CN117147966B - Electromagnetic spectrum signal energy anomaly detection method - Google Patents
Electromagnetic spectrum signal energy anomaly detection method Download PDFInfo
- Publication number
- CN117147966B CN117147966B CN202311110359.XA CN202311110359A CN117147966B CN 117147966 B CN117147966 B CN 117147966B CN 202311110359 A CN202311110359 A CN 202311110359A CN 117147966 B CN117147966 B CN 117147966B
- Authority
- CN
- China
- Prior art keywords
- energy
- variance
- signal
- processing
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001228 spectrum Methods 0.000 title claims abstract description 163
- 238000001514 detection method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 74
- 230000005856 abnormality Effects 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 29
- 230000008859 change Effects 0.000 claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 34
- 230000003595 spectral effect Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 6
- 230000002547 anomalous effect Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 14
- 230000006870 function Effects 0.000 description 18
- 230000008569 process Effects 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010219 correlation analysis Methods 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/318—Received signal strength
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R23/00—Arrangements for measuring frequencies; Arrangements for analysing frequency spectra
- G01R23/16—Spectrum analysis; Fourier analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Mathematical Optimization (AREA)
- Computer Networks & Wireless Communication (AREA)
- Emergency Management (AREA)
- Computing Systems (AREA)
- Electromagnetism (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Business, Economics & Management (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for detecting electromagnetic spectrum signal energy abnormality, which comprises the following steps: before an important monitoring task is executed, acquiring electromagnetic spectrum signals; processing electromagnetic spectrum signals to obtain k frequency spectrums of typical frequencies, and processing the k frequency spectrums of typical frequencies to obtain a signal energy fluctuation threshold; when an important monitoring task is executed, calculating the energy fluctuation variance of the electromagnetic spectrum signal in real time; performing spectrum energy fluctuation change comparison detection on the energy fluctuation variance and the signal energy fluctuation threshold to obtain a signal energy abnormality detection result; when the signal energy is abnormal, the energy fluctuation variance is processed to obtain energy abnormality degree information; and carrying out alarm processing according to the energy abnormality degree information. According to the invention, objective analysis of electromagnetic spectrum signal data and automatic detection of signal energy abnormality are realized, the discovery efficiency of important events causing signal change is improved, and the dimension of target intention analysis is increased.
Description
Technical Field
The invention relates to the technical field of electromagnetic spectrum space anomaly detection, in particular to an electromagnetic spectrum signal energy anomaly detection method.
Background
Mastering the activity of electromagnetic spectrum signals is an important activity in the field of electromagnetic spectrum space, and the advantages of the way and mode determine the analysis efficiency and accuracy. At present, the mastering of the activity condition of electromagnetic spectrum signals mainly depends on electronic reconnaissance aiming at an electronic target and mainly depends on equipment such as spectrum monitoring and the like aiming at a small-range radiation source, but along with the improvement of the capacity of the spectrum monitoring equipment, more distant signals including the signals of the electronic target can be found. The spectrum monitoring device has the advantages that electromagnetic spectrum signals can be analyzed and processed from multiple dimensions such as time, space, frequency, energy, spectrum and the like, and the energy domain is an important element of the spectrum signals, so that the weakness of the traditional electronic reconnaissance mode in energy domain analysis and processing can be overcome. The electromagnetic spectrum signal observed by the spectrum monitoring device changes drastically, and the most direct manifestation is that the signal energy fluctuates greatly, such as: the occurrence and disappearance of signals, the enhancement and reduction of signal power and the like, and the large-amplitude fluctuation of the signal energy is uniformly defined as signal energy abnormality, and the abnormality is often used for indicating the occurrence of important events. The discovery of electromagnetic spectrum signal energy anomalies in the prior art often depends on human experience, and is specifically implemented in the following two aspects:
and manually analyzing the intensity of the change of the energy amplitude of the electromagnetic spectrum signal to judge the abnormality. The method mainly uses parameters such as frequency, bandwidth, modulation mode, direction, signal level and the like measured by spectrum monitoring equipment to compare with historical data, observes signal variation amplitude and duration, and then manually judges whether the signal is abnormal or not. The correctness of judging the signal energy abnormality in this way depends on human experience, and a long time of manual attendance is required to find the spectrum energy abnormality.
And setting an electromagnetic spectrum signal energy threshold to judge out of standard abnormality. The method is based on signal spectrum acquired by spectrum monitoring equipment, an energy amplitude threshold is set according to experience, or a threshold is set according to historical average change condition of statistical signals, and if the threshold is exceeded, the abnormality is indicated. Compared with the previous manual analysis mode, the method has the advantages that the signal threshold is still required to be set according to the experience of people or the average statistical condition of data, and the accuracy of the threshold cannot be ensured; and the electromagnetic environment changes or the monitoring equipment is moved, the threshold needs to be reset, and the threshold cannot be automatically and adaptively adjusted.
Disclosure of Invention
The technical problem to be solved by the invention is to provide an electromagnetic spectrum signal energy anomaly detection method which is applied to detection processing of electromagnetic spectrum signal changes and can be used for objectively and automatically detecting and finding electromagnetic spectrum signal energy anomalies based on the characteristics of electromagnetic spectrum signal spectrum changes acquired by spectrum monitoring equipment.
