Communication radiation source individual identification method, device, equipment and storage medium
By modal decomposing and demixing the signals to be detected by the communication radiation source, screening and merging independent signals, the problem of complex environmental noise affecting the recognition accuracy is solved, and higher recognition accuracy and robustness are achieved.
Patent Information
- Application Number
- CN202211418456.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-11-14
- Publication Date
- 2025-03-07
- Estimated Expiration
- 2042-11-14
AI Technical Summary
The existing communication radiation source individual identification technology is difficult to effectively extract information under complex and changing environmental noise conditions, resulting in inaccurate identification results and inability to meet actual needs.
By extracting the real and imaginary signals from the signals to be detected, modal decomposition and demixing are performed, independent signals with low degree of chaos are selected, combined into effective signals, and individual identification of communication radiation sources is performed.
The robustness and accuracy of individual recognition of communication radiation sources is improved, and the signal-to-noise ratio is improved by removing complex noise, ensuring the stability of the identification results.
Smart Images
Figure CN115865222B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of communication technology, and more specifically, to a method, device, equipment and storage medium for identifying individual communication radiation sources. Background Art
[0002] Communication radiation source individual identification is to extract the essential difference information of different communication radiation sources from the received signal through signal processing methods, so as to distinguish the individual communication radiation sources. Existing communication radiation source individual identification technologies include individual identification methods based on traditional feature extraction and individual identification methods based on time-frequency feature extraction.
[0003] The existing communication radiation source individual identification technology can effectively perform individual identification when the signal-to-noise ratio is high and the noise is steady-state. However, the actual propagation environment is often accompanied by complex and changeable environmental noise, which seriously affects the extraction of effective information and the final identification results, resulting in the identification results being unable to meet actual requirements.
[0004] Therefore, how to improve the robustness and accuracy of individual identification of communication radiation sources has become a technical problem that needs to be solved urgently. Summary of the invention
[0005] In view of this, the present application provides a method, apparatus, device and storage medium for individual identification of communication radiation sources to improve the robustness and accuracy of individual identification of communication radiation sources.
[0006] In order to achieve the above objectives, the proposed solution is as follows:
[0007] A method for identifying an individual communication radiation source, comprising:
[0008] Extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected;
[0009] Performing modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component;
[0010] Demixing the plurality of intrinsic mode function components to obtain a plurality of independent signals;
[0011] Based on the degree of confusion of each independent signal, a candidate independent signal is screened out from the plurality of independent signals; the degree of confusion of the candidate independent signal is less than the degree of confusion of non-candidate independent signals among the plurality of independent signals;
[0012] Merging candidate independent signals screened based on different target signal components to obtain a target effective signal;
[0013] The communication radiation source is individually identified based on the target effective signal.
[0014] In the above method, preferably, performing modal decomposition on the target signal component comprises:
[0015] Obtain all local maximum points and all local minimum points of the target signal component;
[0016] Fitting an upper envelope of the target signal component based on all the local maximum points, and fitting a lower envelope of the target signal component based on all the local minimum points;
[0017] Obtaining a detail component, wherein the detail component is a difference between the target signal component and a mean curve; the mean curve is a mean of the upper envelope and the lower envelope;
[0018] If the detail component belongs to the intrinsic mode function and the mean value of the detail component is less than a threshold value, the detail component is saved and the remaining signal is subjected to modal decomposition; otherwise, the detail component is subjected to modal decomposition until the modal decomposition termination condition is met; the remaining signal is the signal after removing the saved detail component from the target signal component.
[0019] In the above method, preferably, the step of satisfying the end condition of modal decomposition includes:
[0020] The residual signal is a monotonic function.
[0021] In the above method, preferably, the unmixing of the plurality of eigenmode function components comprises:
[0022] The plurality of eigenmode function components are demixed using an independent component analysis method.
[0023] In the above method, preferably, the step of selecting a candidate independent signal from the plurality of independent signals based on the degree of confusion of each independent signal comprises:
[0024] Calculate the mean of the chaos levels of all independent signals;
[0025] For each independent signal, if the confusion degree of the independent signal is less than or equal to the mean value, the independent signal is determined as a candidate independent signal.
