Radio signal classification method and device

Abstract

The invention discloses a radio signal classification method and device. The method comprises the following steps: acquiring an original data set; performing training processing on a signal classification model by utilizing the original data set to obtain a signal classification optimization model; and acquiring radio signal data, and processing the radio signal data by using the signal classification optimization model to obtain radio signal modulation information. According to the radio signal classification method and device provided by the invention, the signal classification model is adopted to realize effective identification of complex modulation signals, the modulation identification accuracy of high-order modulation signals is improved, and the method and the device have important significance for ensuring the reliability and the stability of a communication system.

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a radio signal classification method and device. Background Art

[0002] In modern communication systems, high-order modulation technology has been widely used because it can significantly improve spectrum efficiency. However, traditional modulation recognition methods face the challenges of high computational complexity and limited recognition efficiency. Existing deep learning models often find it difficult to achieve ideal discrimination when dealing with the classification of high-order modulation signals. Therefore, achieving classification and recognition of high-order modulation signals is an urgent problem to be solved. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a radio signal classification method and device, which utilizes a signal classification model to achieve effective recognition of complex modulated signals and improve the modulation recognition accuracy of high-order modulated signals.

[0004] In order to solve the above technical problem, a first aspect of an embodiment of the present invention discloses a radio signal classification method, the method comprising:

[0005] S1, obtain the original data set;

[0006] S2, using the original data set to train the signal classification model to obtain a signal classification optimization model;

[0007] S3, acquiring radio signal data, and processing the radio signal data using the signal classification optimization model to obtain radio signal modulation information.

[0008] As an optional implementation, in the first aspect of the embodiment of the present invention, the signal classification model includes: a data input layer, a data convolution processing layer, a batch normalization layer, a first function processing layer, a random inactivation layer, a first long short-term memory layer, a second function processing layer, a second long short-term memory layer, a third function processing layer, a third long short-term memory layer, a fourth function processing layer, a first fully connected layer, a fifth function processing layer, a second fully connected layer and a data output layer;

[0009] The data input layer, the data convolution processing layer, the batch normalization layer, the first function processing layer, the random inactivation layer, the first long short-term memory layer, the second function processing layer, the second long short-term memory layer, the third function processing layer, the third long short-term memory layer, the fourth function processing layer, the first fully connected layer, the fifth function processing layer, the second fully connected layer and the data output layer are data connected in sequence.

[0010] As an optional implementation, in the first aspect of the embodiment of the present invention, the using of the original data set to train the signal classification model to obtain the signal classification optimization model includes:

[0011] S21, preprocessing the original data set to obtain a preprocessed original data set;

[0012] S22, using the pre-processed original data set to train a signal classification model to obtain a signal classification optimization model.

[0013] As an optional implementation, in the first aspect of the embodiment of the present invention, the using of the preprocessed original data set to train the signal classification model to obtain the signal classification optimization model includes:

[0014] S221, dividing the preprocessed original data set according to a set ratio to obtain a training data set and a test data set;

[0015] Preset training stop threshold;

[0016] S222, using the signal classification model and the multi-classification cross entropy loss function, processing the training data set to obtain a first difference value;

[0017] S223, using an adaptive estimation function and a weight attenuation coefficient, updating the parameters of the signal classification model to obtain a stop parameter;

[0018] S224, determining whether the stop parameter is greater than a preset training stop threshold, and obtaining a stop parameter determination result;

[0019] When the stop parameter judgment result is yes, execute S225;

[0020] When the stop parameter judgment result is no, executing S222;

[0021] S225, determining whether the first difference value is less than a preset difference value threshold, and obtaining a difference value determination result;

[0022] When the difference value determination result is no, executing S221;

[0023] If the difference value determination result is yes, the training process of the signal classification model is completed to obtain the signal classification optimization model.

[0024] As an optional implementation, in the first aspect of the embodiment of the present invention, the multi-classification cross entropy loss function expression is:

[0025]

[0026] Among them, Q i represents the difference between the probability that the sample belongs to the i-th category and the true probability distribution; i represents the index of the modulation type; k represents the sample data index; N represents the number of modulation categories; K represents the number of sample data of the i-th category; Represents the true label value of the kth sample data of the i-th modulation category; Indicates the predicted probability value that the kth sample data is the i-th modulation category;

[0027] The adaptive estimation function expression is:

[0028]

[0029] Among them, w i+1 represents the gradient update value at the i+1th moment; w i represents the gradient update value at the i-th moment; μ represents the learning rate; represents the second-order moment estimate at the i-th moment; represents the second-order moment estimate after deviation correction at the i-th moment; β i represents the attenuation coefficient at the i-th moment; τ represents the first reference constant.

[0030] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the acquiring of radio signal data, and processing of the radio signal data using the signal classification optimization model to obtain radio signal modulation information includes:

[0031] S31, receiving and acquiring radio signal data in real time;

[0032] S32, preprocessing the radio signal data to obtain preprocessed signal data;

[0033] S33, based on the signal classification optimization model, processing the pre-processed signal data to obtain radio signal modulation information.

