CN110798419A - Modulation mode identification method and device - Google Patents
Modulation mode identification method and device Download PDFInfo
- Publication number
- CN110798419A CN110798419A CN201911028838.0A CN201911028838A CN110798419A CN 110798419 A CN110798419 A CN 110798419A CN 201911028838 A CN201911028838 A CN 201911028838A CN 110798419 A CN110798419 A CN 110798419A
- Authority
- CN
- China
- Prior art keywords
- signal
- cyclic
- identified
- spectrogram
- frequency band
- 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.)
- Withdrawn
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Digital Transmission Methods That Use Modulated Carrier Waves (AREA)
Abstract
The embodiment of the application provides a modulation mode identification method and a modulation mode identification device, which relate to the technical field of radio communication, and the method comprises the following steps: the electronic equipment can receive the signal to be recognized, determine a cyclic spectrogram of the signal to be recognized as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be recognized, and then input the target cyclic spectrogram into a pre-trained modulation mode recognition model to obtain a modulation mode of the signal to be recognized. By adopting the method and the device, the cycle spectrogram of the signal to be identified can be completely input into the modulation mode identification model to identify the modulation mode of the signal to be identified, namely, the modulation mode of the signal to be identified is identified by utilizing all the characteristics of the cycle spectrogram of the signal to be identified, but not the modulation mode of the signal to be identified is identified by utilizing partial characteristics of the cycle spectrogram, so that the accuracy of the identification of the modulation mode of the signal is improved.
Description
Technical Field
The present application relates to the field of radio communications technologies, and in particular, to a modulation scheme identification method and apparatus.
Background
In a non-cooperative mode, that is, in a case where a modulation scheme of a signal is to be identified, a modulation scheme identification technique of a signal (particularly, a weak signal) has important applications in many fields. The purpose of the signal modulation scheme identification technology is to identify the modulation scheme of a received signal in the absence of transmitting end and channel information. The existing method for identifying the modulation mode of the signal mainly comprises the following steps: calculating a cyclic spectrum of the signal to be identified to obtain a cyclic spectrum of the signal to be identified, extracting partial peak positions of the cyclic spectrum of the signal to be identified and/or partial features of the cyclic spectrum, such as cross section information at the peak position of the cyclic spectrum of the signal to be identified, and identifying the modulation mode of the signal to be identified by using the partial features of the cyclic spectrum.
However, if the modulation scheme of the signal to be identified is identified by using the above-mentioned modulation scheme identification method of the signal, only part of the features of the cyclic spectrogram are utilized in the identification. This makes the modulation scheme identification accuracy of the signal low.
Disclosure of Invention
An object of the embodiments of the present application is to provide a modulation scheme identification method and apparatus, so as to improve the accuracy of the modulation scheme identification of a signal. The specific technical scheme is as follows:
in a first aspect, to achieve the above object, an embodiment of the present application provides a modulation scheme identifying method, where the method includes:
receiving a signal to be identified;
determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified;
and inputting the target cycle spectrogram into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified, wherein the modulation mode identification model is obtained by training a deep neural network by using sample data, and the sample data comprises a plurality of sample signals and a labeled modulation mode of each sample signal.
Optionally, the step of determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified includes:
moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified;
determining a cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal;
and overlapping the cycle spectrograms corresponding to the multiple frequency bands to obtain the cycle spectrogram of the signal to be identified as a target cycle spectrogram.
Optionally, the step of moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified includes:
carrying out segmentation processing on the signals to be identified to obtain a plurality of sub-signals to be identified;
moving the frequency spectrum of each sub-signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band sub-signals corresponding to the sub-signal to be identified; the frequency band sub-signals corresponding to the sub-signals to be identified on one frequency band are frequency band signals corresponding to the signals to be identified on the frequency band;
the step of determining the cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal includes:
determining a cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal;
and aiming at each frequency band, carrying out averaging processing on the cyclic spectrograms of the frequency band sub-signals on the frequency band to obtain the cyclic spectrogram of the frequency band signal on the frequency band.
Optionally, the step of determining a cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal includes:
performing fast Fourier transform on each frequency band sub-signal to obtain a transform sub-signal corresponding to each frequency band sub-signal;
and determining a cyclic spectrogram of each transformed sub-signal according to each frequency component and each cyclic frequency component of each transformed sub-signal, and taking the cyclic spectrogram of the frequency band sub-signal corresponding to each transformed sub-signal.
Optionally, the step of determining a cyclic spectrogram of each transformed sub-signal according to each frequency component and each cyclic frequency component of each transformed sub-signal, as the cyclic spectrogram of the frequency band sub-signal corresponding to each transformed sub-signal, includes:
determining a cyclic spectrogram of each transformed sub-signal as a cyclic spectrogram of a frequency band sub-signal corresponding to each transformed sub-signal by using the following formula:
wherein the content of the first and second substances,
a cyclic spectrum, N, representing the kth transformed subsignal0Denotes the signal length of the k-th transform sub-signal, f denotes the frequency component, α denotes the cyclic frequency component,
expressed at a frequency of
The k-th transformed sub-signal of (k-th),
to represent
The conjugate, |, represents the modulo value calculation.
