CN105426832A - Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio) - Google Patents
Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio) Download PDFInfo
- Publication number
- CN105426832A CN105426832A CN201510770863.1A CN201510770863A CN105426832A CN 105426832 A CN105426832 A CN 105426832A CN 201510770863 A CN201510770863 A CN 201510770863A CN 105426832 A CN105426832 A CN 105426832A
- Authority
- CN
- China
- Prior art keywords
- signal
- ratio
- noise ratio
- emitter
- radiation source
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a communication radar radiation source identification method in the presence of an unsteady SNR (Signal Noise Ratio). The communication radar radiation source identification method comprises the steps of performing discrete normalization respectively for different types of radiation source signals; capturing the same discrete point number for signals of each radiation source so as to respectively compose a respective radiation source signal sequence; regrouping the composed radiation source signal sequences to obtain a series of feature vectors; selecting a multi-fractal dimension, then calculating the feature vector of the multi-fractal dimension feature of the signals in the presence of multiple different signal noise ratios and then storing the feature vector of the multi-fractal dimension feature as a feature database; training the feature vectors in the database by utilizing a neural network so as to obtain public features of the same type of the radiation source signals; and training and testing a neural network system by regarding a to-be-identified signal as an input so as to realize identification of the radiation source signals in the presence of the unsteady SNR.
Description
Technical field
The present invention relates to the emitter Signals Recognition technical field in electronic countermeasure scouting, be specifically related to radar emitter signal and the radar based on Multifractal Dimension under the concrete recognition methods, particularly unstable signal to noise ratio (S/N ratio) of the emitter Signals that communicates, communication emitter Signals Feature extraction and recognition method.
Background technology
Scout in emitter Signals Recognition system [1-2] at hyundai electronics, not only requirement can identify emitter Signals that is dissimilar, difference in functionality parameter, also requires to identify the emitter Signals with the Different Individual of close parameter simultaneously.Under the electromagnetic environment of complexity, signal to noise ratio (S/N ratio) is not often stable, therefore, under astable signal to noise ratio (S/N ratio), how to realize being identified as in order to important research contents of radiation source.Simultaneously, the basic function parameters such as traditional signal characteristic parameter and modulation type are relied on to be difficult to realize identifying modern complicated emitter Signals, therefore, need to propose new characteristic parameter, signature analysis and classification are carried out to signal internal feature structure and the small change of signal.
In emitter Signals Recognition field, the current new feature for identifying mainly comprises wavelet packet character [3], resemblance Coefficient [4], box counting dimension [5], entropy [6] etc.These New System features overcome the defects such as traditional parameters identification signal is single, anti-noise ability is poor, the signal waveform fine feature of time domain or frequency domain has carried out identifying [7] to emitter Signals, achieve certain achievement, improve the class number of identification signal, to a certain extent, improve the anti-noise ability of signal characteristic.
In communication Radar recognition field, have based on several recognition methodss such as decision theory, neural network, wavelet transformation and parametric statisticss, wherein, method based on parametric statistics is comparatively simple, and calculated amount is little, is easy to realize, but, how to select suitable characteristic parameter to be the difficult point of this algorithm; Wavelet transformation has obtained in Radar recognition field and has applied more widely, but its noiseproof feature is poor, is difficult to realize identifying under low signal-to-noise ratio; Neural network recognition method is obtained in every field and applies more widely, by carrying out training test to the signal characteristic obtained, usually can reach reasonable recognition effect, but will with the time of training for cost.
Along with the current development of electronic reconnaissance technology and the increasingly sophisticated of electromagnetic environment, new requirement is proposed gradually to emitter Signals, how under the electromagnetic environment of unstable signal to noise ratio (S/N ratio), effectively extracts the personal feature of emitter Signals, and it is identified, be our problem demanding prompt solution.
< list of references list >
[1] Yu Zhibin. based on the radar emitter signal Study of recognition [D] of intrapulse feature. Chengdu: Southwest Jiaotong University, 2010.
[2] Yu Zhibin, Chen Chunxia, Jin Weidong. based on the emitter Signals Recognition [J] merging entropy feature. modern radar, 2010 (1): 34-38.
[3] Sun Laijun. Wavelet Packet-characteristic Entropy for Vibration Signals time become with frequency dependent characteristic analysis [J]. High-Voltage Technology, 2007,33 (8): 146-150.