[0034] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the preprocessed signal data based on the signal classification optimization model to obtain the radio signal modulation information includes:

[0035] S3301, using the data convolution processing layer, performing convolution processing on the preprocessed signal data to obtain first processed data;

[0036] S3302, using the batch normalization layer, normalize the first processed data to obtain second processed data;

[0037] S3303, using the first function processing layer, performing calculation processing on the second processed data to obtain third processed data;

[0038] S3304, using the random dropout layer, generalize the third processed data to obtain fourth processed data;

[0039] S3305, using the first long short-term memory layer, processing the fourth processed data to obtain fifth processed data;

[0040] S3306, using the second function processing layer, performing calculation processing on the fifth processed data to obtain sixth processed data;

[0041] S3307, using the second long short-term memory layer, processing the sixth processed data to obtain seventh processed data;

[0042] S3308, using the third function processing layer, performing calculation processing on the seventh processed data to obtain eighth processed data;

[0043] S3309, using the third long short-term memory layer, processing the eighth processed data to obtain ninth processed data;

[0044] S3310, using the fourth function processing layer, performing calculation processing on the ninth processed data to obtain tenth processed data;

[0045] S3311 uses the first fully connected layer to process the tenth processed data to obtain eleventh processed data;

[0046] S3312, using the fifth function processing layer, performing calculation processing on the eleventh processed data to obtain twelfth processed data;

[0047] S3313: Use the second fully connected layer to process the twelfth processed data to obtain radio signal modulation information.

[0048] A second aspect of an embodiment of the present invention discloses a radio signal classification device, the device comprising:

[0049] Data acquisition module, training processing module and recognition processing module;

[0050] The data acquisition module is used to acquire the original data set;

[0051] The training processing module is used to use the original data set to train the signal classification model to obtain a signal classification optimization model;

[0052] The identification and processing module is used to obtain radio signal data, and process the radio signal data using the signal classification optimization model to obtain radio signal modulation information.

[0053] A third aspect of the present invention discloses a radio signal classification device, the device comprising:

[0054] A memory storing executable program code;

[0055] a processor coupled to the memory;

[0056] The processor calls the executable program code stored in the memory to execute part or all of the steps in the radio signal classification method disclosed in the first aspect of the embodiment of the present invention.

[0057] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores computer instructions. When the computer instructions are called, some or all of the steps in the radio signal classification method disclosed in the first aspect of the embodiment of the present invention are executed.

[0058] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0059] In the embodiment of the present invention, the signal classification model is used to realize the effective recognition of low-order complex modulated signals, and the modulation recognition accuracy of high-order modulated signals is improved, which is of great significance for ensuring the reliability and stability of the communication system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 is a schematic diagram of a scenario of a radio signal classification system provided by an embodiment of the present invention;

[0062] Figure 2 It is a flowchart of a radio signal classification method disclosed in an embodiment of the present invention;

[0063] Figure 3 is the signal modulation recognition accuracy under four preprocessing modes of the convolutional neural network (CNN) model disclosed in the embodiment of the present invention. Figure 3 (a) is a line graph showing the change of recognition accuracy of the CNN model with the signal-to-noise ratio under the original IQ signal preprocessing method. Figure 3 (b) is a line graph showing the change of the recognition accuracy of the CNN model with the signal-to-noise ratio under the signal amplitude and phase preprocessing mode. Figure 3(c) is a line graph showing the change of the recognition accuracy of the CNN model with the signal-to-noise ratio under the signal amplitude, phase and frequency preprocessing. Figure 3 (d) is a line graph showing the variation of the recognition accuracy of the CNN model with the signal-to-noise ratio under the signal two-dimensional Grammar angle field preprocessing method;

[0064] Figure 4 : is a confusion matrix diagram of signal modulation recognition under four preprocessing modes of the convolutional neural network (CNN) model disclosed in the embodiment of the present invention. Figure 4 (a) is the recognition confusion matrix diagram of the CNN model under the original IQ signal preprocessing method. Figure 4 (b) is the recognition confusion matrix diagram of the CNN model under the signal amplitude and phase preprocessing method. Figure 4 (c) is the recognition confusion matrix diagram of the CNN model under the signal amplitude, phase and frequency preprocessing. Figure 4 (d) is the recognition confusion matrix diagram of the CNN model under the signal two-dimensional Gram angle field preprocessing method;

[0065] Figure 5 It is the signal modulation recognition accuracy under four preprocessing modes of the model combining convolutional neural network and long short-term memory network (CNN-LSTM) disclosed in the embodiment of the present invention. Figure 5 (a) is a line graph showing the change of recognition accuracy of the CNN-LSTM model with the signal-to-noise ratio under the original IQ signal preprocessing method. Figure 5 (b) is a line graph showing the change of recognition accuracy of the CNN-LSTM model with signal-to-noise ratio under signal amplitude and phase preprocessing. Figure 5 (c) is a line graph showing the change of recognition accuracy of the CNN-LSTM model with signal-to-noise ratio under signal amplitude, phase and frequency preprocessing. Figure 5 (d) is a line graph showing the variation of the recognition accuracy of the CNN-LSTM model with the signal-to-noise ratio under the signal two-dimensional Grammar angle field preprocessing method;

[0066] Figure 6 It is a confusion matrix diagram of signal modulation recognition under four preprocessing modes of the model combining convolutional neural network and long short-term memory network (CNN-LSTM) disclosed in the embodiment of the present invention. Figure 6 (a) is the recognition confusion matrix diagram of the CNN-LSTM model under the original IQ signal preprocessing method. Figure 6 (b) is the recognition confusion matrix diagram of the CNN-LSTM model under the signal amplitude and phase preprocessing mode. Figure 6 (c) is the recognition confusion matrix diagram of the CNN-LSTM model under the signal amplitude, phase and frequency preprocessing. Figure 6(d) is the recognition confusion matrix diagram of the CNN-LSTM model under the signal two-dimensional Gram angular field preprocessing method;

