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
- signal
- support vector
- vector machine
- cluster
- 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
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 present invention relates to a kind of Automatic Modulation Recognition implementation, belong to communication technical field based on cluster and SVMs.
Background technology
Along with development of Communication Technique, signal of communication adopts different modulation modes on very wide frequency band, and the modulation parameter of these signals also is not quite similar simultaneously.The Automatic Modulation Recognition of digital signal can multiple modulation signal with the modulation system of determining signal under the condition of noise jamming is arranged, in the civil and military field important effect is arranged all.Along with the system of signal of communication and modulation pattern become complicated more various, it is particularly important and urgent that the Modulation Identification of signal of communication just seems.
At present, modulation system automatically the research method of identification mainly can be divided into two types: based on the maximum likelihood method of hypothesis testing with based on the mode identification method of feature extraction.Based on the maximum likelihood method of hypothesis testing, handle through likelihood function signal, likelihood ratio that obtains and threshold value are compared, accomplish the Modulation Identification function.Based on the mode identification method of feature extraction, comprise two sub-systems usually, a sub-systems is used to extract the characteristic parameter of signal, and another subsystem adopts certain grader to confirm the modulation type of signal according to the characteristic parameter of signal.
Based on the mode identification method of feature extraction, be a kind of method of suboptimum in theory, but its form is fairly simple usually, be easy to realize, and can reach the recognition performance of near-optimization under certain conditions.Under the situation of model mismatch, more sane than maximum likelihood method based on the mode identification method of feature extraction.In mode identification method based on feature extraction, be used for the grader of Modulation Identification, mainly comprise artificial neural net, SVMs, cluster and some other mode identification method.
Cluster is important means in the data mining, be with data set be divided into some groups or type process, and make the data object in same group have higher similarity, then right and wrong are not similar for the data object on the same group.At present in a lot of fields, comprise that data mining, statistics, pattern recognition, machine learning, image processing, market analysis all have the research and the application of cluster.Be used for based on the planisphere automatic Modulation Recognition at present based on the clustering algorithm of distance and based on the clustering method of density.
SVMs is based on Statistical Learning Theory and a kind of mode identification method of growing up; Its basic thought is: at first through nonlinear transformation the input space is transformed to a high-dimensional feature space; Ask the linear classification face at this higher dimensional space then; And this nonlinear transformation is to realize through defining suitable kernel function, has just changed inner product operation after the liter dimension, and algorithm complexity is increased along with the increase of dimension.SVM has realized that theoretically different classes of optimal classification is had the ability of promoting preferably, can be according to the characteristic value of signal, and the modulation type of identification signal.
Yet in Modulation Recognition in the past, for example, in the Modulation Recognition based on cluster, when the signal to noise ratio that receives signal was low, the discrimination of modulation system was very low.So that can't be further processing signals, perhaps disturbing like correct demodulation, analysis provides reliable foundation.How to improve the Modulation Identification rate of signal, being still needs one of problem that solves in the Automatic Modulation Recognition algorithm.
Summary of the invention
Technical problem:The objective of the invention is to be to provide a kind of associating Modulation Identification method, to improve clustering algorithm low shortcoming of Modulation Identification rate when the low signal-to-noise ratio based on cluster and SVMs.This method is utilized the characteristic parameter of clustering algorithm extraction modulation signal to the modulation system PSK/QAM based on planisphere, identifies the modulation system of signal through support vector machine classifier.Compare with independent employing clustering algorithm, this method can improve the Modulation Identification rate of system, and especially when the signal to noise ratio that receives signal was low, the discrimination of modulation signal obviously improved.
Technical scheme:The present invention provides a kind of algorithm based on cluster and SVMs, realizes automatic Modulation Recognition, to improve clustering algorithm low shortcoming of Modulation Identification rate when the low signal-to-noise ratio.This method is to typical modulation system PSK/QAM based on planisphere; At first utilize clustering algorithm; Like the K-mean cluster, rebuild the planisphere that receives signal, then through structure validity valuation functions; Obtain when different cluster centres are counted, can reflecting the validity functional value of modulation type significant difference respectively, as the characteristic parameter of input SVMs.When discerning the multiclass problem in order to overcome SVMs, commonly used a pair of surplus type reaches type two kinds of shortcomings that the algorithm computation complexity is high one to one, can adopt the algorithm of classification that SVMs is trained.Utilize the support vector machine classifier train at last, identify the modulation system of signal, to improve the Modulation Identification rate that system docking is collected mail number.