Optionally, the step of performing superposition processing on the cycle spectrograms corresponding to the multiple frequency bands to obtain the cycle spectrogram of the signal to be identified, as a target cycle spectrogram, includes:
and overlapping the cyclic spectrograms corresponding to the multiple frequency bands by using the following formula to obtain the cyclic spectrogram of the signal to be identified as a target cyclic spectrogram:
|S′r(f,α)|＝max{|Sr,1(f,α)|,|Sr,2(f,α)|,…,|Sr,n(f,α)|}；
wherein, | S'r(f, α) | denotes a cyclic spectrum of the signal to be recognized, | Sr,1(f, α) | represents the circulation spectrogram corresponding to the 1 st frequency band, | Sr,2(f, α) | represents the cycle spectrogram corresponding to the 2 nd frequency band, | Sr,n(f, α) | represents the circulation spectrogram corresponding to the nth frequency band, max represents the maximum value, n represents the number of the frequency bands, f represents the frequency component, α represents the circulation frequency component, and | · | represents the modulus calculation.
Optionally, the modulation mode recognition model is obtained by training in the following way:
acquiring the sample data, wherein the sample data comprises a plurality of sample signals and a label modulation mode of each sample signal;
determining a cyclic spectrogram of each sample signal according to each frequency component and each cyclic frequency component of each sample signal;
inputting the cyclic spectrogram of each sample signal into a preset deep neural network to obtain a predicted modulation mode of each sample signal;
determining a loss value identified by a modulation mode according to the predicted modulation mode and the labeled modulation mode of each sample signal;
determining whether the deep neural network converges according to the loss value;
if not, adjusting the parameters of the deep neural network, and returning to the step of inputting the cycle spectrogram of each sample signal into a preset deep neural network to obtain the predicted modulation mode of each sample signal;
if so, determining that the current deep neural network is a modulation mode identification model.
In a second aspect, to achieve the above object, an embodiment of the present application provides a modulation scheme identifying apparatus, including:
the receiving module is used for receiving a signal to be identified;
the determining module is used for determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified;
and the identification module is used for inputting the target cycle spectrogram into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified, wherein the modulation mode identification model is obtained by training the deep neural network by using sample data, and the sample data comprises a plurality of sample signals and a labeled modulation mode of each sample signal.
Optionally, the determining module includes:
the moving sub-module is used for moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified;
the first determining submodule is used for determining a cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal;
and the superposition submodule is used for carrying out superposition processing on the cycle spectrograms corresponding to the multiple frequency bands to obtain the cycle spectrogram of the signal to be identified as a target cycle spectrogram.
Optionally, the moving sub-module is specifically configured to: carrying out segmentation processing on the signals to be identified to obtain a plurality of sub-signals to be identified; moving the frequency spectrum of each sub-signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band sub-signals corresponding to the sub-signal to be identified; the frequency band sub-signals corresponding to the sub-signals to be identified on one frequency band are frequency band signals corresponding to the signals to be identified on the frequency band;
the first determining submodule is specifically configured to: determining a cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal; and aiming at each frequency band, carrying out averaging processing on the cyclic spectrograms of the frequency band sub-signals on the frequency band to obtain the cyclic spectrogram of the frequency band signal on the frequency band.
Optionally, the first determining submodule is specifically configured to:
performing fast Fourier transform on each frequency band sub-signal to obtain a transform sub-signal corresponding to each frequency band sub-signal;
and determining a cyclic spectrogram of each transformed sub-signal according to each frequency component and each cyclic frequency component of each transformed sub-signal, and taking the cyclic spectrogram of the frequency band sub-signal corresponding to each transformed sub-signal.
Optionally, the first determining submodule is specifically configured to:
determining a cyclic spectrogram of each transformed sub-signal as a cyclic spectrogram of a frequency band sub-signal corresponding to each transformed sub-signal by using the following formula:
wherein the content of the first and second substances,
a cyclic spectrum, N, representing the kth transformed subsignal0Denotes the signal length of the k-th transform sub-signal, f denotes the frequency component, α denotes the cyclic frequency component,
expressed at a frequency ofThe k-th transformed sub-signal of (k-th),to representThe conjugate, |, represents the modulo value calculation.
Optionally, the superposition sub-module is specifically configured to:
and overlapping the cyclic spectrograms corresponding to the multiple frequency bands by using the following formula to obtain the cyclic spectrogram of the signal to be identified as a target cyclic spectrogram:
|S′r(f,α)|＝max{|Sr,1(f,α)|,|Sr,2(f,α)|,…,|Sr,n(f,α)|}；
wherein, | S'r(f, α) | denotes a cyclic spectrum of the signal to be recognized, | Sr,1(f, α) | represents the circulation spectrogram corresponding to the 1 st frequency band, | Sr,2(f, α) | represents the cycle spectrogram corresponding to the 2 nd frequency band, | Sr,n(f, α) | represents the circulation spectrogram corresponding to the nth frequency band, max represents the maximum value, n represents the number of the frequency bands, f represents the frequency component, α represents the circulation frequency component, and | · | represents the modulus calculation.
Optionally, the apparatus further comprises: the training module is used for training to obtain the modulation mode identification model;
the training module comprises:
the obtaining submodule is used for obtaining the sample data, and the sample data comprises a plurality of sample signals and a label modulation mode of each sample signal;
the second determining submodule is used for determining a cyclic spectrogram of each sample signal according to each frequency component and each cyclic frequency component of each sample signal;
the prediction sub-module is used for inputting the cyclic spectrogram of each sample signal into a preset deep neural network to obtain a prediction modulation mode of each sample signal;
a third determining submodule, configured to determine a loss value identified by a modulation mode according to the predicted modulation mode and the labeled modulation mode of each sample signal;
a fourth determining submodule, configured to determine whether the deep neural network converges according to the loss value; if not, adjusting the parameters of the deep neural network, and returning to the step of inputting the cycle spectrogram of each sample signal into a preset deep neural network to obtain the predicted modulation mode of each sample signal; if so, determining that the current deep neural network is a modulation mode identification model.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
a processor adapted to perform any of the method steps of the first aspect when executing a program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, having stored thereon a computer program which, when being executed by a processor, carries out any of the method steps of the first aspect.