[4] Zhang Gexiang. radar emitter signal intelligent identification Method research [D]. Chengdu: electrical engineering institute of Southwest Jiaotong University, 2005.
[5] Zhang Gexiang. radar emitter signal intelligent identification Method research [D]. Chengdu: electrical engineering institute of Southwest Jiaotong University, 2005.
[6] Luo Guomin, He Zhengyou, Lin Sheng. utilize the discussion [J] of the difference identification transmission line of electricity transient signal of the relative entropy of small echo. electric power network technique, 2008,32 (15): 47-51.
[7] Zhang Zhengchao, Li Yingsheng, Wang Lei, etc. radar emitter signal Study of recognition summary [J]. marine electronic engineering, 2009 (4): 10-14.
Summary of the invention
Technical matters to be solved by this invention is for there is above-mentioned defect in prior art, a kind of emitter Signals Recognition method based on Multifractal Dimension under astable signal to noise ratio (S/N ratio) is provided, the method can overcome in existing recognition methods, to the requirement of signal to noise ratio (S/N ratio) stability, the Multifractal Dimension feature of signal is extracted in certain signal to noise ratio (S/N ratio) variation range, after extracting feature, by training, the test of neural network classifier, can be issued in unstable signal to noise ratio (S/N ratio) the object that emitter Signals is identified.
In order to realize above-mentioned technical purpose, according to the present invention, providing a kind of emitter Signals Recognition method based on Multifractal Dimension under astable signal to noise ratio (S/N ratio), comprising: dissimilar emitter Signals is carried out discrete normalization respectively; Respectively identical discrete counting is intercepted to each emitter Signals and form respective emitter Signals sequence respectively; The emitter Signals sequence of composition is carried out recombinating to obtain series of features vector; Select suitable Multifractal Dimension according to actual requirement, calculate the proper vector of the Multifractal Dimension feature of signal under multiple different signal to noise ratio (S/N ratio) subsequently, and the proper vector of described Multifractal Dimension feature is stored as property data base; Neural network is utilized to train the proper vector in database, to obtain the public characteristic of identical type emitter Signals, for Classification and Identification is prepared; Using signal to be identified as input, training and testing is carried out to nerve network system, to realize the identification to emitter Signals under astable signal to noise ratio (S/N ratio).
Preferably, Multifractal Dimension is not less than 3.
Preferably, Multifractal Dimension is not more than 11.
Preferably, described multiple different signal to noise ratio (S/N ratio) is in preset range.
Preferably, intercept identical discrete step of counting to each emitter Signals respectively to comprise: carry out feature extraction to intercept identical discretely to count to each emitter Signals at identical conditions.
Accompanying drawing explanation
By reference to the accompanying drawings, and by reference to detailed description below, will more easily there is more complete understanding to the present invention and more easily understand its adjoint advantage and feature, wherein:
Fig. 1 schematically shows the process flow diagram of the Radar-Communication Emitter Recognition under astable according to the preferred embodiment of the invention signal to noise ratio (S/N ratio).
Fig. 2 schematically shows fsk signal Multifractal Dimension curve map.
Fig. 3 schematically shows psk signal Multifractal Dimension curve map.
Fig. 4 schematically shows LFM signal Multifractal Dimension curve map.
Fig. 5 schematically shows SFCW signal Multifractal Dimension curve map.
The type charcteristics of different emitter Signals when Fig. 6 schematically shows triple dimension.
It should be noted that, accompanying drawing is for illustration of the present invention, and unrestricted the present invention.Note, represent that the accompanying drawing of structure may not be draw in proportion.Further, in accompanying drawing, identical or similar element indicates identical or similar label.
Embodiment
In order to make content of the present invention clearly with understandable, below in conjunction with specific embodiments and the drawings, content of the present invention is described in detail.
The present invention, under astable signal to noise ratio (S/N ratio), extracts the Multifractal Dimension feature of emitter Signals, obtains different trickle waveform feature data storehouses, and recycling neural network, realizes the identification to different emitter Signals individuality.
The present invention includes under astable signal to noise ratio (S/N ratio) environment, realize emitter Signals Recognition.Signal to noise ratio (S/N ratio) environment can be set change in certain scope, the Multifractal Dimension feature of emitter Signals is extracted under the signal to noise ratio (S/N ratio) of change, under requiring the environment that this characteristic parameter of emitter Signals changes in signal to noise ratio (S/N ratio), there is stability, meanwhile, there is in good class degree of separation between concentration class and class.