In order to solve the technical problems, an embodiment of the invention discloses an electromagnetic spectrum signal energy anomaly detection method, which comprises the following steps:
s1, acquiring electromagnetic spectrum signals before executing important monitoring tasks;
S2, processing the electromagnetic spectrum signals to obtain k frequency spectrums with typical frequencies, wherein k is an integer;
s3, processing the frequency spectrums of the k typical frequencies to obtain a signal energy fluctuation threshold;
s4, when an important monitoring task is executed, calculating the energy fluctuation variance of the electromagnetic spectrum signal in real time;
s5, carrying out spectrum energy fluctuation change comparison detection on the energy fluctuation variance and the signal energy fluctuation threshold to obtain a signal energy abnormality detection result;
s6, when the signal energy is abnormal, the energy fluctuation variance is processed to obtain energy abnormality degree information;
and S7, carrying out alarm processing according to the energy abnormality degree information.
As an optional implementation manner, in an embodiment of the present invention, the processing the frequency spectrums of the k typical frequencies to obtain a signal energy fluctuation threshold includes:
S31, processing the frequency spectrums of the k typical frequencies to obtain a frequency spectrum energy square difference matrix;
S32, mapping the spectrum energy variance matrix to obtain spectrum energy variance image information;
S33, processing the spectrum energy variance image information to obtain the total fuzzy entropy of the image;
s34, processing the total fuzzy entropy of the image to obtain a signal energy fluctuation threshold.
In an alternative implementation manner, in an embodiment of the present invention, the processing the frequency spectrums of the k typical frequencies to obtain a spectrum energy square difference matrix includes:
Processing the frequency spectrums of the k typical frequencies by using a variance calculation model to obtain a frequency spectrum energy variance matrix;
The variance calculation model is as follows:
Where i=1, 2, …, k, M is the number of frames of the acquired electromagnetic spectrum signal, For the mi th frame of spectrum energy variance matrix, S mi (E) is mi th frame of spectrum of the i-th typical frequency,/>Is the spectral mean of k typical frequencies.
In an optional implementation manner, in an embodiment of the present invention, mapping the spectrum energy variance matrix to obtain spectrum energy variance image information includes:
Processing the spectrum energy square difference matrix to obtain an image gray value;
The image gray value is:
where mi=1, 2, …, M is the number of frames of the acquired electromagnetic spectrum signal, For the mi th frame of spectrum energy square difference matrix, l=256, x imi is the image gray value of the i typical frequency mi th frame;
k typical frequency image gray values form spectral energy variance image information;
the spectral energy variance image information is:
{xi1,xi2,…,xiM}
Where i=1, 2, …, k.
In an optional implementation manner, in an embodiment of the present invention, the processing the spectral energy variance image information to obtain a total blurred entropy of an image includes:
s331, processing the spectrum energy variance image information to obtain a fuzzy set matrix;
s332, processing the spectrum energy variance image information to obtain an image histogram;
s333, presetting a threshold value, and dividing an image histogram according to the threshold value to obtain a target image and a background image;
s334, processing the target image and the background image according to the fuzzy set matrix to obtain the conditional probability that the pixel belongs to the target image and the conditional probability that the pixel belongs to the background image;
S335, processing the conditional probability that the pixel belongs to the target image and the conditional probability that the pixel belongs to the background image to obtain the total fuzzy entropy of the image.
In an optional implementation manner, in an embodiment of the present invention, the processing the total fuzzy entropy of the image to obtain a signal energy fluctuation threshold includes:
S341, processing the total fuzzy entropy of the image to obtain the maximum fuzzy entropy and the average fuzzy entropy;
S342, processing the maximum fuzzy entropy and the average fuzzy entropy to obtain a heuristic function;
s343, processing the heuristic function to obtain an optimal fuzzy entropy;
S344, processing the optimal fuzzy entropy to obtain an image segmentation threshold;
s345, the image segmentation threshold is processed to obtain a signal energy fluctuation threshold.
As an optional implementation manner, in an embodiment of the present invention, the calculating, in real time, an energy fluctuation variance of an electromagnetic spectrum signal includes:
Calculating the energy fluctuation variance of the electromagnetic spectrum signal by using a real-time sliding window model;
The real-time sliding window model is as follows:
Where ni=t 0,t0+1,t0+2,…,N+t0 -1, the width of the window is N, the step size is denoted 1, Representing the variance of the energy fluctuation of the electromagnetic spectrum signal within the ith typical frequency t 0 window, S ni (E) is the spectrum within the ith typical frequency t 0 window,/>Is the spectral mean of k typical frequencies.
In an optional implementation manner, in an embodiment of the present invention, the detecting the energy fluctuation variance and the signal energy fluctuation threshold by comparing the spectral energy fluctuation change with each other to obtain signal energy anomaly detection information includes:
s51, recording the energy fluctuation variance in the current window and the energy fluctuation variance in the window before the current window by 1 step length, and obtaining a first energy fluctuation variance and a second energy fluctuation variance;
s52, carrying out frequency spectrum energy fluctuation change comparison detection on the first energy fluctuation variance and the second energy fluctuation variance and the signal energy fluctuation threshold to obtain signal energy abnormality detection information.
In an optional implementation manner, in an embodiment of the present invention, the comparing and detecting the spectral energy fluctuation changes of the first energy fluctuation variance and the second energy fluctuation variance with the signal energy fluctuation threshold to obtain a signal energy anomaly detection result includes:
S521, if the signal energy fluctuation threshold is greater than or equal to the first energy fluctuation variance and less than the second energy fluctuation variance, the signal energy of the current time window is greatly increased, and the signal energy abnormality detection result is signal energy abnormality;
S522, if the signal energy fluctuation threshold is greater than or equal to the second energy fluctuation variance and smaller than the first energy fluctuation variance, the signal energy of the current time window is greatly reduced, and the signal energy abnormality detection result is signal energy abnormality.