[0026] In the above method, preferably, the step of selecting a candidate independent signal from the plurality of independent signals based on the degree of confusion of each independent signal comprises:
[0027] For each independent signal, a power disorder degree of the independent signal is obtained, wherein the power disorder degree is the difference between a result of performing an exponential operation on the disorder degree of the independent signal and the first target value as a base and a second target value;
[0028] Calculate the mean of the power disorder of all independent signals;
[0029] For each independent signal, if the power disorder of the independent signal is less than or equal to the mean value, the independent signal is determined as a candidate independent signal.
[0030] In the above method, preferably, the individual identification of the communication radiation source based on the target effective signal includes:
[0031] The target valid signal is processed by a pre-trained classification model to obtain an output result of the classification model, and the output result represents whether the target valid signal belongs to each individual communication radiation source.
[0032] In the above method, preferably, the step of merging the candidate independent signals screened out based on different target signal components comprises:
[0033] The candidate independent signals screened based on the same target signal component are superimposed to obtain the effective signal component corresponding to the same target signal component;
[0034] According to the time sequence and the order of the real part in the odd-numbered positions and the imaginary part in the even-numbered positions, the effective signal components corresponding to different target signal components are spliced to obtain the target effective signal.
[0035] A communication radiation source individual identification device, comprising:
[0036] An extraction module, used for extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected;
[0037] A modal decomposition module, used for performing modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component;
[0038] An unmixing module, used for unmixing the plurality of intrinsic mode function components to obtain a plurality of independent signals;
[0039] A screening module, configured to screen out a candidate independent signal from the plurality of independent signals based on the degree of confusion of each independent signal; the degree of confusion of the candidate independent signal being less than the degree of confusion of a non-candidate independent signal from the plurality of independent signals;
[0040] A merging module, used to merge candidate independent signals screened based on different target signal components to obtain a target valid signal;
[0041] An identification module is used to identify individual communication radiation sources based on the target effective signal.
[0042] A communication radiation source individual identification device, comprising a memory and a processor;
[0043] The memory is used to store programs;
[0044] The processor is used to execute the program to implement each step of the communication radiation source individual identification method as described in any one of the above items.
[0045] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements each step of the method for identifying an individual communication radiation source as described in any one of the above items.
[0046] It can be seen from the above technical scheme that the communication radiation source individual identification method, device, equipment and storage medium provided by the embodiment of the present application extract two target signal components from the signal to be detected, which are the real signal and the imaginary signal of the signal to be detected; modal decomposition of the target signal component is performed to obtain several intrinsic mode function components of the target signal component; several intrinsic mode function components are unmixed to obtain several independent signals; based on the degree of confusion of each independent signal, candidate independent signals are screened out from several independent signals; the degree of confusion of the candidate independent signal is less than the degree of confusion of the non-candidate independent signal in several independent signals; the candidate independent signals screened out based on different target signal components are merged to obtain a valid signal; and individual identification of the communication radiation source is performed based on the valid signal. The present application first performs modal decomposition and unmixing on the target signal component, which can separate the individual information of the communication radiation source from the complex environmental noise. Therefore, the independent signal obtained by unmixing contains the individual signal of the communication radiation source and the noise signal. Subsequently, the noise is filtered out based on the degree of confusion of the independent signal, and then the target valid signal is obtained, and the individual identification of the communication radiation source is performed based on the target valid signal. Since the complex and changeable noise is filtered out, the obtained target effective signal is guaranteed to be in a stable state and the signal-to-noise ratio is improved, thereby improving the accuracy and robustness of individual identification of communication radiation sources. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0048] Figure 1 A flowchart of an implementation of the communication radiation source individual identification method disclosed in an embodiment of the present application;
[0049] Figure 2 A flowchart for implementing modal decomposition of target signal components disclosed in an embodiment of the present application;
[0050] Figure 3A flowchart for implementing the method of screening out candidate independent signals from a plurality of independent signals based on the degree of confusion of each independent signal disclosed in an embodiment of the present application;
[0051] Figure 4 Another implementation flow chart of screening out candidate independent signals from a number of independent signals based on the degree of confusion of each independent signal disclosed in an embodiment of the present application;
[0052] Figure 5 A flowchart for implementing the merging of candidate independent signals screened based on different target signal components disclosed in an embodiment of the present application;
[0053] Figure 6 A schematic diagram of the structure of a communication radiation source individual identification device disclosed in an embodiment of the present application;
[0054] Figure 7 This is a hardware structure block diagram of the communication radiation source individual identification device disclosed in an embodiment of the present application. DETAILED DESCRIPTION
[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0056] In the physical world, the propagation of radiation source signals is often accompanied by various complex environments and noises, which makes the individual identification of communication radiation sources poorly robust and accurate, making it difficult to meet the actual needs of modern society. In order to improve the accuracy and robustness of individual identification of communication radiation sources, this application is proposed.