For Multifractal Dimension feature extraction, discrete normalization can be carried out to emitter Signals, intercept identical discrete sampling counts as pending burst simultaneously, ensure that each emitter Signals carries out feature extraction at identical conditions, simultaneously, corresponding fractal dimension is set, according to the definition of Multifractal Dimension, Multifractal Dimension feature extraction is carried out to emitter Signals.
And the present invention is directed to neural network recognization system, to the Multifractal Dimension feature extracted under astable signal to noise ratio (S/N ratio) as the input of neural network, train, test, finally realizes the emitter Signals Recognition under astable signal to noise ratio (S/N ratio).
Specifically describe the preferred embodiments of the present invention below.
Fig. 1 schematically shows the process flow diagram based on the Radar-Communication Emitter Recognition of Multifractal Dimension under astable according to the preferred embodiment of the invention signal to noise ratio (S/N ratio).
As shown in Figure 1, the Radar-Communication Emitter Recognition based on Multifractal Dimension under astable according to the preferred embodiment of the invention signal to noise ratio (S/N ratio) comprises the steps:
1. get 4 emitter Signals to be identified, be respectively frequency shift (FS) modulation (FSK) signal, phase-shift keying (PSK) (PSK) signal, linear frequency modulation (LFM) signal and frequency step (SFCW) signal.For these 4 radars, communication emitter Signals, carry out discrete normalization to each signal, meanwhile, intercept identical sampling number to each signal, correspondence obtains 4 bursts;
2. pairs of 4 bursts carry out the restructuring of same form, and each signal is divided into M zonule, for i-th (i=1,2 ..., M) and the dimension size of individual its correspondence of regional signal is taken as ε
i, the density fonction P in i-th region
i, then the scaling exponent α of zones of different i
ican be described as:
Non-integer α
ibe commonly referred to as singular index, its value is relevant with region, represents the fractal dimension in a certain region.
3. in order to obtain the distribution character of a series of subset, defined function X
q(ε), it is the probability weight summation of regional, and wherein, ε is dimension size, and q is density fonction P
iexponential, that is:
Define generalized dimension function D further thus
qfor:
The size of q value determines the selection of dimension in Multifractal Dimension.
According to the waveform variation characteristic of signal, select suitable tuple, tuple is more, to signal portray meticulousr, accordingly, the complexity of calculating is also larger.Fig. 2 to Fig. 5 describes the 11 heavy Dimension Characteristics of 4 signals under q gets-5 ~ 5 values, particularly, Fig. 2 schematically shows fsk signal Multifractal Dimension curve map, Fig. 3 schematically shows psk signal Multifractal Dimension curve map, Fig. 4 schematically shows LFM signal Multifractal Dimension curve map, and Fig. 5 schematically shows SFCW signal Multifractal Dimension curve map.As can be seen from the figure, 11 heavy Dimension Characteristics of different emitter Signals are different, can realize the classification to emitter Signals according to each signal Multifractal Dimension characteristic profile.
Because 11 heavy dimensions are more, there is certain computation complexity, and do not need so many tuple just can reach the effect of Classification and Identification to these 4 kinds of signals, therefore, get 3 heavy Dimension Characteristics, make q=0 ~ 2, draw multifractal curve map as shown in Figure 6, as can be seen from the figure, the Multifractal Dimension feature of unlike signal is different, using the Multifractal Dimension feature that the obtains property data base as different emitter Signals, thus unknown emitter Signals is identified.
Noting, in above Multifractal Dimension computation process, is all carry out under the prerequisite of signal to noise ratio (S/N ratio) change.Set a signal to noise ratio (S/N ratio) variation range, the multifractal calculating each signal within the scope of this is numerical value, as the signal characteristic value under this SNR ranges, because Multifractal Dimension is when signal to noise ratio (S/N ratio) changes, there is certain stability, therefore, there is in good class degree of separation between concentration class and class.
Using the eigenvectors matrix that obtains as the input of neural network, neural network is trained, test.Wherein, 3 hidden layers are arranged to neural network, after being trained by great amount of samples, test is carried out to signal and identifies.Often kind of signal gets 100 samples, and under the signal to noise ratio (S/N ratio) of 3 dB range, identify above 4 kinds of emitter Signals, discrimination result of calculation is as shown in table 1.