[0067] Figure 7 It is the signal modulation recognition accuracy under two preprocessing modes of the signal classification model (Convolutional Long Short Term Memory Networks with Fully Connected Layer, CLF model) disclosed in the embodiment of the present invention. Figure 7 (a) is a line graph showing the change of the recognition accuracy of the signal classification model with the signal-to-noise ratio under the signal amplitude and phase preprocessing mode. Figure 7 (b) is a line graph showing the variation of the recognition accuracy of the signal classification model with the signal-to-noise ratio under the signal amplitude, phase and frequency preprocessing methods;

[0068] Figure 8 It is a confusion matrix diagram of signal modulation recognition under two preprocessing modes of the signal classification model (Convolutional Long Short Term Memory Networks with Fully Connected Layer, CLF model) disclosed in the embodiment of the present invention. Figure 8 (a) is the identification confusion matrix diagram of the signal classification model under the signal amplitude and phase preprocessing method. Figure 8 (b) is the identification confusion matrix diagram of the signal classification model under the signal amplitude, phase and frequency preprocessing methods;

[0069] Fig. 9 It is a structural schematic diagram of a radio signal classification device disclosed in an embodiment of the present invention;

[0070] Fig.10 It is a structural schematic diagram of another radio signal classification device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0071] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0072] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0073] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0074] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0075] It should be noted that since the method of the embodiment of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, they are all corresponding data for processing by the computer device. The details will not be repeated here.

[0076] The embodiments of the present application provide a radio signal classification method, system, apparatus, computer device, and computer-readable storage medium, which are described in detail below.

[0077] See also Figure 1 , Figure 1 Schematic diagram of a signal analysis system provided in an embodiment of the present application. The system may include a computer device 100, in which a radio signal classification device is integrated. Figure 1Computer equipment in.

[0078] In the embodiment of the present application, the computer device 100 may be an independent server, or a server network or server cluster composed of servers. For example, the computer device 100 described in the embodiment of the present application includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud server composed of a plurality of servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0079] It is understandable that the computer device 100 used in the embodiments of the present application may be a device including both receiving and transmitting hardware, that is, a device having receiving and transmitting hardware capable of performing two-way communication on a two-way communication link. Such a device may include: a cellular or other communication device having a single-line display or a multi-line display or a cellular or other communication device without a multi-line display. The specific computer device 100 may be a desktop terminal or a mobile terminal, and the computer device 100 may also be one of a mobile phone, a tablet computer, a laptop computer, etc.

[0080] Those skilled in the art will understand that Figure 1 The application environment shown in the figure is only one application scenario of the present application solution and does not constitute a limitation on the application scenario of the present application solution. Other application environments may also include Figure 1 More or less computer equipment as shown in Figure 1 Only one computer device is shown in the figure. It can be understood that the system can also include one or more other services, which are not limited here.

[0081] In addition, if Figure 1 As shown, the signal analysis system may further include a data storage device 200 for storing recognition result data and sample data, such as simulation result data.

[0082] It should be noted that Figure 1 The scenario diagram of the signal analysis system shown is merely an example. The signal analysis system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the signal analysis control management system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is equally applicable to similar technical problems.

[0083] The present invention discloses a radio signal classification method and device, which utilizes a signal classification model to effectively identify complex modulated signals and improves the modulation recognition accuracy of high-order modulated signals. The following are detailed descriptions.

[0084] Embodiment 1

[0085] See also Figure 2 , Figure 2 is a flow chart of a radio signal classification method disclosed in an embodiment of the present invention. Figure 2 The radio signal classification method described is applied to a signal analysis and management system, such as a local server or a cloud server of the signal analysis and management system, and is not limited in the embodiments of the present invention. Figure 2 As shown, the radio signal classification method may include the following operations:

[0086] S1, obtain the original data set;

[0087] It should be noted that the original data set obtained includes but is not limited to the original IQ data directly collected by the receiver and the public data set;

[0088] S2, using the original data set to train the signal classification model to obtain a signal classification optimization model;

[0089] S3, acquiring radio signal data, and processing the radio signal data using the signal classification optimization model to obtain radio signal modulation information.

[0090] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented, and the signal classification model is used to realize the effective recognition of complex modulated signals, thereby improving the modulation recognition accuracy of high-order modulated signals.

[0091] In an optional embodiment, in the above step S2, the signal classification model includes: a data input layer, a data convolution processing layer, a batch normalization layer, a first function processing layer, a random inactivation layer, a first long short-term memory layer, a second function processing layer, a second long short-term memory layer, a third function processing layer, a third long short-term memory layer, a fourth function processing layer, a first fully connected layer, a fifth function processing layer, a second fully connected layer and a data output layer;

[0092] The data input layer, the data convolution processing layer, the batch normalization layer, the first function processing layer, the random inactivation layer, the first long short-term memory layer, the second function processing layer, the second long short-term memory layer, the third function processing layer, the third long short-term memory layer, the fourth function processing layer, the first fully connected layer, the fifth function processing layer, the second fully connected layer and the data output layer are sequentially data-connected;

[0093] It should be noted that the data input layer is used to receive a data set to be processed; the data set to be processed includes an original data set or radio signal data, which is a 3×128 array and includes amplitude information, phase information and frequency information of the data to be processed;

[0094] It should be noted that the data convolution processing layer is used to perform convolution processing on the data set to be processed to obtain first processed data;

[0095] It should be noted that, in this embodiment, the data convolution processing layer adopts a one-dimensional convolution layer, the input channel is set to 2 (set to 3 in the data preprocessing mode of amplitude, phase and frequency), the output channel is 50; the convolution kernel size is set to 7, the step size is 1, and edge padding is used, the size is 1;

[0096] It should be noted that the batch normalization layer is used to normalize the first processed data to obtain the second processed data;