In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the first aspect described above.
In the signal identification method and device provided by the embodiment of the application, the electronic device completely inputs the cycle spectrogram of the signal to be identified into the modulation mode identification model to identify the modulation mode of the signal to be identified, that is, the modulation mode of the signal to be identified is identified by using all the characteristics of the cycle spectrogram of the signal to be identified, rather than the modulation mode of the signal to be identified by using part of the characteristics of the cycle spectrogram, so that the accuracy of the identification of the modulation mode of the signal is improved.
Of course, not all advantages described above need to be achieved at the same time in the practice of any one product or method of the present application.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a modulation scheme identification method according to an embodiment of the present disclosure;
fig. 2 is another flowchart of a method for identifying a modulation scheme according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of increasing a center frequency point according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of center frequency point reduction according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram of an averaging process provided in an embodiment of the present application;
fig. 6 is a schematic diagram of a picture stacking process according to an embodiment of the present application;
FIG. 7 is a flowchart of deep neural network training provided by an embodiment of the present application;
fig. 8 is a schematic structural diagram of a deep neural network according to an embodiment of the present disclosure;
fig. 9 is a third flowchart of a method for identifying a modulation scheme according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of an apparatus for identifying a modulation scheme according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. 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 application.
A modulation scheme identifying method provided in an embodiment of the present application will be described in detail below with reference to specific embodiments, as shown in fig. 1, the specific steps are as follows:
step 101, receiving a signal to be identified.
In the embodiment of the application, when the modulation mode is identified, the electronic device may receive a signal with an unknown modulation mode as a signal to be identified.
And 102, determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified.
In the embodiment of the application, after receiving the signal to be identified, the electronic device may determine the cyclic spectrogram of the signal to be identified according to each frequency component and each cyclic frequency component of the signal to be identified.
And 103, inputting the target cyclic spectrogram into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified.
The modulation mode identification model is obtained by training the deep neural network by using sample data, and the sample data comprises a plurality of sample signals and a labeled modulation mode of each sample signal.
In this embodiment, the electronic device may input the target cyclic spectrogram obtained by the method into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified, where the modulation mode identification model is obtained by training the deep neural network using sample data, and the sample data may include a plurality of sample signals and a label modulation mode of each sample signal.
In one embodiment, the electronic device may first shift the frequency spectrum of the received signal to be identified to a plurality of preset frequency bands. Specifically referring to fig. 2, fig. 2 is a flowchart of another method of a modulation scheme identification method provided in the embodiment of the present application, where the method may include the following steps:
step 201, receiving a signal to be identified. Step 201 corresponds to step 101.
Step 202, moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified.
In the embodiment of the application, the electronic device can move the frequency spectrum of the received signal to be identified to a plurality of preset frequency bands, namely, the central frequency point f of the signal to be identified is changedcObtaining the information to be identifiedA plurality of frequency band signals corresponding to the number.
In an embodiment, in step 202, the electronic device may directly move the frequency spectrum of the signal to be identified to a plurality of preset frequency bands, so as to obtain a plurality of frequency band signals corresponding to the signal to be identified.
In another embodiment, the electronic device may obtain a plurality of frequency band signals corresponding to the signal to be identified by the following steps. Specifically, in step 202, the frequency spectrum of the signal to be identified is moved to a plurality of preset frequency bands, so as to obtain a plurality of frequency band signals corresponding to the signal to be identified, which may include:
after receiving the signal to be identified, the electronic device may perform segmentation processing on the signal to be identified to obtain a plurality of sub-signals to be identified. For each sub-signal to be identified, the electronic device moves the frequency spectrum of the sub-signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band sub-signals corresponding to the sub-signal to be identified, wherein the plurality of frequency band signals corresponding to the plurality of sub-signals to be identified on one frequency band are the frequency band signals corresponding to the signals to be identified on the frequency band.
Step 203, determining a cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal.
In this embodiment, the electronic device may determine a cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal.
In one embodiment, the electronic device directly moves the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified, and for each frequency band, the electronic device determines a cyclic spectrogram of the frequency band signal according to each frequency component and each cyclic frequency component of the frequency band signal on the frequency band.
In another embodiment, the electronic device obtains a plurality of frequency band sub-signals for each frequency band. The electronic device may determine a cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal. The signals shifted to different frequency bands correspond to a cyclic spectrogramAnd not the same. When the center frequency point fcWhen the change is made, the cycle spectrum of the product is also changed. As shown in fig. 3, when the center frequency f iscWhen the peak distance is increased, the distance between the peaks of the corresponding cycle spectrogram is also increased; on the contrary, as shown in FIG. 4, when the center frequency point fcAs this decreases, the distance between the peaks of their corresponding cycle profiles also decreases. For each frequency band, the electronic device may perform an averaging process on the cyclic spectrograms of the multiple frequency band sub-signals on the frequency band to obtain the cyclic spectrogram of the frequency band signal on the frequency band.