[0057] like Figure 1 As shown, a flowchart of an implementation method of the communication radiation source individual identification method provided in an embodiment of the present application may include:
[0058] Step S101: extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected.
[0059] The signal to be detected is an IQ signal collected by a signal acquisition device. The IQ signal includes a real signal and an imaginary signal. The present application extracts the real signal from the IQ signal as a target signal component and extracts the imaginary signal from the IQ signal as another target signal component.
[0060] Step S102: performing modal decomposition on the target signal component to obtain a number of intrinsic mode function components of the target signal component.
[0061] The present application processes the two target signal components in the same manner, that is, steps S102 to S104 are performed on the extracted real signal, and steps S102 to S104 are also performed on the extracted imaginary signal.
[0062] Optionally, the target signal component may be modally decomposed by any of the following modal decomposition methods:
[0063] Empirical Mode Decomposition (EMD), Ensemble Empirical Mode Decomposition (EEMD), local characteristic scale decomposition (LCD), LMD, VMD (Variational mode decomposition)EMD, EEMD, LCD (local characteristic scale decomposition), local mean decomposition (LMD), variational mode decomposition (VMD).
[0064] Step S103: Demixing a plurality of intrinsic mode function components to obtain a plurality of independent signals.
[0065] The several intrinsic mode function components obtained by modal decomposition are not mutually independent signals. Therefore, it is necessary to unmix the several intrinsic mode function components to obtain several independent signals.
[0066] Optionally, independent component analysis (ICA) may be used to unmix several intrinsic mode function components to obtain several independent signals. Assuming that there are N intrinsic mode function components, the N intrinsic mode function components are unmixed to obtain N independent signals.
[0067] After the target signal component is processed in steps S102-S103, the individual information of the communication radiation source in the target signal component can be separated from the environmental noise. That is to say, several independent signals contain both individual signals of the communication radiation source and noise signals, and the noise signals need to be filtered out later.
[0068] Step S104: based on the confusion degree of each independent signal, select a candidate independent signal from the plurality of independent signals; the confusion degree of the candidate independent signal is less than the confusion degree of the non-candidate independent signal from the plurality of independent signals.
[0069] The degree of chaos of a signal can be characterized by any of the following indicators: approximate entropy, sample entropy, and fuzzy entropy. These three indicators are used to evaluate the degree of chaos between the front and back parts of a waveform, or in other words, to evaluate the repeatability of the waveform. The larger the entropy value, the more frequencies there are in the waveform, and the smaller the entropy value, the fewer frequencies there are in the waveform.
[0070] Taking fuzzy entropy as an example, fuzzy entropy (FuzzyEn) measures the probability of a new pattern. The larger the value of fuzzy entropy, the greater the probability of a new pattern, the worse the representation repeatability, that is, the greater the sequence complexity. Compared with the stability of individual information, noise is non-stationary and will appear or disappear with the change of various factors such as time and environment, which will cause the overall complexity of the entire signal to increase. Therefore, based on fuzzy entropy, independent signals belonging to noise signals can be filtered out to obtain candidate independent signals.
[0071] Step S105: Merge the candidate independent signals screened out based on different target signal components to obtain a target valid signal.
[0072] The candidate independent signals obtained based on the same target signal component are components of the same target signal component. Therefore, the candidate independent signals obtained based on the same target signal component need to be merged to obtain the valid signal component corresponding to the same target signal component.
[0073] The effective signal components corresponding to different target signal components are combined to obtain the effective signal in the signal to be detected, that is, the target effective signal.
[0074] Step S106: performing individual identification of communication radiation sources based on the target effective signal.