[0097] The batch normalization layer is used to improve the generalization ability of the model;

[0098] It should be noted that the expression of the normalization process is:

[0099]

[0100] Among them, A i represents the normalized value of the i-th sample data; α represents the first learning parameter; β represents the second learning parameter; m represents the total number of sample data; x i represents the i-th sample data; ε represents the second reference constant;

[0101] It should be noted that, in this embodiment, ε is a very small constant used to prevent division by zero, and the value of ε is 10 -5 ;

[0102] It should be noted that the first function processing layer is used to perform calculation processing on the second processed data to obtain third processed data;

[0103] It should be noted that the calculation processing expression is:

[0104]

[0105] Wherein, x represents the second processed data;

[0106] It should be noted that the random dropout layer is used to perform generalization processing on the third processed data to obtain fourth processed data;

[0107] The random inactivation layer is used to reduce overfitting during the training of the convolutional neural network. The ratio is set to 0.6, which means that during the training process, 60% of the neuron outputs will be randomly set to zero, which can prevent the network from being overly sensitive to the training data and improve the generalization ability of the model;

[0108] It should be noted that the generalized processing expression is:

[0109] y=x⊙Bernoulli(p)

[0110] Wherein, ⊙ represents element-by-element multiplication, Bernoulli() represents Bernoulli distribution; p represents the probability of discarding an element; x represents the third processed data;

[0111] In this embodiment, p = 0.6;

[0112] It should be noted that the first long short-term memory layer is used to process the fourth processed data to obtain fifth processed data;

[0113] It should be noted that the size of the hidden layer of the first LSTM layer is 64, the corresponding input is set to 50, and the size of the hidden state and cell state is 64;

[0114] It should be noted that the first long short-term memory layer processing expression is:

[0115] f t =σ(w f ·[h t-1 , x t ]+b f )

[0116] i t =σ(w i ·[h t-1 , x t ]+b i )

[0117]

[0118] o t =σ(w o ·[h t-1 , x t ]+b o )

[0119] h t =o t ·tanh(c t )

[0120] Among them, f t Indicates forget gate calculation; i trepresents the input gate calculation; represents the candidate cell state; c t Indicates cell status; o t Indicates output gate calculation; h t represents hidden state calculation; σ represents the sigmoid function, which is used to generate values ​​between 0 and 1; * represents element-by-element multiplication; w f represents the first weight matrix; w i represents the second weight matrix; w c represents the third weight matrix; w o represents the fourth weight matrix; b f represents the first bias vector; b i represents the second bias vector; b c represents the third bias vector; b o represents the fourth bias vector; [h t-1 , x t ] represents the connection between hidden state and input; tanh() represents the hyperbolic tangent function, which is used to map values ​​between [-1,1];

[0121] It should be noted that the second function processing layer is used to perform calculation processing on the fifth processed data to obtain sixth processed data;

[0122] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0123] It should be noted that the second long short-term memory layer is used to process the sixth processed data to obtain seventh processed data;

[0124] It should be noted that the size of the hidden layer of the second LSTM layer is 100, and the corresponding input is set to 64:

[0125] It should be noted that the second long short-term memory layer is consistent with the first long short-term memory layer;

[0126] It should be noted that the third function processing layer is used to perform calculation processing on the seventh processed data to obtain eighth processed data;

[0127] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0128] It should be noted that the third long short-term memory layer is used to process the eighth processed data to obtain ninth processed data;

[0129] It should be noted that the size of the hidden layer of the third long short-term memory layer is 128, and the corresponding input is set to 100;

[0130] It should be noted that the third long short-term memory layer is consistent with the first long short-term memory layer;

[0131] It should be noted that the fourth function processing layer is used to perform calculation processing on the ninth processed data to obtain tenth processed data;

[0132] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0133] It should be noted that the first fully connected layer is used to process the tenth processed data to obtain the eleventh processed data;

[0134] It should be noted that the output feature of the first fully connected layer is set to 128;

[0135] It should be noted that, in this embodiment, the fully connected layer uses linear transformation, which reduces the number of input features from 128 to 64;

[0136] y=Wx+a

[0137] Wherein, x represents the tenth processed data, and its dimension is (N, 128), wherein N represents the batch size; W represents the first weight matrix, and its dimension is (64, 128); a represents the first bias vector, and its dimension is (64, 1); y represents the eleventh processed data, and its dimension is (N, 64);

[0138] It should be noted that the fifth function processing layer is used to perform calculation processing on the eleventh processed data to obtain the twelfth processed data;

[0139] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0140] It should be noted that the second fully connected layer is used to process the twelfth processed data to obtain radio signal modulation information;

[0141] It should be noted that the output features of the second fully connected layer are the results of classification processing;

[0142] It should be noted that, in this embodiment, the second fully connected layer also uses linear transformation, which reduces the number of input features from 128 to 64;

[0143] q=μp+b

[0144] Wherein, p represents the twelfth processed data, and its dimension is (N, 128), wherein N represents the batch size; μ represents the second weight matrix, and its dimension is (64, 128); b represents the second bias vector, and its dimension is (64, 1); y represents the radio signal modulation information, and its dimension is (N, 64);

[0145] It can be seen that by implementing the radio signal classification method described in the embodiment of the present invention, a signal classification model is constructed and used to realize effective recognition of complex modulated signals, thereby improving the modulation recognition accuracy of high-order modulated signals.

[0146] In another optional embodiment, in the above step S2, the use of the original data set to train the signal classification model to obtain the signal classification optimization model includes:

[0147] S21, preprocessing the original data set to obtain a preprocessed original data set;

[0148] S22, using the pre-processed original data set to train a signal classification model to obtain a signal classification optimization model.