In an embodiment, the step of determining the cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal may include:
the electronic device may perform fast fourier transform on each frequency band sub-signal to obtain a transform sub-signal corresponding to each frequency band sub-signal, and then, the electronic device may determine a cyclic spectrogram of each transform sub-signal according to each frequency component and each cyclic frequency component of each transform sub-signal, and use the cyclic spectrogram as a cyclic spectrogram of a frequency band sub-signal corresponding to each transform sub-signal.
In one embodiment, the electronic device may determine a cyclic spectrogram of each transformed sub-signal as a cyclic spectrogram of a frequency band sub-signal corresponding to each transformed sub-signal by using the following formula:
wherein the content of the first and second substances,
can represent a cyclic spectrum of the k-th transformed sub-signal, N0May represent the signal length of the kth transform sub-signal, f may represent the frequency component, α may represent the cyclic frequency component,
can be expressed at a frequency of
The k-th transformed sub-signal of (k-th),
can representThe conjugate, |, may represent a modulo value calculation.
In an embodiment, for each frequency band, the cyclic spectrogram of the frequency band sub-signals on the frequency band may be obtained by averaging the cyclic spectrogram of the frequency band sub-signals on the frequency band by the following formula:
wherein, | Sr,l(f, α) | denotes a cyclic spectrum of the frequency band signal in the l-th frequency band, NlRepresents the total number of the cycle spectrogram, i.e. the number of frequency band sub-signals on the l-th frequency band, n represents the n-th frequency band sub-signal, l represents the l-th frequency band, | Sr,l,n(f, α) | represents the cyclic spectrogram corresponding to the nth frequency band sub-signal on the ith frequency band, f represents the frequency component, α represents the cyclic frequency component, |, may represent a modulo value calculation.
As shown in FIG. 5, the first, second and third frequency bands are shown as 1 st, 2 nd and NthlA cycle spectrum obtained by dividing the above-mentioned NlThe average value of each cyclic spectrogram is calculated to obtain the average value shown below in fig. 5, and based on this, the electronic device calculates the average value of the cyclic spectrograms of the frequency band sub-signals on each frequency band, so that the number of burrs caused by noise in the cyclic spectrograms can be reduced as much as possible, and the influence of noise interference is reduced.
And 204, overlapping the cycle spectrograms corresponding to the multiple frequency bands to obtain a cycle spectrogram of the signal to be identified as a target cycle spectrogram.
In an embodiment of the application, the electronic device may perform superposition processing on the cycle spectrograms corresponding to the multiple frequency bands by using the following formula to obtain a cycle spectrogram of a signal to be identified, which is used as a target cycle spectrogram:
|S′r(f,α)|＝max{|Sr,1(f,α)|,|Sr,2(f,α)|,…,|Sr,n(f,α)|}；
wherein, | S'r(f, α) | may represent a cyclic spectrum, | S, of the signal to be recognizedr,1(f, α) | may represent a cyclic spectrum corresponding to the 1 st frequency band, | Sr,2(f, α) | may represent a cyclic spectrum corresponding to the 2 nd frequency band, | Sr,nBased on the above, the electronic device may superimpose the cyclic spectrograms corresponding to the multiple frequency bands, that is, the electronic device may perform processing of calculating the maximum value on the cyclic spectrogram subjected to averaging processing on each frequency band, so that the number of peaks of the cyclic spectrogram is increased, and the accuracy of identification of the modulation mode is improved.
As shown in fig. 6, the figure includes a central frequency point f of the signal to be identifiedcMoved to 0.1fcA cyclic spectrogram and a central frequency point f of a signal to be identifiedcMoved to 0.3fcA cyclic spectrogram and a central frequency point f of a signal to be identifiedcMoved to 1.5fcAnd (4) overlapping the cyclic spectrograms corresponding to the different frequency bands to obtain a cyclic spectrogram obtained by overlapping the pictures shown below the graph in fig. 6, namely the target cyclic spectrogram.
And step 205, inputting the target cyclic spectrogram into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified. Step 205 corresponds to step 103.
In an embodiment, the electronic device may obtain the modulation scheme recognition model through the following method steps, specifically referring to fig. 7:
In this embodiment, the electronic device may obtain sample data, where the sample data may include a plurality of sample signals and a modulation scheme labeled for each sample signal, where the modulation schemes of the plurality of sample signals are known, that is, the modulation scheme labeled for example, a is quadrature amplitude modulation, and b is key shift modulation.
In this embodiment, after acquiring a plurality of sample signals, the electronic device may determine a cyclic spectrogram of each sample signal according to each frequency component and each cyclic frequency component of each sample signal. The frequency component and the cyclic frequency component of each sample signal can be arbitrarily chosen within a certain value range, for example, the frequency value range is 100 hz to 1000 mhz, and the cyclic frequency value range is 2000 hz to 10000 hz.
In the embodiment of the application, after determining the cyclic spectrogram of each sample signal, the electronic device may input the cyclic spectrogram into a preset deep neural network to obtain a predicted modulation mode of each sample signal, where the deep neural network may select ResNet 50.
In an alternative embodiment, the deep neural network may be ResNet50, which introduces the concept of residual error, and avoids the phenomena of gradient diffusion and gradient disappearance that often occur in the deep neural network during the training phase, and its structural diagram specifically refers to fig. 8, where the ResNet50 shown in the diagram may include 1 input layer, (3+4+6+3) × 3 hidden layers and one output layer, totaling 50 layers. In addition, the deep neural network can be built in a Pytorch, wherein the Pytorch is a free open source deep neural network framework.