[0075] Based on the effective signal in the combined signal to be detected, the communication radiation source individual is identified to determine the communication radiation source individual to which the signal to be detected belongs.
[0076] The communication radiation source individual identification method provided by the embodiment of the present application extracts two target signal components from the signal to be detected, first performs modal decomposition and unmixing on the target signal components, and can separate the communication radiation source individual information from the complex environmental noise. Therefore, the independent signal obtained by unmixing contains the communication radiation source individual signal and the noise signal. Subsequently, the noise is filtered out based on the degree of confusion of the signal, and then the target effective signal is obtained, and the communication radiation source individual identification is performed based on the target effective signal. Since the complex and changeable noise is filtered out, it is ensured that the obtained target effective signal is in a stable state and the signal-to-noise ratio is improved, thereby improving the accuracy and robustness of the communication radiation source individual identification.
[0077] In an optional embodiment, the mean empirical mode decomposition (MEMD) method can be used to perform modal decomposition on the target signal component. MEMD is an improved method designed by the present application based on EMD. Based on this, a flow chart for implementing modal decomposition of the target signal component is shown in FIG. Figure 2 As shown, it may include:
[0078] Step S201: Acquire all local maximum points and all local minimum points of the target signal component.
[0079] The target signal component is usually a discrete signal, and each preset number of signal points can be regarded as a local signal to obtain the maximum and minimum points of the local signal. As an example, each continuous K signal points can be regarded as a local signal, where K is an integer greater than 2.
[0080] Step S202: fitting the upper envelope of the target signal component based on all local maximum points, and fitting the lower envelope of the target signal component based on all local minimum points.
[0081] As an example, an interpolation method may be used to interpolate all local maximum points to obtain an upper envelope, and an interpolation method may be used to interpolate all local minimum points to obtain a lower envelope.
[0082] The interpolation method may include but is not limited to any of the following: cubic spline interpolation method, quartic spline interpolation method, and quintic spline interpolation method.
[0083] Step S203: Obtain detail components, where the detail components are the difference between the target signal components and the mean curve; the mean curve is the mean of the upper envelope and the lower envelope.
[0084] In this application, the upper envelope (denoted as X max ) and the lower envelope (denoted as X min ) to find the mean value and obtain the mean curve (denoted as X mean ), which can be expressed as:
[0085] X mean =(X max +X min ) / 2
[0086] If the target signal component is recorded as X t , and the detail component is recorded as D t , then we have: D t =X t -X mean .
[0087] Step S204: Determine whether the detail component belongs to the intrinsic mode function and the mean of the detail component is less than the threshold. If the judgment result is yes, execute step S205, that is, save the detail component and perform modal decomposition on the remaining signal; if the judgment result is no, enter step S206, that is, perform modal decomposition on the detail component until the modal decomposition end condition is met; wherein the remaining signal is the signal after removing the saved detail component from the target signal component.
[0088] Optionally, if the detail component satisfies the definition of an intrinsic mode function, it is determined that the detail component belongs to an intrinsic mode function component. The definition of an intrinsic mode function is: an intrinsic mode function (IMF) must satisfy the following two conditions: (1) the number of local extreme points and zero crossing points of the function must be equal or differ by at most one in the entire time range; (2) at any time point, the envelope of the local maximum value (upper envelope) and the envelope of the local minimum value (lower envelope) must average zero.
[0089] The mean value of the detail component is the mean value of the value of the detail component at each moment.
[0090] In the present application, if the detail component belongs to the intrinsic mode function and the mean value of the detail component is less than the threshold value, it can be determined that the detail component is an intrinsic mode function component, and the detail component is saved. If the detail component does not belong to the intrinsic mode function, and / or the mean value of the detail component is greater than or equal to the threshold value, it means that the detail component is not an intrinsic mode function component, and the detail component is prohibited from being saved.
[0091] Step S205: Save the detail components and perform modal decomposition on the remaining signal.
[0092] When the detail component belongs to the eigenmode function and the mean of the detail component is less than the threshold, in addition to saving the detail component, the remaining signal is also modally decomposed, that is, the remaining signal is used as a new target signal component, and the above-mentioned steps S201-S204 are executed on the new target signal component.