[0149] It can be seen that by implementing the radio signal classification method described in the embodiment of the present invention, the signal classification model is trained to obtain a signal classification optimization model, thereby achieving effective recognition of complex modulated signals and improving the modulation recognition accuracy of high-order modulated signals.

[0150] In another optional embodiment, in the above step S21, preprocessing the original data set to obtain the preprocessed original data set includes:

[0151] Optionally, performing a first processing on the original data set to obtain a first preprocessed data set;

[0152] The first processing expression is:

[0153]

[0154] Wherein, N represents the length of the original data set; r q (n) represents the Q component of the nth original data; ri(n) represents the I component of the nth original data; Φ n Represents the phase information of the nth original data; A n Indicates the amplitude information of the nth original data;

[0155] Optionally, performing a second processing on the original data set to obtain a first preprocessed data set;

[0156] The second processing expression is:

[0157]

[0158] Wherein, N represents the length of the original data set; r q (n) represents the Q component of the nth original data; r i (n) represents the I component of the nth original data; φ n Represents the phase information of the nth original data; A n represents the amplitude information of the nth original data; x[n] represents the time domain discrete signal of the nth original data, X[k] is the frequency domain discrete signal of the nth original data; M represents the total number of samples of the original data set; k represents the kth frequency domain component of the original data set; j represents an imaginary unit;

[0159] Normalizing the first preprocessed data set to obtain a second preprocessed data set;

[0160] The normalization expression is:

[0161]

[0162] Wherein, norm(x) represents the second preprocessed data set; x i represents the i-th first preprocessed data; n represents the total number of first preprocessed data sets;

[0163] Processing the second preprocessed data set to obtain a preprocessed original data set;

[0164] The processing expression is:

[0165]

[0166] Wherein, X′ represents the preprocessed original data set; x i represents the i-th first pre-processed data (i=1, ..., n).

[0167] It should be noted that, in this embodiment, Figure 3 and Figure 4 They are the recognition accuracy and confusion matrix of the convolutional neural network (CNN) model for the four data preprocessing methods; Figure 5 and Figure 6 The recognition accuracy and confusion matrix of the four data preprocessing methods are shown in the figure. Figure 3 , Figure 4 , Figure 5 and Figure 6It can be seen that the data preprocessing method using amplitude, phase and frequency also has the best recognition accuracy, followed by the data preprocessing method using amplitude and phase. Therefore, the preprocessing method adopted by the signal classification model is the data preprocessing method using amplitude, phase and frequency, or the data preprocessing method using amplitude and phase.

[0168] It should be noted that, in this embodiment, the data is preprocessed using the data preprocessing method of amplitude, phase and frequency and the data preprocessing method of amplitude and phase, and the signal classification model (CLF model) is trained using the data of the two data preprocessing methods respectively, and the learning rate is set to 1e-5. Figure 7 and Figure 8 It can be seen that compared with the commonly used deep learning models, the diagonal line of the signal classification model (CLF model) is extremely obvious, and the recognition accuracy is very high. It can basically solve the problem of 8PSK and QPSK recognition errors shown in the commonly used deep learning models, and the signal classification model (CLF model) shows a smaller number of overall misidentifications on the confusion matrix diagram. The signal classification model also shows great advantages for high-order modulation. For 16QAM and 64QAM, it can be seen from the confusion matrix that compared with a rectangle with basically no distinction shown by the commonly used deep learning model, the signal classification model shows a diagonal line that can be well distinguished. For two different data preprocessing methods, the method of using amplitude and phase is more convenient, with less data and better processing effect. Therefore, the signal classification model can achieve a good modulation recognition effect by using the data preprocessing methods of amplitude and phase, amplitude and phase and frequency.

[0169] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented to preprocess the original data set to obtain a preprocessed original data set, which meets the data requirements of the signal classification model, thereby realizing effective recognition of complex modulated signals and improving the modulation recognition accuracy of high-order modulated signals.

[0170] In another optional embodiment, in the above step S22, the use of the pre-processed original data set to train the signal classification model to obtain the signal classification optimization model includes:

[0171] S221, dividing the preprocessed original data set according to a set ratio to obtain a training data set and a test data set;

[0172] It should be noted that, in this embodiment, the set ratio is 8:2, that is, the division of the training set and the test set of the data is 8:2;

[0173] It should be noted that, in this embodiment, at each signal-to-noise ratio, there are 8800 signals for training and 2200 signals for testing;

[0174] Preset training stop threshold;

[0175] It should be noted that, in the embodiment of the present invention, the training stop threshold is set to 3;

[0176] S222, using the signal classification model and the multi-classification cross entropy loss function, processing the training data set to obtain a first difference value;

[0177] S223, using an adaptive estimation function and a weight attenuation coefficient, updating the parameters of the signal classification model to obtain a stop parameter;

[0178] S224, determining whether the stop parameter is greater than a preset training stop threshold, and obtaining a stop parameter determination result;

[0179] When the stop parameter judgment result is yes, execute S225;

[0180] When the stop parameter judgment result is no, executing S222;

[0181] S227, determining whether the first difference value is less than a preset difference value threshold, and obtaining a difference value determination result;

[0182] When the difference value determination result is no, executing S221;

[0183] If the difference value determination result is yes, the training process of the signal classification model is completed to obtain the signal classification optimization model.

[0184] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented by preprocessing the original data set to realize the training processing of the signal classification model, thereby obtaining a signal classification optimization model, which lays the foundation for the effective recognition of complex modulated signals and improves the modulation recognition accuracy of high-order modulated signals.