In the embodiment of the present application, a cross entropy function (CE) may be specifically used as a loss function to obtain a loss value JCE(Φ), see the following equation:
wherein c can be expressed as the c modulation mode, l can be expressed as the cycle spectrogram corresponding to the l sample signal,
can take the value of 0 or 1, phi can be expressed as the parameter of a deep neural network, OclCan be represented as the output of a deep neural network.
Specifically, convergence may be determined when the loss value is less than a preset loss value threshold; or when the difference between the loss value obtained by the current calculation and the loss value obtained by the last calculation is smaller than a preset change threshold, determining convergence, which is not limited herein in this embodiment of the application.
And step 707, determining that the current deep neural network is a modulation mode identification model.
In the embodiment of the application, the electronic device for training the modulation mode recognition model and the electronic device for recognizing the modulation mode may be located on the same physical machine, or may be located on different physical machines. This is not particularly limited.
In the embodiment of the present application, the modulation mode identification model obtained by the training in the above steps 701-707 can accurately identify the modulation mode, and the accuracy of the modulation mode identification is improved.
The following describes the modulation scheme identification method provided in the embodiment of the present invention in detail with reference to the flowchart of the modulation scheme identification method shown in fig. 9.
A training stage:
the electronic equipment acquires a received signal in the cooperation mode, and performs processing such as spectrum shifting, cyclic spectrum calculation, smoothing, image superposition and the like on the received signal to obtain a cyclic spectrogram of the received signal. The spectrum moving operation is a preparation operation for overlaying the picture. The electronic equipment inputs the cyclic spectrogram of the received signal into a preset depth neural network, trains to obtain a modulation mode recognition model, and fixes the neural network parameters of the neural network with the preset depth in the modulation mode recognition model. The processing of moving the frequency spectrum, calculating the cyclic spectrum, superposing the pictures and the like is consistent with the corresponding processing description, and the smoothing is the processing of obtaining the average value.
And (3) identification:
the electronic equipment acquires a signal to be recognized, performs processing such as frequency spectrum shifting, cyclic spectrum calculation, smoothing, picture superposition and the like on the signal to be recognized to obtain a cyclic spectrogram of the signal to be recognized, inputs the cyclic spectrogram of the signal to be recognized into a modulation mode recognition model obtained through training, and recognizes to obtain a modulation mode of the signal to be recognized. The processing of moving the frequency spectrum, calculating the cyclic spectrum, superposing the pictures and the like is consistent with the corresponding processing description, and the smoothing is the processing of obtaining the average value.
The description of the section of fig. 9 is relatively simple and reference may be made in particular to the description of fig. 1 to 8 above.
In the signal identification method provided by the embodiment of the application, the electronic device completely inputs the cycle spectrogram of the signal to be identified into the modulation mode identification model to identify the modulation mode of the signal to be identified, that is, the modulation mode of the signal to be identified is identified by using all the characteristics of the cycle spectrogram of the signal to be identified, rather than the modulation mode of the signal to be identified by using part of the characteristics of the cycle spectrogram, so that the accuracy of the identification of the modulation mode of the signal is improved.
Based on the same technical concept, an embodiment of the present application further provides a modulation scheme identifying apparatus, as shown in fig. 10, the apparatus includes:
a receiving module 1001, configured to receive a signal to be identified;
a determining module 1002, configured to determine, according to each frequency component and each cyclic frequency component of the signal to be identified, a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram;
the identification module 1003 is configured to input the target cyclic spectrogram into a pre-trained modulation scheme identification model to obtain a modulation scheme of the signal to be identified, where the modulation scheme identification model is obtained by training the deep neural network using sample data, and the sample data includes a plurality of sample signals and a labeled modulation scheme of each sample signal.
Optionally, the determining module 1002 may include:
the moving sub-module is used for moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified;
the first determining submodule is used for determining a cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal;
and the superposition submodule is used for carrying out superposition processing on the cycle spectrograms corresponding to the multiple frequency bands to obtain the cycle spectrogram of the signal to be identified as a target cycle spectrogram.
Optionally, the moving sub-module may be specifically configured to: carrying out segmentation processing on the signals to be identified to obtain a plurality of sub-signals to be identified; moving the frequency spectrum of each sub-signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band sub-signals corresponding to the sub-signal to be identified; the frequency band signals corresponding to the sub-signals to be identified on one frequency band are frequency band signals corresponding to the signals to be identified on the frequency band;
the first determining submodule may be specifically configured to: determining a cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal; and aiming at each frequency band, carrying out averaging processing on the cyclic spectrograms of the sub-signals of the frequency bands to obtain the cyclic spectrogram corresponding to the frequency band.
Optionally, the first determining submodule may be specifically configured to:
performing fast Fourier transform on each frequency band sub-signal to obtain a transform sub-signal corresponding to each frequency band sub-signal;
and determining a cyclic spectrogram of each transformed sub-signal according to each frequency component and each cyclic frequency component of each transformed sub-signal, and taking the cyclic spectrogram of the frequency band sub-signal corresponding to each transformed sub-signal.
