CN113904902B - Method and device for identifying signal modulation type - Google Patents
Method and device for identifying signal modulation type Download PDFInfo
- Publication number
- CN113904902B CN113904902B CN202111101685.5A CN202111101685A CN113904902B CN 113904902 B CN113904902 B CN 113904902B CN 202111101685 A CN202111101685 A CN 202111101685A CN 113904902 B CN113904902 B CN 113904902B
- Authority
- CN
- China
- Prior art keywords
- signal
- identified
- characteristic
- fusion
- identifying
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 60
- 230000004927 fusion Effects 0.000 claims abstract description 65
- 238000007499 fusion processing Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005562 fading Methods 0.000 claims description 13
- 238000011176 pooling Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000007500 overflow downdraw method Methods 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000006467 substitution reaction 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
- H04B7/0891—Space-time diversity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/02—Arrangements for detecting or preventing errors in the information received by diversity reception
- H04L1/06—Arrangements for detecting or preventing errors in the information received by diversity reception using space diversity
- H04L1/0612—Space-time modulation
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Radio Transmission System (AREA)
Abstract
The invention provides a method and a device for identifying a signal modulation type, wherein the method comprises the following steps: acquiring a signal to be identified; determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified; performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified; and identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified. The method can quickly and accurately identify the modulation type of the digital signal.
Description
Technical Field
The present invention relates to the field of digital signal technology, and in particular, to a method and an apparatus for identifying a signal modulation type.
Background
In recent years, with the rapid development of communication technology and high-performance computing technology, the digital signal modulation types are more and more complex to adapt to the increasing demands of communication effectiveness and reliability.
The traditional digital signal modulation type identification method based on feature extraction has the following defects:
(1) Manual extraction which is very dependent on characteristic parameters;
(2) The performance of its classifier also greatly limits the accuracy of the method.
Therefore, how to quickly and accurately identify the modulation type of the digital signal is an important issue to be solved in the industry at present.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for identifying a signal modulation type, which are used for solving the defect that the modulation type of a digital signal cannot be identified accurately and quickly in the prior art and realizing the rapid and accurate identification of the modulation type of the digital signal.
In a first aspect, the present invention provides a method for identifying a signal modulation type, including:
acquiring a signal to be identified;
determining the time domain space convolution characteristics of the signal to be identified and the high-order cumulant characteristics of the signal to be identified;
performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
Optionally, according to the method for identifying a signal modulation type of the present invention, the acquiring a signal to be identified includes:
receiving a multipath fading radio frequency signal through multi-antenna diversity;
performing signal processing on the multipath fading radio frequency signals to obtain a plurality of complex baseband signals;
and performing energy normalization processing on the multiple complex baseband signals to obtain normalized complex baseband signals, wherein the normalized complex baseband signals are the signals to be identified.
Optionally, according to the method for identifying a signal modulation type of the present invention, the determining a time-domain spatial convolution characteristic of the signal to be identified includes:
setting the signal to be identified to obtain the time domain space convolution characteristic of the signal to be identified;
wherein the setting process includes one or more of:
zero padding operation;
performing convolution operation;
performing pooling operation;
flattening operation;
and (5) performing full connection operation.
Optionally, according to the method for identifying a signal modulation type of the present invention, the high-order cumulative quantity characteristic of the signal to be identified includes a required order of the signal to be identified and/or a high-order cumulative quantity of a required conjugate parameter.
Optionally, according to the method for identifying a signal modulation type of the present invention, the performing fusion processing on the time-domain spatial convolution feature and the high-order cumulant feature includes:
determining a multi-dimensional fusion network model for fusion processing;
and inputting the time domain space convolution characteristic and the high-order cumulant characteristic into the multi-dimensional fusion network model, wherein the output result of the multi-dimensional fusion network model is the fusion characteristic of the signal to be identified.
Optionally, according to the method for identifying a signal modulation type of the present invention, the identifying a modulation type of the signal to be identified according to the fusion feature of the signal to be identified includes:
determining a classification network model for identifying a modulation type of a signal;
and inputting the fusion characteristics of the signals to be identified into the classification network model, wherein the output result of the multi-classification network model is the modulation type of the signals to be identified.
In a second aspect, the present invention further provides an apparatus for identifying a signal modulation type, including:
an acquisition unit for acquiring a signal to be identified;
the determining unit is used for determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified;
the fusion unit is used for performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and the identification unit is used for identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
In a third aspect, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for identifying a signal modulation type according to any one of the above first aspects when executing the program.