[0185] In another optional embodiment, in the above step S223, the multi-classification cross entropy loss function expression is:

[0186]

[0187] Among them, Q i represents the difference between the probability that the sample belongs to the i-th category and the true probability distribution; i represents the index of the modulation type; k represents the sample data index; N represents the number of modulation categories; K represents the number of sample data of the i-th category; Represents the true label value of the kth sample data of the i-th modulation category; Indicates the predicted probability value that the kth sample data is the i-th modulation category;

[0188] The adaptive estimation function expression is:

[0189]

[0190] Among them, w i+1 represents the gradient update value at the i+1th moment; w i represents the gradient update value at the i-th moment; μ represents the learning rate; represents the second-order moment estimate at the i-th moment; represents the second-order moment estimate after deviation correction at the i-th moment; β i represents the attenuation coefficient at the i-th moment; τ represents the first reference constant;

[0191] It should be noted that the first reference constant is set to 10 -5 , used to prevent division by zero;

[0192] It should be noted that the β i The value is 0.99 or 0.9.

[0193] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented by preprocessing the original data set to realize the training processing of the signal classification model, thereby obtaining a signal classification optimization model, which lays the foundation for the effective recognition of complex modulated signals and improves the modulation recognition accuracy of high-order modulated signals.

[0194] In an optional embodiment, in the above step S3, the acquiring of radio signal data, and processing of the radio signal data using the signal classification optimization model to obtain radio signal modulation information includes:

[0195] S31, receiving and acquiring radio signal data in real time;

[0196] It should be noted that the radio signal data refers to the original IQ data directly collected by the receiver;

[0197] S32, preprocessing the radio signal data to obtain preprocessed signal data;

[0198] S33, based on the signal classification optimization model, processing the pre-processed signal data to obtain radio signal modulation information.

[0199] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented, and the signal classification optimization model is used to realize the classification and recognition processing of radio signal data, which lays the foundation for the effective recognition of complex modulated signals and improves the modulation recognition accuracy of high-order modulated signals.

[0200] In another optional embodiment, in the above step S32, the preprocessing of the radio signal data to obtain preprocessed signal data includes:

[0201] Optionally, performing a first processing on the radio signal data to obtain a first preprocessed signal set;

[0202] The first processing expression is:

[0203]

[0204] Wherein, N represents the radio signal data; r q (n) represents the Q component of the n-th radio signal data; r i (n) represents the I component of the n-th radio signal data; Φ n Represents the phase information of the nth radio signal data; A n Indicates the amplitude information of the nth radio signal data;

[0205] Optionally, performing a second processing on the radio signal data to obtain a first preprocessed signal set;

[0206] The second processing expression is:

[0207]

[0208] Wherein, N represents the length of the radio signal data; rq(n) represents the Q component of the nth radio signal data; r i (n) represents the I component of the nth radio signal data; φ n Represents the phase information of the nth radio signal data; A n represents the amplitude information of the nth radio signal data; x[n] represents the time domain discrete signal of the nth radio signal data, X[k] is the frequency domain discrete signal of the nth radio signal data; M represents the total number of samples of the radio signal data; k represents the kth frequency domain component of the radio signal data; j represents an imaginary unit;

[0209] Normalizing the first preprocessed signal set to obtain a second preprocessed signal set;

[0210] The normalization expression is:

[0211]

[0212] Wherein, norm(x) represents the second preprocessed signal set; x i represents the i-th first preprocessed signal data; n represents the total number of first preprocessed signals;

[0213] Processing the second preprocessed signal set to obtain a preprocessed signal data set;

[0214] The processing expression is:

[0215]

[0216] Wherein, X′ represents the preprocessed signal data set; x i represents the i-th second pre-processed signal (i=1, ..., n).

[0217] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented to preprocess the radio signal data to obtain preprocessed signal data, which meets the data requirements of the signal classification optimization model, thereby realizing effective recognition of complex modulated signals and improving the modulation recognition accuracy of high-order modulated signals.

[0218] In another optional embodiment, in the above step S33, the processing of the pre-processed signal data based on the signal classification optimization model to obtain the radio signal modulation information includes:

[0219] S3301, using the data convolution processing layer, performing convolution processing on the preprocessed signal data to obtain first processed data;

[0220] Optionally, in the data preprocessing mode of amplitude, phase and frequency, the input channel of the convolution processing is 3, the output channel is 50, the convolution kernel size is set to 7, the step size is 1, and edge padding is used, the size is 1;

[0221] Optionally, in the data preprocessing mode of amplitude and phase, the input channel of the convolution processing is 2, the output channel is 50, the convolution kernel size is set to 7, the step size is 1, and edge padding is used, with a size of 1;

[0222] S3302, using the batch normalization layer, normalize the first processed data to obtain second processed data;

[0223] It should be noted that the expression of the normalization process is:

[0224]

[0225] Among them, A irepresents the normalized value of the i-th sample data; α represents the first learning parameter; β represents the second learning parameter; m represents the total number of sample data; x i represents the i-th sample data; ε represents the second reference constant;

[0226] It should be noted that, in this embodiment, the value of ε is 10 -5 ;

[0227] S3303, using the first function processing layer, performing calculation processing on the second processed data to obtain third processed data;

[0228] It should be noted that the calculation processing expression is:

[0229]

[0230] Wherein, x represents the second processed data;

[0231] S3304, using the random dropout layer, generalize the third processed data to obtain fourth processed data;

[0232] It should be noted that the generalized processing expression is:

[0233] y=x ⊙ Bernoulli(p)