Associating Modulation Identification method based on cluster and SVMs is directed against the modulation system PSK/QAM based on planisphere; Utilize clustering algorithm to extract the characteristic parameter of modulation signal; Identify the modulation system of signal through support vector machine classifier, the method includes the steps of:
A. establish through the reception signal
that obtains after the Signal Pretreatment in-phase component is
; Quadrature component is
; Wherein
in the subscript represents in-phase component;
represents quadrature component;
, N is the number of sampling point;
B. utilize the K-means clustering algorithm that sampling point is classified; Obtain the degree of membership
of cluster centre point
and the individual cluster centre of
individual sampling point to the
; Thereby determine the ownership of each sampling point; Rebuild the planisphere that receives signal; Wherein
;
is the Euclidean distance of sample
and cluster centre
;
; The value of
depends on the exponent number of modulation system; If modulation system to be identified is BPSK, QPSK, 8PSK, 16QAM, 32QAM and 64QAM, then the value of
is respectively 2,4,8,16,32 and 64;
C. to each sampling point
; Calculate
and be worth;
; Wherein
is the average Euclidean distance of other sampling points in sampling point
and the cluster centre
that is divided into its place, and
is divided into the average Euclidean distance of all sampling points of k cluster centre
for sampling point
with all;
D. calculate the mean value
of all
that are divided into the sampling point in i the cluster centre
, wherein
is under the jurisdiction of the sampling point number of cluster centre
for all;
E. when the cluster centre number is K; The assessed value
of the whole results of cluster is defined as the average that owns
, i.e.
;
F. utilize
support vector machine classifier that input trains as characteristic parameter that extracts, identify the modulation system of input signal;
=2; 4,8,16; 32,64.
Beneficial effect:The invention provides a kind of associating Modulation Identification method based on cluster and SVMs; Carrying out Automatic Modulation Recognition with independent employing clustering algorithm compares; The algorithm that the present invention proposes can effectively improve the Modulation Identification rate of system; Especially when the signal to noise ratio that receives signal was low, the discrimination of modulation system obviously improved.
Description of drawings
Fig. 1 system model.
Fig. 2 classification svm classifier device.
Fig. 3 unites the Modulation Recognition flow process.
Embodiment
The given system model based on the associating Modulation Recognition of cluster and SVMs of the present invention is as shown in Figure 1.Modulation signal is the modulation system PSK/QAM based on planisphere, and signal can receive the influence of additive white Gaussian noise and other interference in the channel in communication process.Cluster and neural net are two kinds of main algorithm of carrying out Modulation Identification at receiving terminal.
Cluster is a kind of unsupervised learning, be with data set be divided into some groups or type process, and make the data object in same group have higher similarity, then right and wrong are not similar for the data object on the same group.Cluster analysis can be found the valuable correlative connection that exists between distribution pattern and the data attribute of data.Modulation system based on planisphere; Because its modulation signal can be by the unique statement of its planisphere, thereby can pass through clustering algorithm, the signaling point that receives is classified; Recover to receive signal constellation which, and then extract the characteristic parameter that has significant difference between the reflection modulation type.
Support vector machine method is that the optimal classification hyperplane under the linear separability situation proposes, and it at first transforms to a higher dimensional space through the nonlinear transformation of kernel function definition with the input space, in this new space, asks for optimum linearity classification hyperplane then.SVMs has realized that theoretically different classes of optimal classification is had the ability of promoting preferably.Therefore; Can be from improving the Modulation Identification performance of system; Utilize the new combination of the characteristic parameter that clustering algorithm extracts support vector machine classifier to be trained, utilize the support vector machine classifier after the training that the modulation system based on planisphere is discerned then as the input of SVMs.
Flow process based on the associating Modulation Recognition of cluster and SVMs comprises three parts: the one, and the preliminary treatment of signal; In this stage signal is handled; Utilize clustering algorithm, like the K-mean cluster, the planisphere of reconstruction signal; Adopt the validity function calculation to go out the functional value when different cluster centres are counted then, as the characteristic parameter of input SVMs; The 2nd, the training study of SVMs can adopt the algorithm of classification in this stage, support vector machine classifier is trained, to reach the required precision of setting; The 3rd, test phase promptly utilizes the support vector machine classifier that trains that modulation system is discerned.Through the combination of cluster and two kinds of algorithm for pattern recognitions of SVMs, with the discrimination of effective raising system to modulation system.