Emitter Signals Recognition rate (q=0 ~ 2) under the astable signal to noise ratio (S/N ratio) of table 1
As can be seen from simulation result, under change signal to noise ratio (S/N ratio), utilize Multifractal Dimension feature, then identified by neural network, good recognition effect can be reached.It can thus be appreciated that the method can identify emitter Signals under change signal to noise ratio (S/N ratio).
As can be seen from the simulation result of accompanying drawing 6, the Multifractal Dimension feature of emitter Signals is extracted in the scope of q=0 ~ 2, for the tuple value had, some coincidence of the feature of various signal, and in this 3 heavy feature, what play classification effect is correlation dimension feature, therefore, if only get correlation dimension eigenwert, also can under change signal to noise ratio (S/N ratio), identify 4 kinds of emitter Signals, Simulation identification result is as shown in table 2.
Emitter Signals Recognition rate (q=2) under the astable signal to noise ratio (S/N ratio) of table 2
The simulation result of contrast table 1 and table 2 is known, in identical signal to noise ratio (S/N ratio) variation range, gets 3 heavy fractal dimensions and has better recognition effect than 1 heavy fractal dimension, but, be increase to cost with calculated amount.Although the discrimination in table 2 decreases, the degree of reduction is also little, when not being strict with discrimination, a heavy dimension only can being utilized to identify, while reduction calculated amount, also can reach certain recognition effect.Therefore, can according to the requirement of reality, balance discrimination and calculated amount relation between the two, and then select suitable dimension.
Based on the above analysis discussion to this inventive method, can learn, under astable signal to noise ratio (S/N ratio), extract the Multifractal Dimension of signal, recycling neural network is trained, and has good recognition effect, can according to actual environment, set suitable signal to noise ratio (S/N ratio) variation range, signal to noise ratio (S/N ratio) variation range is larger, and corresponding discrimination is lower, but, under certain signal to noise ratio (S/N ratio), still can identify emitter Signals.This just provides good theoretical foundation for the emitter Signals Recognition in electronic reconnaissance system.
In a word, instant invention overcomes the problem that in existing signal characteristic extracting methods, under low signal-to-noise ratio, discrimination is lower, utilize the good Cancers Fractional Dimension Feature of noiseproof feature, portray the complexity characteristics of signal in astable noise circumstance, by being reconstructed signal, select suitable Multifractal Dimension, recycling neural network classifier is classified, the object identified signal under realizing change low signal-to-noise ratio.
The present invention at least has such beneficial effect: adopt the emitter Signals Recognition system under astable signal to noise ratio (S/N ratio) of the present invention, the Multifractal Dimension feature of signal can be extracted under change signal to noise ratio (S/N ratio) environment, based on stable characteristic parameter, train by neural network, reach under astable signal to noise ratio (S/N ratio), radar emitter signal and the emitter Signals that communicates are carried out to the effect of Classification and Identification.
In addition, it should be noted that, unless stated otherwise or point out, otherwise the term " first " in instructions, " second ", " the 3rd " etc. describe only for distinguishing each assembly, element, step etc. in instructions, instead of for representing logical relation between each assembly, element, step or ordinal relation etc.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (5)
1. the Radar-Communication Emitter Recognition under astable signal to noise ratio (S/N ratio), is characterized in that comprising: dissimilar emitter Signals is carried out discrete normalization respectively; Respectively identical discrete counting is intercepted to each emitter Signals and form respective emitter Signals sequence respectively; The emitter Signals sequence of composition is carried out recombinating to obtain series of features vector; Select Multifractal Dimension, calculate the proper vector of the Multifractal Dimension feature of signal under multiple different signal to noise ratio (S/N ratio) subsequently, and the proper vector of described Multifractal Dimension feature is stored as property data base; Neural network is utilized to train the proper vector in database, to obtain the public characteristic of identical type emitter Signals; Using signal to be identified as input, training and testing is carried out to nerve network system, to realize the identification to emitter Signals under astable signal to noise ratio (S/N ratio).
2. the Radar-Communication Emitter Recognition under astable signal to noise ratio (S/N ratio) according to claim 1, it is characterized in that, Multifractal Dimension is not less than 3.
3. the Radar-Communication Emitter Recognition under astable signal to noise ratio (S/N ratio) according to claim 1 and 2, it is characterized in that, Multifractal Dimension is not more than 11.
4. the Radar-Communication Emitter Recognition under astable signal to noise ratio (S/N ratio) according to claim 1 and 2, is characterized in that, described multiple different signal to noise ratio (S/N ratio) is in preset range.