In an optional implementation manner, in an embodiment of the present invention, when the signal energy is abnormal, the processing the energy fluctuation variance to obtain energy abnormality degree information includes:
Processing the energy fluctuation variance to obtain a first energy fluctuation variance and a second energy fluctuation variance;
processing the first energy fluctuation variance and the second energy fluctuation variance by using an energy abnormality degree calculation model to obtain energy abnormality degree information;
The energy abnormality degree calculation model is as follows:
Wherein E 1 is energy abnormality degree information, For the second energy fluctuation variance,/>For the first energy fluctuation variance, i=1, 2, …, k, ni=t 0,t0+1,t0+2,…,N+t0 -1, the width of the window is N, t 0 is the position of the window, and k is the number of typical frequencies.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
(1) The invention provides an electromagnetic spectrum signal energy anomaly detection method, which realizes objective analysis of electromagnetic spectrum signal data and automatic detection of signal energy anomaly, and improves the discovery efficiency of important events causing signal change;
(2) A new evidence measure is provided for the analysis of the abnormal behaviors of the targets from the energy domain dimension, and the dimension of the target intention analysis is increased;
(3) So that the target frequency change detection extends from frequency point switching or operating mode change to change of frequency energy.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for detecting electromagnetic spectrum signal energy anomalies according to an embodiment of the present invention;
fig. 2 is a flowchart of another electromagnetic spectrum signal energy anomaly detection method according to an embodiment of the present invention.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, apparatus, article, or device that comprises a list of steps or elements is not limited to the list of steps or elements but may, in the alternative, include other steps or elements not expressly listed or inherent to such process, method, article, or device.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The invention discloses an electromagnetic spectrum signal energy anomaly detection method, which comprises the steps of acquiring an electromagnetic spectrum signal before an important monitoring task is executed; processing electromagnetic spectrum signals to obtain k frequency spectrums of typical frequencies, and processing the k frequency spectrums of typical frequencies to obtain a signal energy fluctuation threshold; when an important monitoring task is executed, calculating the energy fluctuation variance of the electromagnetic spectrum signal in real time; performing spectrum energy fluctuation change comparison detection on the energy fluctuation variance and the signal energy fluctuation threshold to obtain a signal energy abnormality detection result; when the signal energy is abnormal, the energy fluctuation variance is processed to obtain energy abnormality degree information; and carrying out alarm processing according to the energy abnormality degree information. According to the invention, objective analysis of electromagnetic spectrum signal data and automatic detection of signal energy abnormality are realized, the discovery efficiency of important events causing signal change is improved, and the dimension of target intention analysis is increased. The following will describe in detail.
Example 1
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for detecting an abnormal energy of an electromagnetic spectrum signal according to an embodiment of the present invention. The electromagnetic spectrum signal energy anomaly detection method described in fig. 1 is applied to a spectrum situation system to complete automatic detection of electromagnetic spectrum signal energy anomalies in real time, and provides powerful support for electromagnetic spectrum signal event correlation analysis, target frequency behavior and intention analysis. As shown in fig. 1, the method for detecting abnormal energy of the electromagnetic spectrum signal may include the following operations:
s1, acquiring electromagnetic spectrum signals before executing important monitoring tasks;
S2, processing the electromagnetic spectrum signals to obtain k frequency spectrums with typical frequencies, wherein k is an integer;
s3, processing the frequency spectrums of the k typical frequencies to obtain a signal energy fluctuation threshold;
s4, when an important monitoring task is executed, calculating the energy fluctuation variance of the electromagnetic spectrum signal in real time;
s5, carrying out spectrum energy fluctuation change comparison detection on the energy fluctuation variance and the signal energy fluctuation threshold to obtain a signal energy abnormality detection result;
s6, when the signal energy is abnormal, the energy fluctuation variance is processed to obtain energy abnormality degree information;
and S7, carrying out alarm processing according to the energy abnormality degree information.
Optionally, the processing the frequency spectrums of the k typical frequencies to obtain a signal energy fluctuation threshold includes:
S31, processing the frequency spectrums of the k typical frequencies to obtain a frequency spectrum energy square difference matrix;
S32, mapping the spectrum energy variance matrix to obtain spectrum energy variance image information;
S33, processing the spectrum energy variance image information to obtain the total fuzzy entropy of the image;
s34, processing the total fuzzy entropy of the image to obtain a signal energy fluctuation threshold.
Optionally, the processing the spectrums of the k typical frequencies to obtain a spectrum energy variance matrix includes:
Processing the frequency spectrums of the k typical frequencies by using a variance calculation model to obtain a frequency spectrum energy variance matrix;
The variance calculation model is as follows:
Where i=1, 2, …, k, M is the number of frames of the acquired electromagnetic spectrum signal, For the mi th frame of spectrum energy variance matrix, S mi (E) is mi th frame of spectrum of the i-th typical frequency,/>Is the spectral mean of k typical frequencies.
Optionally, the mapping the spectrum energy variance matrix to obtain spectrum energy variance image information includes:
Processing the spectrum energy square difference matrix to obtain an image gray value;
The image gray value is:
where mi=1, 2, …, M is the number of frames of the acquired electromagnetic spectrum signal, For the mi th frame of spectrum energy square difference matrix, l=256, x imi is the image gray value of the i typical frequency mi th frame;
k typical frequency image gray values form spectral energy variance image information;
the spectral energy variance image information is:
{xi1,xi2,…,xiM}
Where i=1, 2, …, k.