[0234] Wherein, ⊙ represents element-by-element multiplication, Bernoulli() represents Bernoulli distribution; p represents the probability of discarding an element; x represents the third processed data;

[0235] S3305, using the first long short-term memory layer, processing the fourth processed data to obtain fifth processed data;

[0236] It should be noted that the size of the hidden layer of the first LSTM layer is 64, the corresponding input is set to 50, and the size of the hidden state and cell state is 64;

[0237] It should be noted that the first long short-term memory layer processing expression is:

[0238] f t =σ(w f ·[h t-1 , x t ]+b f )

[0239] i t =σ(w i ·[h t-1 , x t ]+b i )

[0240]

[0241] o t =σ(w o ·[h t-1 , x t ]+b o )

[0242] h t =o t ·tanh(c t )

[0243] Among them, f t Indicates forget gate calculation; i t represents the input gate calculation; represents the candidate cell state; c t Indicates cell status; o t Indicates output gate calculation; h t represents hidden state calculation; σ represents the sigmoid function, which is used to generate values ​​between 0 and 1; * represents element-by-element multiplication; w f represents the first weight matrix; w i represents the second weight matrix; w c represents the third weight matrix; w o represents the fourth weight matrix; b f represents the first bias vector; b i represents the second bias vector; b c represents the third bias vector; b o represents the fourth bias vector; [h t-1 , x t ] represents the connection between hidden state and input; tanh() represents the hyperbolic tangent function, which is used to map values ​​between [-1,1];

[0244] S3306, using the second function processing layer, performing calculation processing on the fifth processed data to obtain sixth processed data;

[0245] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0246] S3307, using the second long short-term memory layer, processing the sixth processed data to obtain seventh processed data;

[0247] It should be noted that the size of the hidden layer of the second LSTM layer is 100, and the corresponding input is set to 64;

[0248] It should be noted that the second long short-term memory layer is consistent with the first long short-term memory layer;

[0249] S3308, using the third function processing layer, performing calculation processing on the seventh processed data to obtain eighth processed data;

[0250] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0251] S3309, using the third long short-term memory layer, processing the eighth processed data to obtain ninth processed data;

[0252] It should be noted that the size of the hidden layer of the third long short-term memory layer is 128, and the corresponding input is set to 100;

[0253] It should be noted that the third long short-term memory layer is consistent with the first long short-term memory layer;

[0254] S3310, using the fourth function processing layer, performing calculation processing on the ninth processed data to obtain tenth processed data;

[0255] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0256] S3311 uses the first fully connected layer to process the tenth processed data to obtain eleventh processed data;

[0257] It should be noted that the output feature of the first fully connected layer is set to 128;

[0258] It should be noted that, in this embodiment, the fully connected layer uses linear transformation, which reduces the number of input features from 128 to 64;

[0259] y=Wx+a

[0260] Wherein, x represents the tenth processed data, and its dimension is (N, 128), wherein N represents the batch size; W represents the first weight matrix, and its dimension is (64, 128); a represents the first bias vector, and its dimension is (64, 1); y represents the eleventh processed data, and its dimension is (N, 64);

[0261] S3312, using the fifth function processing layer, performing calculation processing on the eleventh processed data to obtain twelfth processed data;

[0262] It should be noted that the calculation processing method is consistent with the calculation processing of the first function processing layer;

[0263] S3313, using the second fully connected layer, processing the twelfth processed data to obtain radio signal modulation information;

[0264] It should be noted that the output features of the second fully connected layer are the results of classification processing;

[0265] It should be noted that, in this embodiment, the second fully connected layer also uses linear transformation, which reduces the number of input features from 128 to 64;

[0266] q=μp+b

[0267] Among them, p represents the twelfth processed data, whose dimension is (N, 128), where N represents the batch size; μ represents the second weight matrix, whose dimension is (64, 128); b represents the second bias vector, whose dimension is (64, 1); y represents the radio signal modulation information, whose dimension is (N, 64).

[0268] It can be seen that the radio signal classification method described in the embodiment of the present invention is implemented, and the pre-processed signal data is processed using the signal classification optimization model, so as to achieve effective recognition of complex modulated signals and improve the modulation recognition accuracy of high-order modulated signals.

[0269] Embodiment 2

[0270] See also Fig. 9 , Fig. 9 : is a schematic diagram of the structure of a radio signal classification device disclosed in an embodiment of the present invention. Fig. 9 The described device can be applied to a signal analysis management system, such as a local server or a cloud server for a signal analysis system, and the embodiments of the present invention are not limited thereto. Fig. 9 As shown, the device may include:

[0271] Data acquisition module 101, training processing module 102 and recognition processing module 103;

[0272] The data acquisition module 101 is used to acquire the original data set;

[0273] The training processing module 102 is used to train the signal classification model using the original data set to obtain a signal classification optimization model;

[0274] The identification and processing module 103 is used to obtain radio signal data, and process the radio signal data using the signal classification optimization model to obtain radio signal modulation information.

[0275] Embodiment 3

[0276] See also Fig.10 , Fig.10 : is a schematic diagram of the structure of a radio signal classification device disclosed in an embodiment of the present invention. Fig.10The described device can be applied to a signal analysis management system, such as a local server or a cloud server for a signal analysis system, and the embodiments of the present invention are not limited thereto. Fig.10 As shown, the device may include:

[0277] A memory 201 storing executable program codes;

[0278] a processor 202 coupled to the memory 201;

[0279] The processor 202 calls the executable program code stored in the memory 201 to execute the steps in the radio signal classification method described in the first embodiment.

[0280] Embodiment 4

[0281] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the radio signal classification method described in the first embodiment.