5. the Radar-Communication Emitter Recognition under astable signal to noise ratio (S/N ratio) according to claim 1 and 2, it is characterized in that, respectively identical discrete step of counting is intercepted to each emitter Signals and comprise: at identical conditions feature extraction is carried out to intercept identical discretely to count to each emitter Signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510770863.1A CN105426832A (en) | 2015-11-12 | 2015-11-12 | Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510770863.1A CN105426832A (en) | 2015-11-12 | 2015-11-12 | Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105426832A true CN105426832A (en) | 2016-03-23 |
Family
ID=55505032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510770863.1A Pending CN105426832A (en) | 2015-11-12 | 2015-11-12 | Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105426832A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106772215A (en) * | 2017-01-20 | 2017-05-31 | 大连海事大学 | A kind of VHF multipath signal measurement processing systems based on fractal theory |
| CN106845512A (en) * | 2016-11-30 | 2017-06-13 | 湖南文理学院 | Beasts shape recognition method and system based on fractal parameter |
| CN107301381A (en) * | 2017-06-01 | 2017-10-27 | 西安电子科技大学昆山创新研究院 | Recognition Method of Radar Emitters based on deep learning and multi-task learning strategy |
| CN107577999A (en) * | 2017-08-22 | 2018-01-12 | 哈尔滨工程大学 | A kind of radar emitter signal intra-pulse modulation mode recognition methods based on singular value and fractal dimension |
| CN108090462A (en) * | 2017-12-29 | 2018-05-29 | 哈尔滨工业大学 | A kind of Emitter Fingerprint feature extracting method based on box counting dimension |
| CN108108712A (en) * | 2017-12-29 | 2018-06-01 | 哈尔滨工业大学 | A kind of Emitter Fingerprint feature extracting method based on variance dimension |
| CN108303682A (en) * | 2018-01-17 | 2018-07-20 | 电子科技大学 | A kind of passive MIMO radar external sort algorithm selection method based on relative entropy criterion |
| CN108470189A (en) * | 2018-03-06 | 2018-08-31 | 中国船舶重工集团公司第七二四研究所 | Multiple domain radiation source information fusion method based on antithesis similarity model |
| CN106093873B (en) * | 2016-06-04 | 2018-08-31 | 陈昌孝 | A kind of radar emitter signal recognition methods based on multisensor |
| CN112633121A (en) * | 2020-12-18 | 2021-04-09 | 国网浙江省电力有限公司武义县供电公司 | Radiation source identification method based on Hilbert transform and multi-fractal dimension characteristics |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102436588A (en) * | 2011-11-15 | 2012-05-02 | 哈尔滨工程大学 | Radiation source identification method |
| CN102437984A (en) * | 2011-11-07 | 2012-05-02 | 哈尔滨工程大学 | Modulation signal identification method based on complexity characteristic under low signal-to-noise ratio condition |
| CN104794499A (en) * | 2015-05-08 | 2015-07-22 | 上海电机学院 | Method for designing interval gray correlation classifier based on self-adaptive entropy coefficient |
| CN104796365A (en) * | 2015-03-12 | 2015-07-22 | 上海电机学院 | Modulating signal recognition method based on complexity feature under low signal to noise ratio |
-
2015
- 2015-11-12 CN CN201510770863.1A patent/CN105426832A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102437984A (en) * | 2011-11-07 | 2012-05-02 | 哈尔滨工程大学 | Modulation signal identification method based on complexity characteristic under low signal-to-noise ratio condition |
| CN102436588A (en) * | 2011-11-15 | 2012-05-02 | 哈尔滨工程大学 | Radiation source identification method |
| CN104796365A (en) * | 2015-03-12 | 2015-07-22 | 上海电机学院 | Modulating signal recognition method based on complexity feature under low signal to noise ratio |
| CN104794499A (en) * | 2015-05-08 | 2015-07-22 | 上海电机学院 | Method for designing interval gray correlation classifier based on self-adaptive entropy coefficient |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106093873B (en) * | 2016-06-04 | 2018-08-31 | 陈昌孝 | A kind of radar emitter signal recognition methods based on multisensor |
| CN106845512A (en) * | 2016-11-30 | 2017-06-13 | 湖南文理学院 | Beasts shape recognition method and system based on fractal parameter |
| CN106772215A (en) * | 2017-01-20 | 2017-05-31 | 大连海事大学 | A kind of VHF multipath signal measurement processing systems based on fractal theory |
| CN107301381A (en) * | 2017-06-01 | 2017-10-27 | 西安电子科技大学昆山创新研究院 | Recognition Method of Radar Emitters based on deep learning and multi-task learning strategy |