Optionally, the first determining submodule may be specifically configured to:
determining a cyclic spectrogram of each transformed sub-signal as a cyclic spectrogram of a frequency band sub-signal corresponding to each transformed sub-signal by using the following formula:
wherein the content of the first and second substances,
a cyclic spectrum, N, representing the kth transformed subsignal0Denotes the signal length of the k-th transform sub-signal, f denotes the frequency component, α denotes the cyclic frequency component,
expressed at a frequency of
The k-th transformed sub-signal of (k-th),to represent
The conjugate, |, may represent a modulo value calculation.
Optionally, the overlay sub-module may be specifically configured to:
superposing the cyclic spectrograms corresponding to the multiple frequency bands by using the following formula to obtain a cyclic spectrogram of a signal to be identified as a target cyclic spectrogram:
|S′r(f,α)|＝max{|Sr,1(f,α)|,|Sr,2(f,α)|,…,|Sr,n(f,α)|}；
wherein, | S'r(f, α) | denotes a cyclic spectrum of the signal to be recognized, | Sr,1(f, α) | represents the circulation spectrogram corresponding to the 1 st frequency band, | Sr,2(f, α) | represents the cycle spectrogram corresponding to the 2 nd frequency band, | Sr,n(f, α) | represents the cyclic spectrogram corresponding to the nth frequency band, max represents the maximum value, n represents the number of the plurality of frequency bands, f represents the frequency component, α represents the cyclic frequency component, |, may represent the modulus calculation.
Optionally, the apparatus may further include: the training module is used for training to obtain a modulation mode identification model;
the training module may include:
the acquisition submodule is used for acquiring sample data, and the sample data comprises a plurality of sample signals and a labeled modulation mode of each sample signal;
the second determining submodule is used for determining a cyclic spectrogram of each sample signal according to each frequency component and each cyclic frequency component of each sample signal;
the prediction sub-module is used for inputting the cyclic spectrogram of each sample signal into a preset deep neural network to obtain a prediction modulation mode of each sample signal;
the third determining submodule is used for determining a loss value identified by the modulation mode according to the predicted modulation mode and the labeled modulation mode of each sample signal;
a fourth determining submodule, configured to determine whether the deep neural network converges according to the loss value; if not, adjusting parameters of the deep neural network, returning to the step of inputting the cyclic spectrogram of each sample signal into the preset deep neural network to obtain the predicted modulation mode of each sample signal; if so, determining that the current deep neural network is a modulation mode identification model.
In the signal identification device provided by the embodiment of the application, the electronic equipment completely inputs the cycle spectrogram of the signal to be identified into the modulation mode identification model to identify the modulation mode of the signal to be identified, that is, the modulation mode of the signal to be identified is identified by using all the characteristics of the cycle spectrogram of the signal to be identified, rather than the modulation mode of the signal to be identified by using part of the characteristics of the cycle spectrogram, so that the accuracy of the identification of the modulation mode of the signal is improved.
The embodiment of the present application further provides an electronic device, as shown in fig. 11, including a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104, where the processor 1101, the communication interface 1102 and the memory 1103 complete mutual communication through the communication bus 1104,
a memory 1103 for storing a computer program;
the processor 1101 is configured to implement the method steps in any of the modulation scheme identifying method embodiments described above when executing the program stored in the memory 1103.
In the electronic device provided by the embodiment of the application, the electronic device completely inputs the cycle spectrogram of the signal to be recognized into the modulation mode recognition model to recognize the modulation mode of the signal to be recognized, that is, the modulation mode of the signal to be recognized is recognized by using all the characteristics of the cycle spectrogram of the signal to be recognized, rather than the modulation mode of the signal to be recognized by using part of the characteristics of the cycle spectrogram, so that the accuracy of recognition of the modulation mode of the signal is improved.
The communication bus mentioned in the network device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the network device and other devices.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other Programmable logic devices, discrete Gate or transistor logic devices, or discrete hardware components.
Based on the same technical concept, the embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the modulation scheme identification method.
Based on the same technical concept, embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, causes the computer to perform the steps of the modulation scheme identification method.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus, electronic device, and computer-readable storage medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference may be made to some descriptions of the method embodiments for relevant points.
The above description is only for the preferred embodiment of the present application, and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application are included in the protection scope of the present application.
Claims (10)
1. A modulation scheme identification method is characterized by comprising the following steps:
receiving a signal to be identified;
determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified;
and inputting the target cycle spectrogram into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified, wherein the modulation mode identification model is obtained by training a deep neural network by using sample data, and the sample data comprises a plurality of sample signals and a labeled modulation mode of each sample signal.
2. The method according to claim 1, wherein the step of determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified comprises:
moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified;
determining a cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal;
and overlapping the cycle spectrograms corresponding to the multiple frequency bands to obtain the cycle spectrogram of the signal to be identified as a target cycle spectrogram.
3. The method according to claim 2, wherein the step of moving the frequency spectrum of the signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band signals corresponding to the signal to be identified comprises:
carrying out segmentation processing on the signals to be identified to obtain a plurality of sub-signals to be identified;
moving the frequency spectrum of each sub-signal to be identified to a plurality of preset frequency bands to obtain a plurality of frequency band sub-signals corresponding to the sub-signal to be identified; the frequency band sub-signals corresponding to the sub-signals to be identified on one frequency band are frequency band signals corresponding to the signals to be identified on the frequency band;
the step of determining the cyclic spectrogram of each frequency band signal according to each frequency component and each cyclic frequency component of each frequency band signal includes:
determining a cyclic spectrogram of each frequency band sub-signal according to each frequency component and each cyclic frequency component of each frequency band sub-signal;
and aiming at each frequency band, carrying out averaging processing on the cyclic spectrograms of the frequency band sub-signals on the frequency band to obtain the cyclic spectrogram of the frequency band signal on the frequency band.