In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for identifying a signal modulation type according to any one of the above first aspects.
In a fifth aspect, the present invention further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the method for identifying a signal modulation type according to any one of the above first aspects.
According to the method for identifying the signal modulation type, provided by the invention, the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified are determined, the time domain space convolution characteristic and the high-order cumulant characteristic are subjected to fusion processing to obtain the fusion characteristic of the signal to be identified, the modulation type of the signal to be identified is identified according to the fusion characteristic of the signal to be identified, and the digital signal modulation type can be identified rapidly and accurately.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying a signal modulation type according to the present invention;
FIG. 2 is a second flowchart illustrating a method for identifying a signal modulation type according to the present invention;
fig. 3 is a comparison graph of the recognition accuracy of the recognition method of the signal modulation type provided by the present invention under a five-path rice distribution (Rician) channel;
FIG. 4 is a schematic structural diagram of a device for identifying a signal modulation type provided by the present invention;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
The term "and/or" in the present invention describes an association relationship of associated objects, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The term "plurality" as used herein means two or more, and other terms are analogous.
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The method for identifying the type of signal modulation according to the present invention is described below with reference to fig. 1 to 3.
Fig. 1 is a schematic flow diagram of a method for identifying a signal modulation type provided by the present invention, as shown in fig. 1, the method for identifying a signal modulation type provided by the present invention can be used for identifying a modulation type of a signal in a multipath fading channel scenario, and the method for identifying a signal modulation type includes:
Specifically, the Modulation type of the signal to be identified may be a Phase-Shift Keying (PSK) signal, a Quadrature Amplitude Modulation (QAM) signal, or a Frequency-Shift Keying (FSK) signal, and the Modulation type of the signal to be identified is not specifically limited herein. The signals to be identified of various modulation types are acquired, and the modulation type of the signals to be identified can be identified by applying the method for identifying the modulation type of the signals to be identified.
And 102, determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified.
Specifically, the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified are respectively determined according to the acquired signal to be identified, and the execution sequence of determining the time domain space convolution characteristic of the signal to be identified and determining the high-order cumulant characteristic of the signal to be identified is not specifically limited, and the two can be executed simultaneously or sequentially.
And 103, performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified.
Specifically, a time domain space convolution characteristic of a signal to be recognized and a high-order cumulant characteristic of the signal to be recognized are used as two parameters and input into a pre-trained fusion model, and data output by the fusion model is a characteristic obtained by fusing the time domain space convolution characteristic of the signal to be recognized and the high-order cumulant characteristic of the signal to be recognized, namely the fusion characteristic of the signal to be recognized. The training method of the fusion model is not particularly limited, and may be a linear weighted fusion method or a cross fusion method, and preferably a feature fusion method.
And 104, identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
Specifically, the fusion characteristics of the signal to be recognized are input into a pre-trained recognition model, data output by the recognition model are analyzed, a result is obtained, and the modulation type of the signal to be recognized is recognized.
As can be seen from the foregoing embodiments, in the method for identifying a signal modulation type provided by the present invention, a time-domain spatial convolution feature of the signal to be identified and a high-order cumulant feature of the signal to be identified are determined, and the time-domain spatial convolution feature and the high-order cumulant feature are subjected to fusion processing to obtain a fusion feature of the signal to be identified, and a modulation type of the signal to be identified is identified according to the fusion feature of the signal to be identified, so that a digital signal modulation type can be identified quickly and accurately.
Optionally, the acquiring the signal to be identified includes:
receiving a multipath fading radio frequency signal through multi-antenna diversity;
performing signal processing on the multipath fading radio frequency signals to obtain a plurality of complex baseband signals;
and performing energy normalization processing on the multiple complex baseband signals to obtain normalized complex baseband signals, wherein the normalized complex baseband signals are the signals to be identified.
Specifically, when a multi-antenna diversity reception multi-path fading radio frequency signal is received, the spacing between the antennas is constrained not to be too small, otherwise, the independence of signals received by the two antennas is affected, and further, the gain of diversity reception for modulation type identification is affected, and the constraint is as follows:
dant＞Δd
wherein d isantFor the antenna spacing, Δ d is preferably 10 times the wavelength of the electromagnetic wave in the current frequency band.
Processing the received multipath fading radio frequency signal to obtain a plurality of complex baseband signals, wherein the processing mode is one or more of the following modes:
processing a radio frequency part;
performing orthogonal down-conversion treatment;
hilbert transform processing;
an Analog-to-Digital (AD) sampling process;
and (5) performing decimation filtering processing.