[0282] Embodiment 5

[0283] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the radio signal classification method described in the first embodiment.

[0284] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0285] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, a magnetic disk storage, a magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0286] Finally, it should be noted that the radio signal classification method, system and device disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A radio signal classification method, characterized in that: The method comprises: S1, obtain the original data set; S2, using the original data set to train the signal classification model to obtain a signal classification optimization model; S3, acquiring radio signal data, and processing the radio signal data using the signal classification optimization model to obtain radio signal modulation information.

2. The radio signal classification method according to claim 1, characterized in that: The signal classification model comprises: a data input layer, a data convolution processing layer, a batch normalization layer, a first function processing layer, a random inactivation layer, a first long short-term memory layer, a second function processing layer, a second long short-term memory layer, a third function processing layer, a third long short-term memory layer, a fourth function processing layer, a first fully connected layer, a fifth function processing layer, a second fully connected layer and a data output layer; The data input layer, the data convolution processing layer, the batch normalization layer, the first function processing layer, the random inactivation layer, the first long short-term memory layer, the second function processing layer, the second long short-term memory layer, the third function processing layer, the third long short-term memory layer, the fourth function processing layer, the first fully connected layer, the fifth function processing layer, the second fully connected layer and the data output layer are data connected in sequence.

3. The radio signal classification method according to claim 1, characterized in that: The method of using the original data set to train the signal classification model to obtain a signal classification optimization model includes: S21, preprocessing the original data set to obtain a preprocessed original data set; S22, using the pre-processed original data set to train a signal classification model to obtain a signal classification optimization model.

4. The radio signal classification method according to claim 3, characterized in that: The method of using the preprocessed original data set to train the signal classification model to obtain a signal classification optimization model includes: S221, dividing the preprocessed original data set according to a set ratio to obtain a training data set and a test data set; Preset training stop threshold; S222, using the signal classification model and the multi-classification cross entropy loss function, processing the training data set to obtain a first difference value; S223, using an adaptive estimation function and a weight attenuation coefficient, updating the parameters of the signal classification model to obtain a stop parameter; S224, determining whether the stop parameter is greater than a preset training stop threshold, and obtaining a stop parameter determination result; When the stop parameter judgment result is yes, execute S225; When the stop parameter judgment result is no, executing S222; S225, determining whether the first difference value is less than a preset difference value threshold, and obtaining a difference value determination result; When the difference value determination result is no, executing S221; If the difference value determination result is yes, the training process of the signal classification model is completed to obtain the signal classification optimization model.

5. The radio signal classification method according to claim 4, characterized in that: The multi-classification cross entropy loss function expression is: Among them, Q i Indicates the difference between the probability that the sample belongs to the i-th category and the true probability distribution; i represents the index of the modulation type; k represents the sample data index; N represents the number of modulation categories; K represents the number of sample data of the i-th category; Represents the true label value of the kth sample data of the i-th modulation category; Indicates the predicted probability value that the k-th sample data is the i-th modulation category; The adaptive estimation function expression is: Among them, w i+1 represents the gradient update value at the i+1th moment; w i represents the gradient update value at the i-th moment; μ represents the learning rate; represents the second-order moment estimate at the i-th moment; represents the second-order moment estimate after deviation correction at the i-th moment; β i represents the attenuation coefficient at the i-th moment; τ represents the first reference constant.

6. The radio signal classification method according to claim 2, characterized in that: The acquiring of radio signal data and processing of the radio signal data using the signal classification optimization model to obtain radio signal modulation information includes: S31, receiving and acquiring radio signal data in real time; S32, preprocessing the radio signal data to obtain preprocessed signal data; S33, based on the signal classification optimization model, processing the pre-processed signal data to obtain radio signal modulation information.

7. The radio signal classification method according to claim 6, characterized in that: The step of processing the preprocessed signal data based on the signal classification optimization model to obtain radio signal modulation information includes: S3301, using the data convolution processing layer, performing convolution processing on the preprocessed signal data to obtain first processed data; S3302, using the batch normalization layer, normalize the first processed data to obtain second processed data; S3303, using the first function processing layer, performing calculation processing on the second processed data to obtain third processed data; S3304, using the random dropout layer, generalize the third processed data to obtain fourth processed data; S3305, using the first long short-term memory layer, processing the fourth processed data to obtain fifth processed data; S3306, using the second function processing layer, performing calculation processing on the fifth processed data to obtain sixth processed data; S3307, using the second long short-term memory layer, processing the sixth processed data to obtain seventh processed data; S3308, using the third function processing layer, performing calculation processing on the seventh processed data to obtain eighth processed data; S3309, using the third long short-term memory layer, processing the eighth processed data to obtain ninth processed data; S3310, using the fourth function processing layer, performing calculation processing on the ninth processed data to obtain tenth processed data; S3311 uses the first fully connected layer to process the tenth processed data to obtain eleventh processed data; S3312, using the fifth function processing layer, performing calculation processing on the eleventh processed data to obtain twelfth processed data; S3313: Use the second fully connected layer to process the twelfth processed data to obtain radio signal modulation information.

8. A radio signal classification device, characterized in that: The device comprises: Data acquisition module, training processing module and recognition processing module; The data acquisition module is used to acquire the original data set; The training processing module is used to use the original data set to train the signal classification model to obtain a signal classification optimization model; The identification and processing module is used to obtain radio signal data, and process the radio signal data using the signal classification optimization model to obtain radio signal modulation information.

9. A radio signal classification device, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the radio signal classification method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the radio signal classification method according to any one of claims 1 to 7.

Images