Optionally, the processing the spectral energy variance image information to obtain a total fuzzy entropy of the image includes:
s331, processing the spectrum energy variance image information to obtain a fuzzy set matrix;
s332, processing the spectrum energy variance image information to obtain an image histogram;
s333, presetting a threshold value, and dividing an image histogram according to the threshold value to obtain a target image and a background image;
the image histogram can be divided by taking the gray value at the valley bottom between the double peaks of the histogram as a threshold value to obtain a target image and a background image;
s334, processing the target image and the background image according to the fuzzy set matrix to obtain the conditional probability that the pixel belongs to the target image and the conditional probability that the pixel belongs to the background image;
S335, processing the conditional probability that the pixel belongs to the target image and the conditional probability that the pixel belongs to the background image to obtain the total fuzzy entropy of the image.
Optionally, the target image and the background image may be implemented by using a pulse coupled neural network model and a moth fire suppression algorithm, which includes the following steps:
step one: and initializing a moth fire suppression algorithm.
Setting the searching scale of the moths population, the initial flame quantity, the maximum iteration number, the current iteration number, the logarithmic spiral constant and the initial value of the variable number to be solved.
Step two: an initial population is generated.
The three parameters to be determined for the image segmentation of the pulse coupled neural network model are a connection coefficient, an amplitude coefficient and an attenuation coefficient, the value range of the connection coefficient is [0.0001,1], the value range of the attenuation coefficient is [0.1,1], and the value range of the amplitude coefficient is set as the upper limit and the lower limit of the gray value of the segmented image. Population size was set at 20.
Random generation of an initialized populationWhere M is the number of moths initially, set m=20.
The spatial position of each individual is vector:
Wherein i=1, 2, …, M, t is the algebra of the iteration, d is the number of variables to be solved, namely the dimension of the solution of the problem to be solved, d=3, and the three variables respectively represent the connection coefficient, the amplitude coefficient and the attenuation coefficient.
Step three: the flame spatial location is initialized.
Randomly generating the positions of the moths in the search space, substituting the obtained parameters corresponding to each moths into the pulse coupling neural network model, and segmenting the image. And sequencing fitness values corresponding to the spatial positions of the moths as the spatial positions of the 1 st generation flames.
Step four: updating the position of the moths.
The update of the space position of the moths depends on the flame surrounded by the space position of the moths, and the space position of the current generation moths is updated:
Mi=S(Mi,Fj)
Wherein S represents a spiral function, M i represents an ith moth, and F j represents a jth flame.
Step five: and calculating the fitness value of each individual.
And carrying the obtained parameters corresponding to each moth into a PCNN model to divide the image, solving the corresponding cross entropy of all the moths in the population, and marking the cross entropy as an adaptability value. The cross entropy function is defined as follows:
Where D is a cross entropy value, Z is a gray value of an image pixel, Z is a maximum value of the gray values, S is a region of the segmentation map, S 1 is a target region, S 2 is a background region, and μ 1 and μ 2 are average values of pixel gray values of the target region and the background region, respectively. t h represents The minimum gray level of the pixel at the time of obtaining the minimum value, h (z) represents the number of pixels having a gray level value z after the image is divided.
Step six: the flame position is updated.
Dividing the image by substituting the updated moth position into parameter pulse coupled neural network models, sorting and arranging the fitness values from large to small, comparing the fitness values with the fitness values of the flames of the previous generation, and selecting a better fitness value to update the position of the flames.
Step seven: the adaptation reduces the number of flames.
The number of the current flames is gradually reduced according to the maximum individual number of the population and the maximum iteration number and the self-adaptive reduction rule, and the reduction of the number of the flames can accelerate the search of the optimal solution by the moths, and the moths which are not matched with the flames because the reduction of the number of the flames participate in the search of the optimal solution in the global range. The formula for the adaptive reduction of flame quantity is as follows:
wherein N represents the number of moths in the population, T represents the maximum iteration number, w represents the current iteration number, and round represents rounding.
Step eight: judging whether the algorithm reaches the maximum iteration number set in the initial process, if so, ending the algorithm and outputting a segmented image; if the maximum iteration number is not reached, returning to the fourth step, and entering the next iteration.
Optionally, the processing the total fuzzy entropy of the image to obtain a signal energy fluctuation threshold includes:
S341, processing the total fuzzy entropy of the image to obtain the maximum fuzzy entropy and the average fuzzy entropy;
S342, processing the maximum fuzzy entropy and the average fuzzy entropy to obtain a heuristic function;
s343, processing the heuristic function to obtain an optimal fuzzy entropy;
S344, processing the optimal fuzzy entropy to obtain an image segmentation threshold;
s345, the image segmentation threshold is processed to obtain a signal energy fluctuation threshold.
Optionally, the calculating, in real time, the energy fluctuation variance of the electromagnetic spectrum signal includes:
Calculating the energy fluctuation variance of the electromagnetic spectrum signal by using a real-time sliding window model;
The real-time sliding window model is as follows:
Where ni=t 0,t0+1,t0+2,…,N+t0 -1, the width of the window is N, the step size is denoted 1, Representing the variance of the energy fluctuation of the electromagnetic spectrum signal within the ith typical frequency t 0 window, S ni (E) is the spectrum within the ith typical frequency t 0 window,/>Is the spectral mean of k typical frequencies.
Optionally, the comparing and detecting the energy fluctuation variance with the signal energy fluctuation threshold to obtain signal energy anomaly detection information includes:
s51, recording the energy fluctuation variance in the current window and the energy fluctuation variance in the window before the current window by 1 step length, and obtaining a first energy fluctuation variance and a second energy fluctuation variance;
s52, carrying out frequency spectrum energy fluctuation change comparison detection on the first energy fluctuation variance and the second energy fluctuation variance and the signal energy fluctuation threshold to obtain signal energy abnormality detection information.