Multiple complex baseband signals are represented as complex baseband received signals under multiple antenna diversity reception
Comprises the following steps:
wherein the matrix shape is Nrx×Nsample，NsampleRepresenting the number of sampling points of the received complex baseband signal, k representing the number of sampling points, NrxRepresenting the number of receive antennas, each receive a complex baseband signal,
represents NrxThe complex baseband signal of each of the receive antennas,
denotes the NthrxThe received symbol of the kth sampling point of each receive antenna,
denotes the NthrxThe real part of the received symbol of the kth sample of each receive antenna,
denotes the NthrxAn imaginary part of a received symbol of a k-th sampling point of the reception antennas.
Performing energy normalization processing on the multiple complex baseband signals to obtain normalized complex baseband signals, wherein the normalized complex baseband signals are the signals to be identified, and the normalized complex baseband signals are
Comprises the following steps:
wherein E isRRepresents NrxThe total energy of the complex baseband signal for each receive antenna,
denotes the NthrxThe complex baseband signal energy of each receive antenna,
comprises the following steps:
wherein,
denotes the NthrxThe real part of the received symbol of the kth sample point of the receive antennas,
denotes the NthrxAn imaginary part of a received symbol of a k-th sampling point of the reception antennas.
As can be seen from the above embodiments, a plurality of complex baseband signals are obtained by receiving multipath fading radio frequency signals through multi-antenna diversity and performing signal processing on the multipath fading radio frequency signals, and energy normalization processing is performed on the plurality of complex baseband signals to obtain normalized complex baseband signals, where the normalized complex baseband signals are the signals to be identified, so that noise for identifying the modulation type of the signals to be identified is reduced, and accuracy of identification is improved.
Optionally, the determining the time-domain spatial convolution characteristic of the signal to be identified includes:
setting the signal to be identified to obtain the time domain space convolution characteristic of the signal to be identified;
wherein the setting process includes one or more of:
zero padding operation;
performing convolution operation;
performing pooling operation;
flattening operation;
and (4) full connection operation.
In particular, the signal to be identified can be inputEntering a pre-trained deep learning convolution neural network model with the input scale of Nrx×2×NsampleThe time domain space convolution characteristics of the signal to be identified can be obtained through one or more of zero padding operation, convolution operation, pooling operation, flattening operation and full-connection operation:
wherein,
representing the time-domain spatial convolution characteristic of the signal to be identified, fCNN′Represents a deep learning convolutional neural network function,
representing the normalized complex baseband signal, W representing the parameters of convolution kernel in the deep learning convolution neural network model obtained by the deep learning training method, theta representing the hyper-parameter used in the training of the deep learning convolution neural network model, fL-1And expressing the L-1 th layer of convolution function of the deep learning convolution neural network model, wherein L is the layer number of the deep learning convolution neural network model.
According to the embodiment, the time domain and space convolution characteristics of the signal to be identified are obtained by performing one or more of zero filling operation, convolution operation, pooling operation, flattening operation and full connection operation on the signal to be identified, so that the noise of identification of the modulation type of the signal to be identified is reduced, and the identification accuracy is improved.
Optionally, the high-order cumulant feature of the signal to be identified comprises a high-order cumulant of a required order and/or a required conjugate parameter of the signal to be identified.
Specifically, the high-order cumulant feature of the signal to be identified includes a high-order cumulant of a required order and/or a required conjugate parameter of the signal to be identified, and is expressed as:
wherein,
representing the high-order cumulant characteristic of the signal to be identified, cum representing a high-order cumulant characteristic calculation function,
representing the normalized complex baseband signal.
According to the embodiment, the high-order cumulant characteristic of the signal to be identified comprises the high-order cumulant of the required order and/or the required conjugate parameter of the signal to be identified, so that the noise of the modulation type identification of the signal to be identified is reduced, and the identification accuracy is improved.
Optionally, the fusing the time-domain spatial convolution feature and the high-order cumulant feature includes:
determining a multi-dimensional fusion network model for fusion processing;
and inputting the time domain space convolution characteristic and the high-order cumulant characteristic into the multi-dimensional fusion network model, wherein the output result of the multi-dimensional fusion network model is the fusion characteristic of the signal to be identified.