4. The method of claim 3, wherein the step of determining a cyclic spectrogram of each frequency band sub-signal based on the respective frequency component and the respective cyclic frequency component of each frequency band sub-signal comprises:
performing fast Fourier transform on each frequency band sub-signal to obtain a transform sub-signal corresponding to each frequency band sub-signal;
and determining a cyclic spectrogram of each transformed sub-signal according to each frequency component and each cyclic frequency component of each transformed sub-signal, and taking the cyclic spectrogram of the frequency band sub-signal corresponding to each transformed sub-signal.
5. The method according to claim 4, wherein the step of determining a cyclic spectrum of each transformed sub-signal as the cyclic spectrum of the frequency band sub-signal corresponding to each transformed sub-signal according to each frequency component and each cyclic frequency component of each transformed sub-signal comprises:
determining a cyclic spectrogram of each transformed sub-signal as a cyclic spectrogram of a frequency band sub-signal corresponding to each transformed sub-signal by using the following formula:
wherein the content of the first and second substances,a cyclic spectrum, N, representing the kth transformed subsignal0Denotes the signal length of the k-th transform sub-signal, f denotes the frequency component, α denotes the cyclic frequency component,
expressed at a frequency of
The k-th transformed sub-signal of (k-th),
to represent
The conjugate, |, represents the modulo value calculation.
6. The method according to claim 2, wherein the step of superimposing the cyclic spectrograms corresponding to the plurality of frequency bands to obtain the cyclic spectrogram of the signal to be identified as the target cyclic spectrogram comprises:
and overlapping the cyclic spectrograms corresponding to the multiple frequency bands by using the following formula to obtain the cyclic spectrogram of the signal to be identified as a target cyclic spectrogram:
|S′r(f，α)|＝max{|Sr，1(f，α)|，|Sr，2(f，α)|，...，|Sr，n(f，α)|}；
wherein, | S'r(f, α) | denotes a cyclic spectrum of the signal to be recognized, | Sr，1(f, α) | represents the circulation spectrogram corresponding to the 1 st frequency band, | Sr，2(f, α) | represents the cycle spectrogram corresponding to the 2 nd frequency band, | Sr，n(f, α) | represents the circulation spectrogram corresponding to the nth frequency band, max represents the maximum value, n represents the number of the frequency bands, f represents the frequency component, α represents the circulation frequency component, and | · | represents the modulus calculation.
7. The method according to any of claims 1-6, wherein the modulation scheme recognition model is trained by:
acquiring the sample data, wherein the sample data comprises a plurality of sample signals and a label modulation mode of each sample signal;
determining a cyclic spectrogram of each sample signal according to each frequency component and each cyclic frequency component of each sample signal;
inputting the cyclic spectrogram of each sample signal into a preset deep neural network to obtain a predicted modulation mode of each sample signal;
determining a loss value identified by a modulation mode according to the predicted modulation mode and the labeled modulation mode of each sample signal;
determining whether the deep neural network converges according to the loss value;
if not, adjusting the parameters of the deep neural network, and returning to the step of inputting the cycle spectrogram of each sample signal into a preset deep neural network to obtain the predicted modulation mode of each sample signal;
if so, determining that the current deep neural network is a modulation mode identification model.
8. A modulation scheme identifying apparatus, comprising:
the receiving module is used for receiving a signal to be identified;
the determining module is used for determining a cyclic spectrogram of the signal to be identified as a target cyclic spectrogram according to each frequency component and each cyclic frequency component of the signal to be identified;
and the identification module is used for inputting the target cycle spectrogram into a pre-trained modulation mode identification model to obtain a modulation mode of the signal to be identified, wherein the modulation mode identification model is obtained by training the deep neural network by using sample data, and the sample data comprises a plurality of sample signals and a labeled modulation mode of each sample signal.