[0093] The residual signal is the difference between the target signal component (the target signal component here is the target signal component extracted from the signal to be detected) and all the saved detail components.
[0094] Assume that after the latest execution of step S205, a total of m detail components are saved, namely D t1 ~D tm , then the remaining signal (denoted as D remain ) is the difference between the target signal component and the sum of the m detail components, which can be expressed as:
[0095] D remain =X t -(D t1 +D t2 +D t3 +……+D tm ).
[0096] Step S206: performing modal decomposition on the detail components.
[0097] When the detail component does not belong to the eigenmode function and / or the mean value of the detail component is greater than or equal to the threshold, in addition to prohibiting the saving of the detail component, the detail component is also used as a new target signal component, and the above-mentioned steps S201-S204 are performed on the new target signal component.
[0098] In an optional embodiment, the above-mentioned condition for ending the modal decomposition may include: the residual signal is a monotonic function. That is, if the waveform of the residual signal belongs to a curve of a monotonic function, it is determined that the condition for ending the modal decomposition is met.
[0099] In an optional embodiment, a flowchart for implementing the above-mentioned screening of candidate independent signals from a number of independent signals based on the degree of confusion of each independent signal is as follows: Figure 3 As shown, it may include:
[0100] Step S301: Calculate the mean of the confusion levels of all independent signals.
[0101] Step S302: For each independent signal, if the degree of confusion of the independent signal is less than or equal to the mean value obtained in step S301, the independent signal is determined as a candidate independent signal.
[0102] If the degree of confusion of the independent signal is less than or equal to the mean value obtained in step S301, it means that the probability of the independent signal being a valid signal is relatively high, and therefore, it can be used as a candidate independent signal. Further, if the degree of confusion of the independent signal is greater than the mean value obtained in step S301, it means that the probability of the independent signal being noise is relatively high, and therefore, it cannot be used as a candidate independent signal.
[0103] In an optional embodiment, another implementation flow chart of selecting candidate independent signals from a number of independent signals based on the degree of confusion of each independent signal is as follows: Figure 4As shown, it may include:
[0104] Step S401: for each independent signal, obtain the power chaos degree of the independent signal, where the power chaos degree is the difference between the result of exponential operation with the chaos degree of the independent signal as the index and the first target value as the base and the second target value.
[0105] For any independent signal, assuming that the disorder degree of the independent signal is Doc, the power disorder degree of the independent signal is PDoc, the first target value is a, and the second target value is b, then:
[0106] PDoc=a Doc -b
[0107] As an example, a = 2, b = 1. Optionally, a may also have other values, such as a = 3.
[0108] In order to better distinguish valid signals from noise, the present application exponentiates the chaos degree, and the purpose of subtracting 1 from the exponential result is to eliminate the added value after the exponential result.
[0109] Step S402: Calculate the mean of the power chaos of all independent signals.
[0110] Step S403: For each independent signal, if the power disorder degree of the independent signal is less than or equal to the mean value calculated in step S402, the independent signal is determined as a candidate independent signal.
[0111] If the power disorder degree of the independent signal is less than or equal to the mean value obtained in step S402, it means that the probability of the independent signal being a valid signal is relatively high, and therefore, it can be used as a candidate independent signal. Further, if the power disorder degree of the independent signal is greater than the mean value obtained in step S402, it means that the probability of the independent signal being noise is relatively high, and therefore, it cannot be used as a candidate independent signal.
[0112] The present application obtains a power disorder degree with better discrimination by taking an exponent of the disorder degree, and filters out noise signals based on the power disorder degree, thereby improving the accuracy of noise filtering.
[0113] In an optional embodiment, an implementation method of the above-mentioned communication radiation source individual identification based on the target effective signal may be:
[0114] The target valid signal is processed by a pre-trained classification model to obtain an output result of the classification model, and the output result represents whether the target valid signal belongs to each individual communication radiation source.
[0115] Typically, the classification model outputs the probability that the target valid signal belongs to each individual communication radiation source, and the probability that the target valid signal belongs to each individual communication radiation source can be compared with a probability threshold, and if the probability that the target valid signal belongs to the first individual communication radiation source is greater than the probability threshold, it is determined that the target valid signal belongs to the first individual communication radiation source. The first individual communication radiation source is any individual communication radiation source in the modeling unit of the classification model.