Specifically, a multidimensional fusion network model for fusion processing is determined, the multidimensional fusion network model is pre-trained, the time domain space convolution feature and the high-order cumulant feature are input into the multidimensional fusion network model, and an output result of the multidimensional fusion network model is a fusion feature of the signal to be identified, and is represented as:
wherein,
fusion features representing a signal to be identified，
A fusion function representing the time-domain spatial convolution characteristic and the high-order cumulant characteristic,
representing the time-domain spatial convolution characteristics of the signal to be identified,
representing the high order cumulative quantity characteristic of the signal to be identified.
According to the embodiment, the fusion characteristics of the signal to be identified can be rapidly acquired according to the determined multidimensional fusion network model for fusion processing, and the efficiency of identifying the modulation type of the signal to be identified is improved.
Optionally, the identifying the modulation type of the signal to be identified according to the fusion feature of the signal to be identified includes:
determining a classification network model for identifying a modulation type of a signal;
and inputting the fusion characteristics of the signals to be identified into the classification network model, wherein the output result of the multi-classification network model is the modulation type of the signals to be identified.
Specifically, a classification network model for identifying the modulation type of the signal is determined, the classification network model is pre-trained, the fusion features of the signal to be identified are input into the classification network model, and the output result of the multi-classification network model is the modulation type of the signal to be identified, and is represented as:
wherein,
indicating the modulation type identification result, argmax indicating the maximum argument point set, fsoftmaxRepresenting fully-connected network functionsNumber, W represents the weight of each neuron in the classification network,
representing the fusion characteristic of the signal to be identified, b representing the bias.
According to the embodiment, the modulation type of the signal to be identified can be rapidly identified according to the determined classification network model for identifying the modulation type of the signal, and the efficiency of identifying the modulation type of the signal to be identified is improved.
Fig. 2 is a second flowchart of the method for identifying a signal modulation type according to the present invention, as shown in fig. 2:
(1) Multipath fading radio frequency signals are received through multi-antenna diversity.
(2) And preprocessing the received multipath fading radio frequency signal, wherein the preprocessed signal is the signal to be identified.
(3) Determining the time domain space convolution characteristics of the signal to be identified through setting processing; and determining the high-order cumulant characteristics of the signal to be identified through the high-order cumulant.
(4) And fusing the time domain space convolution characteristic of the signal to be recognized and the high-order cumulant characteristic of the signal to be recognized through a multi-dimensional fusion network model to obtain the fusion characteristic of the signal to be recognized.
(5) And obtaining the recognition result through the classification network model.
Fig. 3 is a comparison diagram of the recognition accuracy of the recognition method of the signal modulation type in a Rician channel, as shown in fig. 3, and compares the recognition accuracy with the performance of gain combination without using multi-antenna diversity reception technology (i.e. single receiving antenna), diversity reception, etc. and without using the high-order cumulant feature fusion method, respectively, through control variables.
The experimental results and comparison shown in fig. 3 illustrate the modulation recognition accuracy of the recognition method for signal modulation types provided by the present invention. After the multi-antenna diversity reception technology is used, the number of receiving antennas is increased from 1 to 4, and when an equal gain combining method is used, the modulation identification accuracy is remarkably improved in the whole range of the signal-to-noise ratio [ -20,18], and the identification rate can reach 69.77% when the signal-to-noise ratio is 18dB, and is improved by 4.25% compared with the identification rate. After the multidimensional fusion network model is fused, compared with an equal gain combination method, the identification effect in the range of signal-to-noise ratio (-4, 18) dB is improved, the identification rate is 71.53% respectively at the high signal-to-noise ratio of 18dB, the comparison is improved by 1.67%, the performance is improved the most at the signal-to-noise ratio of 0dB, and the identification rate is 69.89% respectively and is improved by 3.7%. After the multidimensional fusion network model provided by the invention is used, the overall recognition effect is improved by 1.21 percent on average, the recognition effect in the range of signal-to-noise ratio (-6, 18) dB is improved, the recognition rate is 72.66 percent respectively at the high signal-to-noise ratio of 18dB, the performance is improved by 1.13 percent compared with the recognition rate, the performance is improved most at the signal-to-noise ratio of 2dB, and the recognition rate is 72.55 percent respectively and is improved by 2.55 percent compared with the recognition rate. In conclusion, compared with a simple Convolutional Neural Network (CNN) method without feature fusion of a single receiving antenna, the identification method for the signal modulation type provided by the invention can improve the overall modulation identification accuracy rate by 7.05% under the condition of a high signal-to-noise ratio of 18dB, and the identification rate can reach 72.57%.
