning | |
| Doan et al. | Learning constellation map with deep CNN for accurate modulation recognition | |
| Liu et al. | Automatic modulation classification based on the combination of clustering and neural network | |
| CN111814777B (en) | Modulation pattern recognition method based on characteristic quantity grading | |
| Jdid et al. | Robust automatic modulation recognition through joint contribution of hand-crafted and contextual features | |
| CN114422311B (en) | Signal modulation recognition method and system combining deep neural network and expert priori features | |
| CN114567528A (en) | Communication signal modulation mode open set identification method and system based on deep learning | |
| CN112613443A (en) | Robustness communication radiation source intelligent identification method based on deep learning | |
| Bouchenak et al. | A semi-supervised modulation identification in MIMO systems: A deep learning strategy | |
| Li et al. | The importance of expert knowledge for automatic modulation open set recognition | |
| CN109274626B (en) | Modulation identification method based on constellation diagram orthogonal scanning characteristics | |
| CN108809874B (en) | Radar and communication multi-signal classification method based on circulation support vector machine | |
| CN114615118A (en) | Modulation identification method based on multi-terminal convolution neural network | |
| Kim et al. | Automatic modulation classification using relation network with denoising autoencoder | |
| CN115913850B (en) | Open set modulation identification method based on residual error network | |
| Huynh-The et al. | Deep learning for constellation-based modulation classification under multipath fading channels | |
| CN115935252A (en) | Communication signal modulation pattern recognition method and device based on self-supervision contrast learning | |
| CN113518050B (en) | Modulation identification method, system, readable storage medium and device | |
| Wong | On the use of convolutional neural networks for specific emitter identification | |
| Alzaq-Osmanoglu et al. | Low-SNR Modulation Recognition based on Deep Learning on Software Defined Radio | |
| Yun et al. | Few-shot modulation recognition using Recurrence Plot Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120613 |