| CN107577999B (en) * | 2017-08-22 | 2021-01-12 | 哈尔滨工程大学 | Radar signal intra-pulse modulation mode identification method based on singular value and fractal dimension |
| CN107577999A (en) * | 2017-08-22 | 2018-01-12 | 哈尔滨工程大学 | A kind of radar emitter signal intra-pulse modulation mode recognition methods based on singular value and fractal dimension |
| CN108108712A (en) * | 2017-12-29 | 2018-06-01 | 哈尔滨工业大学 | A kind of Emitter Fingerprint feature extracting method based on variance dimension |
| CN108090462A (en) * | 2017-12-29 | 2018-05-29 | 哈尔滨工业大学 | A kind of Emitter Fingerprint feature extracting method based on box counting dimension |
| CN108090462B (en) * | 2017-12-29 | 2021-09-03 | 哈尔滨工业大学 | Radiation source fingerprint feature extraction method based on box dimensions |
| CN108303682A (en) * | 2018-01-17 | 2018-07-20 | 电子科技大学 | A kind of passive MIMO radar external sort algorithm selection method based on relative entropy criterion |
| CN108303682B (en) * | 2018-01-17 | 2021-03-30 | 电子科技大学 | Passive MIMO radar external radiation source selection method based on relative entropy criterion |
| CN108470189A (en) * | 2018-03-06 | 2018-08-31 | 中国船舶重工集团公司第七二四研究所 | Multiple domain radiation source information fusion method based on antithesis similarity model |
| CN112633121A (en) * | 2020-12-18 | 2021-04-09 | 国网浙江省电力有限公司武义县供电公司 | Radiation source identification method based on Hilbert transform and multi-fractal dimension characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426832A (en) | Communication radar radiation source identification method in presence of unsteady SNR (Signal Noise Ratio) | |
| CN107301381A (en) | Recognition Method of Radar Emitters based on deep learning and multi-task learning strategy | |
| CN103279957B (en) | A kind of remote sensing images area-of-interest exacting method based on multi-scale feature fusion | |
| CN110110738A (en) | A kind of Recognition Method of Radar Emitters based on multi-feature fusion | |
| CN111175718B (en) | Automatic target recognition method and system for ground radar combining time-frequency domains | |
| CN107577999B (en) | Radar signal intra-pulse modulation mode identification method based on singular value and fractal dimension | |
| CN102437984A (en) | Modulation signal identification method based on complexity characteristic under low signal-to-noise ratio condition | |
| CN109471074A (en) | Recognition Method of Radar Emitters based on singular value decomposition Yu one-dimensional CNN network | |
| CN108696331A (en) | A kind of signal reconfiguring method based on generation confrontation network | |
| CN104135327A (en) | Spectrum sensing method based on support vector machine | |
| CN103247059A (en) | Remote sensing image region of interest detection method based on integer wavelets and visual features | |
| CN104331583B (en) | A kind of Multifractal Modeling method based on Observed sea clutter | |
| CN101763514A (en) | Image segmentation method based on characteristic importance sorting spectral clustering | |
| CN110166387A (en) | A kind of method and system based on convolutional neural networks identification signal modulation system | |
| CN109061774A (en) | A kind of thunderstorm core relevance processing method | |
| CN102867183A (en) | Method and device for detecting littered objects of vehicle and intelligent traffic monitoring system | |
| Li | A new robust signal recognition approach based on holder cloud features under varying SNR environment | |
| CN107390259A (en) | A kind of nuclide identification method based on SVD and SVM | |
| CN104796365A (en) | Modulating signal recognition method based on complexity feature under low signal to noise ratio | |
| CN108090462A (en) | A kind of Emitter Fingerprint feature extracting method based on box counting dimension | |
| CN106548136A (en) | A kind of wireless channel scene classification method | |
| CN104809447A (en) | Radiation source individual feature extraction method | |
| CN102509299B (en) | Image salient area detection method based on visual attention mechanism | |
| CN104408472A (en) | Wishart and SVM (support vector machine)-based polarimetric SAR (synthetic aperture radar) image classification method | |
| CN103164619B (en) | Grounding net of transformer substation corrosion rate pattern recognition method based on best discriminant technique criterion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160323 |