Optionally, the comparing the first energy fluctuation variance and the second energy fluctuation variance with the signal energy fluctuation threshold to detect spectral energy fluctuation changes, to obtain a signal energy anomaly detection result, including:
S521, if the signal energy fluctuation threshold is greater than or equal to the first energy fluctuation variance and less than the second energy fluctuation variance, the signal energy of the current time window is greatly increased, and the signal energy abnormality detection result is signal energy abnormality;
S522, if the signal energy fluctuation threshold is greater than or equal to the second energy fluctuation variance and smaller than the first energy fluctuation variance, the signal energy of the current time window is greatly reduced, and the signal energy abnormality detection result is signal energy abnormality.
Optionally, when the signal energy is abnormal, the processing the energy fluctuation variance to obtain energy abnormality degree information includes:
Processing the energy fluctuation variance to obtain a first energy fluctuation variance and a second energy fluctuation variance;
processing the first energy fluctuation variance and the second energy fluctuation variance by using an energy abnormality degree calculation model to obtain energy abnormality degree information;
The energy abnormality degree calculation model is as follows:
Wherein E 1 is energy abnormality degree information, For the second energy fluctuation variance,/>For the first energy fluctuation variance, i=1, 2, …, k, ni=t 0,t0+1,t0+2,…,N+t0 -1, the width of the window is N, t 0 is the position of the window, and k is the number of typical frequencies.
Example two
Referring to fig. 2, fig. 2 is a flowchart illustrating another electromagnetic spectrum signal energy anomaly detection method according to an embodiment of the present invention. The electromagnetic spectrum signal energy anomaly detection method described in fig. 2 is applied to a spectrum situation system to complete automatic detection of electromagnetic spectrum signal energy anomalies in real time, and provides powerful support for electromagnetic spectrum signal event correlation analysis, target frequency behavior and intention analysis. As shown in fig. 2, the method for detecting abnormal energy of the electromagnetic spectrum signal may include the following operations (for example, f 1):
step 1: calculating the energy fluctuation threshold of each frequency signal
According to the complex electromagnetic environment around the monitoring equipment, selecting reasonable energy fluctuation thresholds for different frequencies is a prerequisite for automatic detection of signal energy anomalies. The specific method comprises continuously monitoring electromagnetic spectrum signal for a certain time, recording the frequency spectrum of each typical frequency (f 1,f2,…,fk), wherein k is the number of the typical frequencies, and deducing calculated variance therefrom by ant colony algorithmAs a signal energy fluctuation threshold.
Step 1.1: calculating a spectral energy variance matrix and mapping to an image
Taking f 1 as an example, firstly collecting M frames of spectrum signals S m1 (E), and calculating the variance of each frame of spectrum signalsObtaining a variance matrix:
E is the energy of the light, and the energy of the light is the energy of the light, Is the mean value of the signal intensity.
The variance matrix is then mapped to an image gray space with 256 levels L:
{x11,x12,…,x1m} (2)
In the method, in the process of the invention,
Step 1.2: construction of fuzzy set and membership function
According to the formed image, a fuzzy set matrix is constructed, and the formula is as follows:
X=[μ1m1(x1m1)]1×M,m1=1,2,3,…,M (3)
Where μ 1m1(x1m1) represents that the membership of the gray fuzzy set of the (1, m 1) th pixel in the matrix is μ 1m1, or that the (1, m 1) th pixel x 1m1 of the image has a certain characteristic degree of μ 1m1, and μ 1m1 e [0,1].
The fuzzy membership function uses an S function and a Z function (z=1-S), as follows:
Where μ a (k) and μ b (k) represent the fuzzy membership function values of the pixels with gray values k belonging to the object and the background, respectively, a, b, c are variable parameters of the membership function, and μ 0 (k) is the membership function.
Let h= { p 0,p1,…,pL-1 } be the histogram of the image, whereN k is the number of pixels in the image X with a gray value k, and mxn represents the size of the gray image matrix. Setting a threshold T to divide the image into two categories, namely a target E a and a background E b, the probability distribution is respectively:
pa=p(Ea) (4)
pb=p(Eb) (5)
The conditional probability that a pixel with a gray value k belongs to the object and the background is represented by p a/k and p b/k respectively, and then the probability distribution of the object and the background is:
pka=pk×pa/k (6)
pkb=pk×pb/k (7)
Associating p a/k and p b/k with their membership function values belonging to the object and the background, with the gray value k, there are:
pa/k=μa(k) (8)
pb/7=μb(k) (9)
thus, the intra-class fuzzy entropy of each class is:
The total fuzzy entropy of the image is:
H(a,b,c)=Ha+Hb
It can be seen that the total fuzzy entropy of the image is a function of the parameters a, b, c, the values of the parameters a, b, c are determined according to the maximum entropy criterion, and at the optimal threshold T, the fuzzy membership function values of the target and the background are equal, namely the following conditions should be satisfied:
μa(T)=μb(T)=0.5 (15)
it follows that finding the optimal segmentation threshold corresponds to finding the optimal combination of a, b, c.
Step 1.3: ant colony algorithm solving variance threshold
The ant colony objective function L (H) is set as follows:
L(H)=H(a,b,c) (16)
Let L max (H) and L avg (H) represent maximum and average fuzzy entropy, respectively, then the heuristic function η can be expressed as:
Obtaining optimal combination value of (a, b, c) through iterative solution, deriving an image segmentation threshold value x 10, namely T by using the result, and then obtaining a variance threshold value of the energy spectrum at the frequency f 1 according to the formula (18)
Step 2: spectral energy fluctuation threshold anomaly detection
In the process of monitoring the spectrum energy of the heavy-point frequency signal in real time, the accumulated spectrum energy fluctuation variance is calculated in a sliding window mode and is compared with the corresponding signal energy fluctuation threshold to realize the detection of the energy abnormality of the instant electromagnetic spectrum signal, and the schematic block diagram is shown in figure 2.