The following describes the identification apparatus of signal modulation type provided by the present invention, and the identification apparatus of signal modulation type described below and the identification method of signal modulation type described above can be referred to correspondingly.
Fig. 4 is a schematic structural diagram of an apparatus for identifying a signal modulation type according to the present invention, and as shown in fig. 4, the apparatus for identifying a signal modulation type according to the present invention includes:
an obtaining unit 401, configured to obtain a signal to be identified;
a determining unit 402, configured to determine a time-domain spatial convolution feature of the signal to be identified and a high-order cumulant feature of the signal to be identified;
a fusion unit 403, configured to perform fusion processing on the time domain space convolution feature and the high-order cumulant feature to obtain a fusion feature of the signal to be identified;
an identifying unit 404, configured to identify a modulation type of the signal to be identified according to the fusion feature of the signal to be identified.
Fig. 5 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 5, the electronic device may include: a processor (processor) 510, a communication Interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a method of identifying a type of signal modulation, the method comprising:
acquiring a signal to be identified;
determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified;
performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, when the computer program is executed by a processor, the computer can execute the method for identifying a signal modulation type provided by the above methods, the method includes:
acquiring a signal to be identified;
determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified;
performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which when executed by a processor, implements a method for identifying a type of signal modulation provided by the above methods, the method comprising:
acquiring a signal to be identified;
determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified;
performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for identifying a type of signal modulation, comprising:
acquiring a signal to be identified;
determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified; the determining the time domain space convolution characteristics of the signal to be identified includes: setting the signal to be identified to obtain the time domain space convolution characteristic of the signal to be identified; wherein the setting process includes one or more of: zero padding operation, convolution operation, pooling operation, flattening operation, and full join operation;
performing fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
2. The method for identifying a signal modulation type according to claim 1, wherein the acquiring a signal to be identified comprises:
receiving a multipath fading radio frequency signal through multi-antenna diversity;
performing signal processing on the multipath fading radio frequency signals to obtain a plurality of complex baseband signals;
and performing energy normalization processing on the multiple complex baseband signals to obtain normalized complex baseband signals, wherein the normalized complex baseband signals are the signals to be identified.
3. The method according to claim 1 or 2, wherein the high-order cumulant feature of the signal to be identified comprises a high-order cumulant of a required order and/or a required conjugate parameter of the signal to be identified.
4. The method for identifying the signal modulation type according to claim 1, wherein the fusing the time-domain spatial convolution feature and the high-order cumulant feature comprises:
determining a multi-dimensional fusion network model for fusion processing;
and inputting the time domain space convolution characteristic and the high-order cumulant characteristic to the multi-dimensional fusion network model, wherein the output result of the multi-dimensional fusion network model is the fusion characteristic of the signal to be identified.
5. The method for identifying the signal modulation type according to claim 1, wherein the identifying the modulation type of the signal to be identified according to the fused feature of the signal to be identified comprises:
determining a classification network model for identifying a modulation type of a signal;
and inputting the fusion characteristics of the signal to be recognized into the classification network model, wherein the output result of the classification network model is the modulation type of the signal to be recognized.
6. An apparatus for identifying a type of signal modulation, comprising:
an acquisition unit for acquiring a signal to be identified;
the determining unit is used for determining the time domain space convolution characteristic of the signal to be identified and the high-order cumulant characteristic of the signal to be identified; determining the time domain and space convolution characteristics of the signal to be identified comprises the following steps: setting the signal to be identified to obtain the time domain space convolution characteristic of the signal to be identified; wherein the setting process includes one or more of: zero padding operation, convolution operation, pooling operation, flattening operation, and full join operation;
the fusion unit is used for carrying out fusion processing on the time domain space convolution characteristic and the high-order cumulant characteristic to obtain a fusion characteristic of the signal to be identified;
and the identification unit is used for identifying the modulation type of the signal to be identified according to the fusion characteristic of the signal to be identified.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method for identifying a type of signal modulation according to any one of claims 1 to 5 are implemented when the program is executed by the processor.
8. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for identifying a type of signal modulation according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111101685.5A CN113904902B (en) | 2021-09-18 | 2021-09-18 | Method and device for identifying signal modulation type |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111101685.5A CN113904902B (en) | 2021-09-18 | 2021-09-18 | Method and device for identifying signal modulation type |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113904902A CN113904902A (en) | 2022-01-07 |
| CN113904902B true CN113904902B (en) | 2022-11-01 |
Family
ID=79028823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111101685.5A Active CN113904902B (en) | 2021-09-18 | 2021-09-18 | Method and device for identifying signal modulation type |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113904902B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114760174B (en) * | 2022-06-14 | 2022-09-13 | 北京邮电大学 | Modulation recognition method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111049770A (en) * | 2019-12-06 | 2020-04-21 | 西安电子科技大学 | Modulation signal identification method based on high-order cumulant |
| CN111314257A (en) * | 2020-03-13 | 2020-06-19 | 电子科技大学 | Modulation mode identification method based on complex value neural network |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017087616A1 (en) * | 2015-11-18 | 2017-05-26 | Kyocera Corporation | Partial decode and forward (pdf) signal forwarding device with scheduler |
| CN109787926A (en) * | 2018-12-24 | 2019-05-21 | 合肥工业大学 | A kind of digital signal modulation mode recognition methods |
| CN111343115B (en) * | 2020-02-19 | 2021-06-29 | 北京邮电大学 | 5G communication modulation signal identification method and system |
| CN113014523B (en) * | 2021-02-25 | 2022-01-11 | 电子科技大学 | Composite modulation signal blind identification method based on fusion characteristics |
-
2021
- 2021-09-18 CN CN202111101685.5A patent/CN113904902B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111049770A (en) * | 2019-12-06 | 2020-04-21 | 西安电子科技大学 | Modulation signal identification method based on high-order cumulant |
| CN111314257A (en) * | 2020-03-13 | 2020-06-19 | 电子科技大学 | Modulation mode identification method based on complex value neural network |
Non-Patent Citations (3)
| Title |
|---|
| Automatic Modulation Classification Using a Deep Multi-Stream Neural Network;Hao Zhang et.al;《IEEE Access》;20200207;第8卷;全文 * |
| 基于高阶累积量和DNN模型的井下信号识别方法;王安义等;《工矿自动化》(第02期);全文 * |
| 基于高阶累积量实现数字调相信号调制识别;孙钢灿等;《电波科学学报》;20120815(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113904902A (en) | 2022-01-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114201988B (en) | Satellite navigation composite interference signal identification method and system | |
| US11477060B2 (en) | Systems and methods for modulation classification of baseband signals using attention-based learned filters | |
| CN104994045B (en) | A kind of digital modulation mode automatic identification platform and method based on USRP platforms | |
| CN110163282A (en) | Modulation Mode Recognition method based on deep learning | |
| CN109274625B (en) | Information modulation mode determining method and device, electronic equipment and storage medium | |
| US11700156B1 (en) | Intelligent data and knowledge-driven method for modulation recognition | |
| CN116866129A (en) | Wireless communication signal detection method | |
| US20220014401A1 (en) | Fast modulation recognition method for multilayer perceptron based on multimodally-distributed test data fusion | |
| CN113904902B (en) | Method and device for identifying signal modulation type | |
| CN114980122A (en) | Small sample radio frequency fingerprint intelligent identification system and method | |
| CN108197581A (en) | A kind of unmanned plane signal identification detection algorithm based on improvement AC-WGANs | |
| CN114268388A (en) | Channel estimation method based on improved GAN network in large-scale MIMO | |
| CN113378644A (en) | Signal modulation type recognition attack defense method based on generative countermeasure network | |
| CN110826425A (en) | VHF/UHF frequency band radio signal modulation mode identification method based on deep neural network | |
| Feng et al. | FCGCN: Feature Correlation Graph Convolution Network for Few-Shot Individual Identification | |
| Omondi et al. | Variational autoencoder-enhanced deep neural network-based detection for MIMO systems | |
| CN112350790A (en) | Deep learning-based spectrum sensing detection method, device and equipment | |
| CN111343115A (en) | 5G communication modulation signal identification method and system | |
| CN114006798B (en) | Signal processing method and device, electronic equipment and storage medium | |
| CN110516566B (en) | Filtering method and device based on convolutional layer | |
| CN109740692A (en) | A kind of target classifying method of the logistic regression based on principal component analysis | |
| CN114818785A (en) | Signal modulation mode identification method based on multi-model fusion | |
| Gu et al. | Deep complex-valued convolutional neural network for drone recognition based on RF fingerprinting | |
| Jiyuan et al. | Multi-modulation recognition using convolution gated recurrent unit networks | |
| CN111917674A (en) | Modulation identification method based on deep learning |
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 |