9. An electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
the memory is used for storing a computer program;
the processor, configured to execute the program stored in the memory, implements the method steps of any of claims 1-7.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911028838.0A CN110798419A (en) | 2019-10-28 | 2019-10-28 | Modulation mode identification method and device |
| PCT/CN2020/096565 WO2021082469A1 (en) | 2019-10-28 | 2020-06-17 | Modulation mode identification method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911028838.0A CN110798419A (en) | 2019-10-28 | 2019-10-28 | Modulation mode identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110798419A true CN110798419A (en) | 2020-02-14 |
Family
ID=69441459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911028838.0A Withdrawn CN110798419A (en) | 2019-10-28 | 2019-10-28 | Modulation mode identification method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110798419A (en) |
| WO (1) | WO2021082469A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111314257A (en) * | 2020-03-13 | 2020-06-19 | 电子科技大学 | Modulation mode identification method based on complex value neural network |
| CN111464469A (en) * | 2020-03-12 | 2020-07-28 | 南京航空航天大学 | Hybrid digital modulation mode identification method based on neural network |
| CN111800357A (en) * | 2020-07-03 | 2020-10-20 | 全球能源互联网研究院有限公司 | Method and system for distinguishing modulation types based on cyclic spectrum |
| WO2021082469A1 (en) * | 2019-10-28 | 2021-05-06 | 北京邮电大学 | Modulation mode identification method and apparatus |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022272100A1 (en) * | 2021-06-24 | 2022-12-29 | Schlumberger Technology Corporation | Data rate mismatch advisor |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070007959A1 (en) * | 2005-06-23 | 2007-01-11 | The Research Foundation Of State Universtiy Of New York | Simultaneous phase cycling for nuclear magnetic resonance spectroscopy |
| CN107147599A (en) * | 2017-04-14 | 2017-09-08 | 电子科技大学 | A kind of figure characteristic of field method for auto constructing for Modulation Recognition of Communication Signal |
| CN108600135A (en) * | 2018-04-27 | 2018-09-28 | 中国科学院计算技术研究所 | A kind of recognition methods of signal modulation mode |
| CN109818892A (en) * | 2019-01-18 | 2019-05-28 | 华中科技大学 | Construct Cyclic Spectrum characteristic parameter extraction model and signal modulation mode recognition methods |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921014B (en) * | 2018-05-21 | 2021-05-14 | 西北工业大学 | Propeller shaft frequency searching method based on improved noise envelope signal identification |
| CN110321953A (en) * | 2019-07-03 | 2019-10-11 | 中山大学 | Deep learning intelligent modulation recognition methods based on circulation Power estimation |
| CN110798419A (en) * | 2019-10-28 | 2020-02-14 | 北京邮电大学 | Modulation mode identification method and device |
-
2019
- 2019-10-28 CN CN201911028838.0A patent/CN110798419A/en not_active Withdrawn
-
2020
- 2020-06-17 WO PCT/CN2020/096565 patent/WO2021082469A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070007959A1 (en) * | 2005-06-23 | 2007-01-11 | The Research Foundation Of State Universtiy Of New York | Simultaneous phase cycling for nuclear magnetic resonance spectroscopy |
| CN107147599A (en) * | 2017-04-14 | 2017-09-08 | 电子科技大学 | A kind of figure characteristic of field method for auto constructing for Modulation Recognition of Communication Signal |
| CN108600135A (en) * | 2018-04-27 | 2018-09-28 | 中国科学院计算技术研究所 | A kind of recognition methods of signal modulation mode |
| CN109818892A (en) * | 2019-01-18 | 2019-05-28 | 华中科技大学 | Construct Cyclic Spectrum characteristic parameter extraction model and signal modulation mode recognition methods |
Non-Patent Citations (1)
| Title |
|---|
| 张克终: "非合作模式下微弱信号识别技术研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082469A1 (en) * | 2019-10-28 | 2021-05-06 | 北京邮电大学 | Modulation mode identification method and apparatus |
| CN111464469A (en) * | 2020-03-12 | 2020-07-28 | 南京航空航天大学 | Hybrid digital modulation mode identification method based on neural network |
| CN111314257A (en) * | 2020-03-13 | 2020-06-19 | 电子科技大学 | Modulation mode identification method based on complex value neural network |
| CN111800357A (en) * | 2020-07-03 | 2020-10-20 | 全球能源互联网研究院有限公司 | Method and system for distinguishing modulation types based on cyclic spectrum |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021082469A1 (en) | 2021-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110798419A (en) | Modulation mode identification method and device | |
| KR102002681B1 (en) | Bandwidth extension based on generative adversarial networks | |
| CN107305774B (en) | Voice detection method and device | |
| CN109065027B (en) | Voice distinguishing model training method and device, computer equipment and storage medium | |
| KR102065603B1 (en) | Dominant signal detection method and apparatus | |
| US20140205141A1 (en) | Systems and methods for tracking and detecting a target object | |
| CN102612711B (en) | Signal processing method, information processor | |
| JP6811791B2 (en) | Methods and equipment for monitoring telecommunications networks | |
| CN111785288B (en) | Voice enhancement method, device, equipment and storage medium | |
| EP2662854A1 (en) | Method and device for detecting fundamental tone | |
| US20220300824A1 (en) | A neural network for identifying radio technologies | |
| US9997168B2 (en) | Method and apparatus for signal extraction of audio signal | |
| CN111754983A (en) | Voice denoising method and device, electronic equipment and storage medium | |
| WO2023049601A1 (en) | Domain adaptation for wireless sensing | |
| RU2018145032A (en) | DEVICE FOR DETERMINING INFORMATION ON SIMILARITY, METHOD FOR DETERMINING INFORMATION ON SIMILARITY, DEVICE FOR DETERMINING INFORMATION ON AUTOCORRELATION, DEVICE FOR DETERMINING INFORMATION ON MUTUAL CORRELATION AND COMPUTER PROGRAM | |
| CN112651429B (en) | Audio signal time sequence alignment method and device | |
| AU2012244118B2 (en) | Method and System for Identifying Events of Digital Signal | |
| CN107347043A (en) | The method of receiver and in the receiver compensating carrier frequency offset | |
| US20210242891A1 (en) | Apparatus and method for correcting an input signal | |
| CN114218428A (en) | Audio data clustering method, device, equipment and storage medium | |
| CN110097893B (en) | Audio signal conversion method and device | |
| JP6229576B2 (en) | Sampling frequency estimation device | |
| CN108599882B (en) | Self-encoder-based broadband spectrum sensing method and device | |
| CN115691541B (en) | Voice separation method, device and storage medium | |
| CN106254291A (en) | Sampling frequency deviation calculates |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200214 |
|
| WW01 | Invention patent application withdrawn after publication |