Step 2.1: calculating signal energy fluctuation variance by real-time sliding window
Taking the typical frequency f 1 as an example, the collected spectral signal energy data S n1 (E) is partitioned in the form of a sliding window, the window width is denoted as N, the step size is denoted as t, and the variance of the data in the window t 0 is calculated in real time:
/>
step 2.2: spectral energy fluctuation change contrast detection
Recording the variance of the data in the current window asVariance of data within window before 1 step is/>Comparing the two variances with a variance threshold, if any one of the following formulas is satisfied and the next window step is kept, judging that the abnormal energy change occurs in the current time window:
σn1 2'≤σ01 2<σn1 2 (20)
σn1 2<σ01 2≤σn1 2' (21)
Wherein the method comprises the steps of The calculation formula of (2) is as follows:
Equation (20) is satisfied to show a large increase in signal energy occurring in the current time window, while equation (21) is satisfied to show a large decrease in signal energy occurring in the current time window.
Step 3: energy anomaly severity analysis and alerting
After the signal energy is found to be abnormal, the abnormal severity is divided by calculating the degree E 1 deviating from the normal threshold, and the warning is prompted to a frequency spectrum monitoring person, so that support is provided for the frequency utilization behavior and the intention analysis of the radiation source signal.
In order to ensure the standardability of the alarm grading method and avoid the influence of the special attribute difference among key frequencies on grading, the calculation method for measuring the deviation normal threshold degree E 1 adopts the ratio form of the fluctuation threshold corresponding to the current frequency, and the calculation method is as follows:
wherein, the amplitude range of E 1 is [0, ], and the severity of the energy anomaly change and the value of E 1 have positive correlation, and the specific anomaly severity classification mode is shown in Table 1.
Table 1 table of the severity of abnormalities
The apparatus embodiments described above are merely illustrative, in which the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above detailed description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product that may be stored in a computer-readable storage medium including Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (Compact Disc Read-Only Memory, CD-ROM) or other optical disc Memory, magnetic disc Memory, tape Memory, or any other medium that can be used for computer-readable carrying or storing data.
Finally, it should be noted that: the embodiment of the invention discloses a method for detecting electromagnetic spectrum signal energy abnormality, which is only a preferred embodiment of the invention, and is only used for illustrating the technical scheme of the invention, but not limiting the technical scheme; although the invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art will understand that; the technical scheme recorded in the various embodiments can be modified or part of technical features in the technical scheme can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (5)
1. A method for detecting electromagnetic spectrum signal energy anomalies, the method comprising:
s1, acquiring electromagnetic spectrum signals before executing important monitoring tasks;
S2, processing the electromagnetic spectrum signals to obtain k frequency spectrums with typical frequencies, wherein k is an integer;
S3, processing the frequency spectrums of the k typical frequencies to obtain a signal energy fluctuation threshold, wherein the signal energy fluctuation threshold comprises:
s31, processing the frequency spectrums of the k typical frequencies to obtain a frequency spectrum energy square difference matrix, wherein the method comprises the following steps:
Processing the frequency spectrums of the k typical frequencies by using a variance calculation model to obtain a frequency spectrum energy variance matrix;
The variance calculation model is as follows:
Where i=1, 2, …, k, M is the number of frames of the acquired electromagnetic spectrum signal, For the mi-th frame spectrum energy variance matrix, S mi (E) is mi -th frame spectrum of the i-th typical frequency,/>Is the spectral mean of k typical frequencies;
s32, mapping the spectrum energy variance matrix to obtain spectrum energy variance image information, wherein the method comprises the following steps:
Processing the spectrum energy square difference matrix to obtain an image gray value;
The image gray value is:
where mi=1, 2, …, M is the number of frames of the acquired electromagnetic spectrum signal, For the mi th frame of spectrum energy square difference matrix, l=256, x imi is the image gray value of the i typical frequency mi th frame;
k typical frequency image gray values form spectral energy variance image information;
the spectral energy variance image information is:
{xi1,xi2,…,xiM}
Wherein i=1, 2, …, k;
S33, processing the spectrum energy variance image information to obtain the total fuzzy entropy of the image, wherein the method comprises the following steps:
s331, processing the spectrum energy variance image information to obtain a fuzzy set matrix;
s332, processing the spectrum energy variance image information to obtain an image histogram;
s333, presetting a threshold value, and dividing an image histogram according to the threshold value to obtain a target image and a background image;
s334, processing the target image and the background image according to the fuzzy set matrix to obtain the conditional probability that the pixel belongs to the target image and the conditional probability that the pixel belongs to the background image;
S335, processing the conditional probability that the pixel belongs to the target image and the conditional probability that the pixel belongs to the background image to obtain the total fuzzy entropy of the image;
s34, processing the total fuzzy entropy of the image to obtain a signal energy fluctuation threshold, wherein the step comprises the following steps:
S341, processing the total fuzzy entropy of the image to obtain the maximum fuzzy entropy and the average fuzzy entropy;
S342, processing the maximum fuzzy entropy and the average fuzzy entropy to obtain a heuristic function;
s343, processing the heuristic function to obtain an optimal fuzzy entropy;
S344, processing the optimal fuzzy entropy to obtain an image segmentation threshold;
s345, processing the image segmentation threshold to obtain a signal energy fluctuation threshold;
s4, when an important monitoring task is executed, calculating the energy fluctuation variance of the electromagnetic spectrum signal in real time;
s5, carrying out spectrum energy fluctuation change comparison detection on the energy fluctuation variance and the signal energy fluctuation threshold to obtain a signal energy abnormality detection result;
s6, when the signal energy is abnormal, the energy fluctuation variance is processed to obtain energy abnormality degree information;
and S7, carrying out alarm processing according to the energy abnormality degree information.