In the associating Modulation Identification method based on cluster and SVMs, at first carry out the extraction of modulation signal characteristic parameter based on clustering algorithm.In clustering algorithm; At first to the signal that receive be carried out preliminary treatment; Through carrier down-conversion; LPF, and Signal Pretreatment process such as sampling obtains receiving the in-phase component of signal and the value of quadrature component, is made as data matrix
.After the process Signal Pretreatment obtains data set
; Can carry out the cluster computing to the sample point that data are concentrated; For example, K-mean cluster.The K-means clustering algorithm can be classified to the data object automatically; Obtain cluster centre
and the degree of membership
of each sample point through optimizing the fuzzy object function, thereby determine the ownership of sample point the class center.The FCM clustering problem can be expressed as following mathematical programming problem, and its target function is:
Its constraints is:
Wherein, N is the number of element in the data set
.K is cluster centre number
; Because modulation signal to be identified is: BPSK; QPSK; 8PSK; 16QAM; 32QAM; And 64QAM, its order of modulation is respectively:
, so get in this article cluster centre number
totally six kinds of situation carry out the cluster computing respectively.
is the sample
and the cluster center
Euclidean distance.
is the degree of membership of j sample to i cluster centre;
,
.The K-means clustering algorithm can be converted into following iterative algorithm and realize:
Step 1: provide iteration standard
; And initialization classification matrix
, you, n=0;
Step 2: calculate renewal and be subordinate to matrix
:
（3）
Step 3: calculate cluster centre matrix
:
Step 4: with matrix norm
compares
and
, if
Then stop iteration, otherwise make k=k+1, turn to step 2.
Through above-mentioned iterative process, optimize the target function of (1) formula, cluster centre that finally can be optimized and the degree of membership matrix of each sample point to cluster centre.
Owing to have the signal of different modulating exponent number; Its best cluster centre number is different; Thereby to obtain distinguishing the characteristic parameter of different modulating mode, and can carry out efficiency analysis to the cluster result that when different cluster centres are counted the K value, obtains, judge whether received signal points is divided into the K class reasonable; Obtain the validity functional value, thereby distinguish different modulation signals.Can adopt different effective property function, for example, silhouette index algorithm, its concrete implementation procedure is following:
1), calculate its
value at first to each signaling point
:
(6)
Wherein,
is the average distance of other signaling points in j signaling point
and the cluster centre
that is divided into its place, and
is that j signaling point
is divided into the average distance of all signaling points of k cluster centre
with all.
2) calculation of all classified into the i-th cluster center
The signal point
average
:
Wherein,
is under the jurisdiction of the sample point number of cluster centre
for all.
When 3) the cluster centre number being K; Assessed value
to the whole results of cluster; Be defined as the average of all
, that is:
The modulation signal that order of modulation is different; With its division of signal is that the resonable degree of K class is different;
value that is different modulated signals has nothing in common with each other; Therefore can distinguish different modulation types through extracting the value of validity function
.
Utilize clustering algorithm to extract the characteristic parameter of modulation signal, the characteristic parameter that will under different received signal to noise ratio, extract is sent into support vector machine classifier, and SVMs is trained.
SVM finds the solution the proposition of optimal classification face under the linear separability situation.So-called optimal classification hyperplane is exactly that requirement classification plane not only can be faultless separately with two types of samples, and will makes the distance between two types maximum.For two types of separable problems, its target function is:
(9)
Find the solution formula (9) formula and obtain optimal solution
; A positive component
of selecting
, and calculate
in view of the above; At last, trying to achieve decision function is:
(10)
During SVMs identification multiclass problem, commonly used a pair of surplus type reaches type two kinds of algorithms one to one.Reach type two kinds of shortcomings that the algorithm computation complexity is high one to one in order to overcome a pair of surplus type, can adopt the algorithm of classification that SVMs is trained in this stage, as shown in Figure 2.
Algorithm flow based on the associating Modulation Recognition of cluster and SVMs is as shown in Figure 3.To modulation system PSK/QAM based on planisphere, utilize clustering algorithm to extract the characteristic parameter of modulation signal, the characteristic parameter that will under different received signal to noise ratio, extract is sent into support vector machine classifier, and SVMs is trained.After the support vector machine classifier training is accomplished,, when the application algorithm based on cluster and SVMs proposed by the invention carries out Modulation Identification, need pass through following steps successively for the modulation signal an of the unknown:
1), obtains comprising the data set
of signal in-phase component and quadrature component through preliminary treatment;
2) data set
is carried out the cluster computing; Like K-average FCM clustering algorithm, obtain the degree of membership matrix
of each signaling point to cluster centre;
3) the degree of membership matrix is handled with the validity function, obtained distinguishing the characteristic parameter vector of different modulating mode.
4) characteristic parameter is vectorial as input, send into the support vector machine classifier that trains.Can obtain the modulation type of unknown signaling from the output of SVMs, promptly realize automatic Modulation Recognition.
Because support vector machine classifier has very strong mode identificating ability, has realized that theoretically different classes of optimal classification is had the ability of promoting preferably.Therefore clustering algorithm is combined with support vector machine classifier, be used for the automatic identification of modulation signal, can effectively improve the Modulation Identification rate of system.
Claims (1)
1. associating Modulation Identification method based on cluster and SVMs; It is characterized in that this method is to the modulation system PSK/QAM based on planisphere; Utilize clustering algorithm to extract the characteristic parameter of modulation signal; Identify the modulation system of signal through support vector machine classifier, the method includes the steps of:
A. establish through the reception signal
that obtains after the Signal Pretreatment in-phase component is
; Quadrature component is
; Wherein
in the subscript represents in-phase component;
represents quadrature component;
, N is the number of sampling point;
B. utilize the K-means clustering algorithm that sampling point is classified; Obtain the degree of membership
of cluster centre point
and the individual cluster centre of
individual sampling point to the
; Thereby determine the ownership of each sampling point; Rebuild the planisphere that receives signal; Wherein
;
is the Euclidean distance of sample
and cluster centre
;
; The value of
depends on the exponent number of modulation system; If modulation system to be identified is BPSK, QPSK, 8PSK, 16QAM, 32QAM and 64QAM, then the value of
is respectively 2,4,8,16,32 and 64;
C. to each sampling point
; Calculate
and be worth;
; Wherein
is the average Euclidean distance of other sampling points in sampling point
and the cluster centre
that is divided into its place, and
is divided into the average Euclidean distance of all sampling points of k cluster centre
for sampling point
with all;
D. calculate the mean value
of all
that are divided into the sampling point in i the cluster centre
, wherein
is under the jurisdiction of the sampling point number of cluster centre
for all;
E. when the cluster centre number is K; The assessed value
of the whole results of cluster is defined as the average that owns
, i.e.
;
F. utilize
support vector machine classifier that input trains as characteristic parameter that extracts, identify the modulation system of 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 | |
| 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 | |
| CN102710572B (en) | Feature extraction and modulation identification method of communication signals | |
| CN107948107B (en) | Digital modulation signal classification method based on joint features | |
| CN108718288B (en) | Method for recognizing digital signal modulation mode based on convolutional neural network | |
| CN109120563B (en) | Modulation recognition method based on neural network integration | |
| CN101834819B (en) | Analog-digital mixing modulation recognition device and digital modulation recognition device based on parallel judgment | |
| CN109660297A (en) | A kind of physical layer visible light communication method based on machine learning | |
| Doan et al. | Learning constellation map with deep CNN for accurate modulation recognition | |
| CN107135017A (en) | Backscatter communication system signal method of sending and receiving | |
| CN107770108A (en) | A kind of combined modulation recognition methods of K mean clusters and classification training SVM classifier | |
| CN103441974B (en) | A kind of Modulation Identification device and method combining high-order statistic and spectral peak feature | |
| CN110113288A (en) | A kind of design and demodulation method of the ofdm demodulator based on machine learning | |
| CN108052956A (en) | Wireless light communication subcarrier modulation constellation recognition methods under a kind of atmospheric turbulance | |
| CN114422311B (en) | Signal modulation recognition method and system combining deep neural network and expert priori features | |
| CN102647391A (en) | Cooperative modulation signal identifying method based on data fusion of decision layer | |
| CN111049770A (en) | Modulation signal identification method based on high-order cumulant | |
| Mustafa et al. | Digital modulation recognition using support vector machine classifier | |
| Almohamad et al. | Dual-determination of modulation types and signal-to-noise ratios using 2D-ASIQH features for next generation of wireless communication systems | |
| 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 | |
| CN109145889A (en) | A kind of bright ciphertext Modulation recognition detection method carrying out blind estimate for wireless signal | |
| CN113869156A (en) | Radio frequency fingerprint identification method |
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 |