[0116] Optionally, the classification model may be a Resnet classifier or other types of classifiers, which are not specifically limited here.
[0117] In an optional embodiment, the sample used to train the classification model is a target valid signal obtained in advance by the aforementioned method, and the label of the sample is an identifier of the individual communication radiation source to which the target valid signal belongs.
[0118] In an optional embodiment, a flowchart for implementing the merging of the candidate independent signals screened out based on different target signal components is as follows: Figure 5 As shown, it may include:
[0119] Step S501: superimposing candidate independent signals screened out based on the same target signal component to obtain a valid signal component corresponding to the same target signal component.
[0120] Optionally, the candidate independent signals screened out based on the same target signal component may be added together to obtain a valid signal component corresponding to the same target signal component.
[0121] Step S502: according to the time sequence and the order of the real part in the odd position and the imaginary part in the even position, the effective signal components corresponding to different target signal components are spliced to obtain the target effective signal.
[0122] Each discrete signal point in the target signal component is arranged in chronological order, so the obtained effective signal component is also arranged in chronological order. Based on this, the signal points in the effective signal component corresponding to the real signal of the signal to be detected (recorded as the first effective signal component) can be used as the odd-numbered signal points of the target effective signal, and the signal points in the effective signal component corresponding to the imaginary signal of the signal to be detected (recorded as the second effective signal component) can be used as the even-numbered signal points of the target effective signal. The signal points in the first effective signal component and the second effective signal component are arranged in chronological order to obtain the target effective signal.
[0123] For example, the first effective signal component contains 4 signal points, which are s11, s12, s13, and s14 in chronological order, and the second effective signal component contains 4 signal points, which are s21, s22, s23, and s24 in chronological order. The target effective signal obtained by splicing the first effective signal component and the second effective signal component is: s11, s21, s12, s22, s13, s23, s14, and s24.
[0124] Corresponding to the method embodiment, the embodiment of the present application further provides a communication radiation source individual identification device. A structural schematic diagram of the communication radiation source individual identification device provided in the embodiment of the present application is as follows: Figure 6 As shown, it may include:
[0125] Extraction module 601, modal decomposition module 602, unmixing module 603, screening module 604, merging module 605 and identification module 606; wherein,
[0126] The extraction module 601 is used to extract two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected;
[0127] The modal decomposition module 602 is used to perform modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component;
[0128] The unmixing module 603 is used to unmix the plurality of intrinsic mode function components to obtain a plurality of independent signals;
[0129] The screening module 604 is used to screen out a candidate independent signal from the plurality of independent signals based on the degree of confusion of each independent signal; the degree of confusion of the candidate independent signal is less than the degree of confusion of the non-candidate independent signal from the plurality of independent signals;
[0130] The merging module 605 is used to merge the candidate independent signals screened based on different target signal components to obtain a target valid signal;
[0131] The identification module 606 is used to perform individual identification of communication radiation sources based on the target effective signal.
[0132] The communication radiation source individual identification device provided by the embodiment of the present application extracts two target signal components from the signal to be detected, first performs modal decomposition and unmixing on the target signal components, and can separate the communication radiation source individual information from the complex environmental noise. Therefore, the independent signal obtained by unmixing contains the communication radiation source individual signal and the noise signal. Subsequently, the noise is filtered out based on the degree of confusion of the signal, and then the target effective signal is obtained, and the communication radiation source individual identification is performed based on the target effective signal. Since the complex and changeable noise is filtered out, it is ensured that the obtained target effective signal is in a stable state and the signal-to-noise ratio is improved, thereby improving the accuracy and robustness of the communication radiation source individual identification.
[0133] In an optional embodiment, the modal decomposition module 602 may include:
[0134] An extreme value acquisition module, used to acquire all local maximum points and all local minimum points of the target signal component;
[0135] A fitting module, used for fitting an upper envelope of the target signal component based on all the local maximum points, and fitting a lower envelope of the target signal component based on all the local minimum points;
[0136] A detail acquisition module, used for acquiring a detail component, wherein the detail component is a difference between the target signal component and a mean curve; the mean curve is a mean of the upper envelope and the lower envelope;
[0137] A control module is used to save the detail component and perform modal decomposition on the remaining signal if the detail component belongs to an eigenmode function and the mean value of the detail component is less than a threshold value; otherwise, perform modal decomposition on the detail component until the modal decomposition end condition is met; the remaining signal is the signal after removing the saved detail component from the target signal component.
[0138] In an optional embodiment, the satisfying of the modal decomposition termination condition includes:
[0139] The residual signal is a monotonic function.
[0140] In an optional embodiment, the demixing module 603 is used to:
[0141] The plurality of eigenmode function components are demixed using an independent component analysis method.
[0142] In an optional embodiment, the screening module 604 is used to:
[0143] Calculate the mean of the chaos levels of all independent signals;
[0144] For each independent signal, if the confusion degree of the independent signal is less than or equal to the mean value, the independent signal is determined as a candidate independent signal.
[0145] In an optional embodiment, the screening module 604 is used to:
[0146] For each independent signal, a power disorder degree of the independent signal is obtained, wherein the power disorder degree is the difference between a result of performing an exponential operation on the disorder degree of the independent signal and the first target value as a base and a second target value;
[0147] Calculate the mean of the power disorder of all independent signals;
[0148] For each independent signal, if the power disorder of the independent signal is less than or equal to the mean value, the independent signal is determined as a candidate independent signal.
[0149] In an optional embodiment, the identification module 606 is used to:
[0150] The target valid signal is processed by a pre-trained classification model to obtain an output result of the classification model, and the output result represents whether the target valid signal belongs to each individual communication radiation source.
[0151] In an optional embodiment, the merging module 605 includes:
[0152] A superposition module, used for superimposing candidate independent signals screened based on the same target signal component to obtain a valid signal component corresponding to the same target signal component;
[0153] The splicing module is used to splice the effective signal components corresponding to different target signal components in the order of time and the order of the real part in the odd position and the imaginary part in the even position to obtain the target effective signal.
[0154] The communication radiation source individual identification device provided in the embodiment of the present application can be applied to communication radiation source individual identification devices, such as PC terminals, cloud platforms, servers and server clusters. Figure 7 The hardware structure diagram of the communication radiation source individual identification device is shown. Figure 7 , the hardware structure of the communication radiation source individual identification device may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
[0155] In the embodiment of the present application, the number of the processor 1, the communication interface 2, the memory 3, and the communication bus 4 is at least one, and the processor 1, the communication interface 2, and the memory 3 communicate with each other through the communication bus 4;
[0156] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention, etc.;
[0157] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;
[0158] The memory stores a program, and the processor can call the program stored in the memory, wherein the program is used to:
[0159] Extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected;
[0160] Performing modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component;
[0161] Demixing the plurality of intrinsic mode function components to obtain a plurality of independent signals;
[0162] Based on the degree of confusion of each independent signal, a candidate independent signal is screened out from the plurality of independent signals; the degree of confusion of the candidate independent signal is less than the degree of confusion of non-candidate independent signals among the plurality of independent signals;
[0163] Merging candidate independent signals screened based on different target signal components to obtain a target effective signal;
[0164] The communication radiation source is individually identified based on the target effective signal.
[0165] Optionally, the detailed functions and extended functions of the program may refer to the above description.
[0166] The embodiment of the present application further provides a storage medium, which may store a program suitable for execution by a processor, wherein the program is used to:
[0167] Extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected;
[0168] Performing modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component;
[0169] Demixing the plurality of intrinsic mode function components to obtain a plurality of independent signals;
[0170] Based on the degree of confusion of each independent signal, a candidate independent signal is screened out from the plurality of independent signals; the degree of confusion of the candidate independent signal is less than the degree of confusion of non-candidate independent signals among the plurality of independent signals;
[0171] Merging candidate independent signals screened based on different target signal components to obtain a target effective signal;
[0172] The communication radiation source is individually identified based on the target effective signal.
[0173] Optionally, the detailed functions and extended functions of the program may refer to the above description.
[0174] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0175] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.
[0176] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0177] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0178] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0179] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0180] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0181] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for identifying individual communication radiation sources, characterized in that: include: Extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected; Performing modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component; Demixing the plurality of intrinsic mode function components to obtain a plurality of independent signals; Based on the degree of confusion of each independent signal, a candidate independent signal is screened out from the plurality of independent signals, and a non-candidate independent signal belonging to a noise signal is filtered out; the degree of confusion of the candidate independent signal is less than the degree of confusion of the non-candidate independent signal among the plurality of independent signals; Merging candidate independent signals screened out based on different target signal components, including: superimposing candidate independent signals screened out based on the same target signal component to obtain valid signal components corresponding to the same target signal component; splicing valid signal components corresponding to different target signal components in chronological order and in the order of real parts in odd positions and imaginary parts in even positions to obtain a target valid signal; The communication radiation source is individually identified based on the target effective signal.
2. The method according to claim 1, characterized in that The performing modal decomposition on the target signal component comprises: Obtain all local maximum points and all local minimum points of the target signal component; Fitting an upper envelope of the target signal component based on all the local maximum points, and fitting a lower envelope of the target signal component based on all the local minimum points; Obtaining a detail component, wherein the detail component is a difference between the target signal component and a mean curve; the mean curve is a mean of the upper envelope and the lower envelope; If the detail component belongs to the intrinsic mode function and the mean value of the detail component is less than a threshold value, the detail component is saved and the remaining signal is subjected to modal decomposition; otherwise, the detail component is subjected to modal decomposition until the modal decomposition termination condition is met; the remaining signal is the signal after removing the saved detail component from the target signal component.
3. The method according to claim 2, characterized in that The condition for ending the modal decomposition is satisfied, including: The residual signal is a monotonic function.
4. The method according to claim 2, characterized in that: The demixing of the plurality of eigenmode function components comprises: The plurality of eigenmode function components are demixed using an independent component analysis method.
5. The method according to claim 1, characterized in that The step of selecting a candidate independent signal from the plurality of independent signals based on the degree of confusion of each independent signal comprises: Calculate the mean of the chaos levels of all independent signals; For each independent signal, if the confusion degree of the independent signal is less than or equal to the mean value, the independent signal is determined as a candidate independent signal.
6. The method according to claim 1, characterized in that The step of selecting a candidate independent signal from the plurality of independent signals based on the degree of confusion of each independent signal comprises: For each independent signal, a power disorder degree of the independent signal is obtained, wherein the power disorder degree is the difference between a result of performing an exponential operation on the disorder degree of the independent signal and the first target value as a base and a second target value; Calculate the mean of the power disorder of all independent signals; For each independent signal, if the power disorder of the independent signal is less than or equal to the mean value, the independent signal is determined as a candidate independent signal.
7. The method according to claim 1, characterized in that The individual identification of the communication radiation source based on the target effective signal includes: The target valid signal is processed by a pre-trained classification model to obtain an output result of the classification model, and the output result represents whether the target valid signal belongs to each individual communication radiation source.
8. A communication radiation source individual identification device, characterized in that: include: An extraction module, used for extracting two target signal components from the signal to be detected, which are respectively the real signal and the imaginary signal of the signal to be detected; A modal decomposition module, used for performing modal decomposition on the target signal component to obtain a plurality of intrinsic mode function components of the target signal component; An unmixing module, used for unmixing the plurality of intrinsic mode function components to obtain a plurality of independent signals; A screening module, used for screening out candidate independent signals from the plurality of independent signals based on the degree of confusion of each independent signal, and filtering out non-candidate independent signals belonging to noise signals; the degree of confusion of the candidate independent signal is less than the degree of confusion of the non-candidate independent signals from the plurality of independent signals; A merging module is used to merge the candidate independent signals screened based on different target signal components, including: superimposing the candidate independent signals screened based on the same target signal component to obtain the effective signal component corresponding to the same target signal component; splicing the effective signal components corresponding to different target signal components in the order of time and the order of the real part in the odd position and the imaginary part in the even position to obtain the target effective signal; An identification module is used to identify individual communication radiation sources based on the target effective signal.
9. A communication radiation source individual identification device, characterized in that: including memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the communication radiation source individual identification method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for identifying an individual communication radiation source according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Micro embedded UHF radio frequency identification anti-metal tag antenna
CN101533946A
Target radiation source individual recognition method
CN109307862A