2. The method of claim 1, wherein said calculating in real time an energy fluctuation variance of an electromagnetic spectrum signal comprises:
Calculating the energy fluctuation variance of the electromagnetic spectrum signal by using a real-time sliding window model;
The real-time sliding window model is as follows:
Where ni=t 0,t0+1,t0+2,…,N+t0 -1, the width of the window is N, the step size is denoted 1, Representing the variance of the energy fluctuation of the electromagnetic spectrum signal within the ith typical frequency t 0 window, S ni (E) is the spectrum within the ith typical frequency t 0 window,/>Is the spectral mean of k typical frequencies.
3. The method for detecting energy anomalies of electromagnetic spectrum signals according to claim 1, wherein the step of comparing the energy fluctuation variance with the signal energy fluctuation threshold to obtain signal energy anomaly detection information includes:
s51, recording the energy fluctuation variance in the current window and the energy fluctuation variance in the window before the current window by 1 step length, and obtaining a first energy fluctuation variance and a second energy fluctuation variance;
s52, carrying out frequency spectrum energy fluctuation change comparison detection on the first energy fluctuation variance and the second energy fluctuation variance and the signal energy fluctuation threshold to obtain signal energy abnormality detection information.
4. The method for detecting electromagnetic spectrum signal energy anomaly according to claim 3, wherein the comparing the first energy fluctuation variance and the second energy fluctuation variance with the signal energy fluctuation threshold to obtain a signal energy anomaly detection result comprises:
S521, if the signal energy fluctuation threshold is greater than or equal to the first energy fluctuation variance and less than the second energy fluctuation variance, the signal energy of the current time window is greatly increased, and the signal energy abnormality detection result is signal energy abnormality;
S522, if the signal energy fluctuation threshold is greater than or equal to the second energy fluctuation variance and smaller than the first energy fluctuation variance, the signal energy of the current time window is greatly reduced, and the signal energy abnormality detection result is signal energy abnormality.
5. The method for detecting energy anomaly of electromagnetic spectrum signal according to claim 1, wherein said processing the energy fluctuation variance to obtain energy anomaly degree information when signal energy is anomalous comprises:
Processing the energy fluctuation variance to obtain a first energy fluctuation variance and a second energy fluctuation variance;
processing the first energy fluctuation variance and the second energy fluctuation variance by using an energy abnormality degree calculation model to obtain energy abnormality degree information;
The energy abnormality degree calculation model is as follows:
Wherein E 1 is energy abnormality degree information, For the second energy fluctuation variance,/>For the first energy fluctuation variance, i=1, 2, …, k, ni=t 0,t0+1,t0+2,…,N+t0 -1, the width of the window is N, t 0 is the position of the window, and k is the number of typical frequencies.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311110359.XA CN117147966B (en) | 2023-08-30 | 2023-08-30 | Electromagnetic spectrum signal energy anomaly detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311110359.XA CN117147966B (en) | 2023-08-30 | 2023-08-30 | Electromagnetic spectrum signal energy anomaly detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117147966A CN117147966A (en) | 2023-12-01 |
CN117147966B true CN117147966B (en) | 2024-05-07 |
Family
ID=88900154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311110359.XA Active CN117147966B (en) | 2023-08-30 | 2023-08-30 | Electromagnetic spectrum signal energy anomaly detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117147966B (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102044244A (en) * | 2009-10-15 | 2011-05-04 | 华为技术有限公司 | Signal classifying method and device |
CN103414527A (en) * | 2013-08-08 | 2013-11-27 | 西安电子科技大学 | Signal detection method based on energy detection |
CN103812577A (en) * | 2012-11-06 | 2014-05-21 | 西南交通大学 | Method for automatically identifying and learning abnormal radio signal type |
CN105025583A (en) * | 2015-07-02 | 2015-11-04 | 哈尔滨工业大学 | Stepped frequency spectrum sensing method based on energy and covariance detection |
CN105467428A (en) * | 2015-11-17 | 2016-04-06 | 南京航空航天大学 | Seismic wave warning method based on short-time energy detection and spectrum feature analysis |
CN105741262A (en) * | 2015-11-01 | 2016-07-06 | 西安电子科技大学 | Sea-land clutter scene segmentation method based on energy concentration measure |
CN106409310A (en) * | 2013-08-06 | 2017-02-15 | 华为技术有限公司 | Audio signal classification method and device |
CN111465023A (en) * | 2020-03-25 | 2020-07-28 | 山东大学 | Self-adaptive double-threshold spectrum sensing method based on historical energy information |
CN111598039A (en) * | 2020-05-24 | 2020-08-28 | 绍兴声科科技有限公司 | Abnormal sound monitoring method and monitoring device for petroleum pipeline monitoring |
CN112541480A (en) * | 2020-12-25 | 2021-03-23 | 华中科技大学 | Online identification method and system for tunnel foreign matter invasion event |
CN112967357A (en) * | 2021-02-19 | 2021-06-15 | 中国人民解放军国防科技大学 | Frequency spectrum map construction method based on convolutional neural network |
CN115776724A (en) * | 2023-02-10 | 2023-03-10 | 南京航空航天大学 | Sensor node layout optimization method and system for electromagnetic spectrum mapping |
CN115964670A (en) * | 2022-12-17 | 2023-04-14 | 中国人民解放军32802部队 | Frequency spectrum anomaly detection method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7395292B2 (en) * | 2003-10-08 | 2008-07-01 | Johnson Mark W | Method for displaying spectral trends in complex signals |
US10104692B2 (en) * | 2016-06-03 | 2018-10-16 | Nokia Technologies Oy | Adaptive energy detection threshold for clear channel assessment |
FR3112048A1 (en) * | 2020-06-26 | 2021-12-31 | Orange | Determining the noise in a signal |
-
2023
- 2023-08-30 CN CN202311110359.XA patent/CN117147966B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102044244A (en) * | 2009-10-15 | 2011-05-04 | 华为技术有限公司 | Signal classifying method and device |
CN103812577A (en) * | 2012-11-06 | 2014-05-21 | 西南交通大学 | Method for automatically identifying and learning abnormal radio signal type |
CN106409310A (en) * | 2013-08-06 | 2017-02-15 | 华为技术有限公司 | Audio signal classification method and device |
CN103414527A (en) * | 2013-08-08 | 2013-11-27 | 西安电子科技大学 | Signal detection method based on energy detection |
CN105025583A (en) * | 2015-07-02 | 2015-11-04 | 哈尔滨工业大学 | Stepped frequency spectrum sensing method based on energy and covariance detection |
CN105741262A (en) * | 2015-11-01 | 2016-07-06 | 西安电子科技大学 | Sea-land clutter scene segmentation method based on energy concentration measure |
CN105467428A (en) * | 2015-11-17 | 2016-04-06 | 南京航空航天大学 | Seismic wave warning method based on short-time energy detection and spectrum feature analysis |
CN111465023A (en) * | 2020-03-25 | 2020-07-28 | 山东大学 | Self-adaptive double-threshold spectrum sensing method based on historical energy information |
CN111598039A (en) * | 2020-05-24 | 2020-08-28 | 绍兴声科科技有限公司 | Abnormal sound monitoring method and monitoring device for petroleum pipeline monitoring |
CN112541480A (en) * | 2020-12-25 | 2021-03-23 | 华中科技大学 | Online identification method and system for tunnel foreign matter invasion event |
CN112967357A (en) * | 2021-02-19 | 2021-06-15 | 中国人民解放军国防科技大学 | Frequency spectrum map construction method based on convolutional neural network |
CN115964670A (en) * | 2022-12-17 | 2023-04-14 | 中国人民解放军32802部队 | Frequency spectrum anomaly detection method |
CN115776724A (en) * | 2023-02-10 | 2023-03-10 | 南京航空航天大学 | Sensor node layout optimization method and system for electromagnetic spectrum mapping |
Non-Patent Citations (6)
Title |
---|
基于深度卷积神经网络的协作频谱感知方法;盖建新 等;《基于深度卷积神经网络的协作频谱感知方法》;20211031;第第43卷卷(第第10期期);2911至2917页 * |
基于蒙特卡洛方法的频谱能量检测研究;王蒙;陈德章;杨晶晶;王鲁嘉;黄铭;;无线电工程;20130105(第01期);全文 * |
小样本图像处理方法赋能的宽带频谱感知;周金 等;《电子与信息学报》;20230331;第第45卷卷(第第3期期);1102至1110页 * |
改进对比度和空间频率的图像融合算法;李艳玮;郑伟勇;;计算机工程与设计;20170916(第09期);全文 * |
未知雷达辐射源分选的一种新方法;汪毅;;微计算机信息;20100205(第04期);全文 * |
非高斯噪声中基于分数低阶矩协方差MME检测的频谱感知算法;宋永健;朱晓梅;包亚萍;朱楹栋;;信号处理;20180225(第02期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117147966A (en) | 2023-12-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109816221B (en) | Project risk decision method, apparatus, computer device and storage medium | |
EP3571809B1 (en) | Method and apparatus for analysing performance of a telecommunications network | |
CN110736968B (en) | Radar abnormal state diagnosis method based on deep learning | |
CN111079655B (en) | Method for recognizing human body behaviors in video based on fusion neural network | |
CN109886496B (en) | Agricultural yield prediction method based on meteorological information | |
CN116993738B (en) | Video quality evaluation method and system based on deep learning | |
CN114898261A (en) | Sleep quality assessment method and system based on fusion of video and physiological data | |
CN117147966B (en) | Electromagnetic spectrum signal energy anomaly detection method | |
CN113435825B (en) | Intelligent management method, system and storage medium based on soil-borne disease control | |
CN114707577A (en) | Anomaly detection method and system based on self-confrontation variational self-encoder | |
CN115964503A (en) | Safety risk prediction method and system based on community equipment facilities | |
CN116597946B (en) | Teenager mental health detection method based on house-tree-person | |
CN115496218B (en) | Weld defect real-time detection method integrating evolutionary algorithm and fuzzy inference | |
CN114283367B (en) | Artificial intelligent open fire detection method and system for garden fire early warning | |
CN110969209B (en) | Stranger identification method and device, electronic equipment and storage medium | |
CN112232329A (en) | Multi-core SVM training and alarming method, device and system for intrusion signal recognition | |
CN114386477A (en) | Automatic identification method for radiation field abnormity monitoring data | |
Jiao et al. | A novel automatic parameter setting method of PCNN for image segmentation | |
JP2015197788A (en) | Laminar flow smoke detection device and laminar flow smoke detection method | |
CN111091269A (en) | Criminal risk assessment method based on multi-dimensional risk index | |
JP6457727B2 (en) | Laminar smoke detection device and laminar smoke detection method | |
CN117391265B (en) | Forestry pest hazard risk prediction method based on big data analysis | |
Erkanli et al. | Entropy-based image fusion with continuous genetic algorithm | |
CN117312800A (en) | Geographic space-time data analysis method and system based on tide analysis | |
CN117235596A (en) | Smart grid security situation assessment method based on improved probabilistic neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |