CN110163040A - Radar emitter signal identification technology in non-gaussian clutter - Google Patents
Radar emitter signal identification technology in non-gaussian clutter Download PDFInfo
- Publication number
- CN110163040A CN110163040A CN201810261342.7A CN201810261342A CN110163040A CN 110163040 A CN110163040 A CN 110163040A CN 201810261342 A CN201810261342 A CN 201810261342A CN 110163040 A CN110163040 A CN 110163040A
- Authority
- CN
- China
- Prior art keywords
- signal
- frequency
- time
- radar
- gaussian clutter
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention belongs to the Radar Signal Processing Technology fields under non-Gaussian clutter environment, disclose a kind of Radar Signal Recognition method based on GENERALIZED VARIATIONAL mode decomposition combination SVM, GENERALIZED VARIATIONAL mode decomposition is carried out to the radar emitter signal received, obtains intrinsic modal components IMF；The smooth and pseudo Wigner-Ville time-frequency distributions matrix of each intrinsic modal components is calculated, and extracts the R é nyi entropy latent structure feature vector T of each time-frequency distributions；Finally Classification and Identification is carried out using SVM；When broad sense signal-to-noise ratio is greater than 5dB, the discrimination of various types of signal reaches 65% or more, and especially when broad sense signal-to-noise ratio is greater than 10dB, the discrimination of various types of signal reaches 90% or more, it can be seen that, recognition effect of the invention is preferable.
Description
Technical field
The invention belongs to GENERALIZED VARIATIONAL mould is based under Radar Signal Processing Technology field more particularly to non-Gaussian clutter environment
The radar emitter signal classifying identification method that state is decomposed.
Background technique
Radar emitter signal identification is the key technology during radar electric is scouted, and directly affects electronic reconnaissance equipment
Can performance be simultaneously related to subsequent warfare decision, it is both the purpose of reconnaissance system signal processing and judges enemy weapon
The important evidence for threatening situation has highly important status and effect during Radar ECM, therefore studies radar
Emitter Signals Recognition is of practical significance.Currently, the research identified for radar emitter signal under Gaussian Clutter environment
Many achievements are had already appeared.Ataollah Abrahamzadeh et al. identified using 8 rank squares and 8 rank cumulants, can be with
The discrimination reached under Low SNR, but with the increase of cumulant and square, its calculated value is also bigger
(Abrahamzadeh A,Seyedin S A,Dehghan M.Digital-signal-type identification
using an efficient identifier[J].Eurasip Journal on Advances in Signal
Processing,2007,2007(1):037690.)；It is general to transport big et al. radar of the proposition based on instantaneous frequency Further Feature Extraction
Emitter Signals classification aspect, but the limitation by instantaneous Frequency Estimation method, this method require signal-to-noise ratio also relatively high (general
Big, Jin Weidong is transported, messes things up that is recruited to learn based on emitter Signals classification [J] the Southwest Jiaotong University of instantaneous frequency Further Feature Extraction
Report, 2007,42 (3): 373-379.)；Prakasam knows signal as feature using the statistic histogram of wavelet coefficient
Not, preferable discrimination can be reached under conditions of signal-to-noise ratio is 5dB, but this method is mainly for signal of communication
(Prakasam P,Madheswaran M.Digital Modulation identification model using
wavelet transform and statistical parameters[J].Journal of Computer Systems
Networks&Communications,2008,2008(3):6.)；Yu Zhibin proposes to be based on WAVELET PACKET DECOMPOSITION, using Energy-Entropy
With Random entropy constitutive characteristic vector, more satisfied correct recognition rata is obtained in larger SNR ranges, but this method is
Preferable recognition effect is obtained under noise circumstance more than moderate strength, in the case where noise relatively low (SNR < 5dB), perhaps
The recognition effect of multi signal is with regard to less desirable (emitter Signals of Yu Zhibin, Chen Chunxia, the Jin Weidong based on fusion entropy feature
Identify [J] modern radar, 2010,32 (1): 34-38.)；For low probability of intercept radar Modulation recognition, Persson C is proposed
It converts to obtain the time-frequency figure of signal using Wigner-Ville first, image procossing then is carried out to it and extracts feature, but is real
It tests the result shows that this method recognition effect is less desirable, the cross term mainly due to Wigner-Ville distribution seriously affects
The feature extraction of signal, in addition the influence of time-frequency image noise could not be effectively reduced in image processing method employed in the document
(Persson C.Classification and Analysis of Low Probability of Intercept Radar
Signals Using Image Processing[J].Thesis Collection,2003.)；Radar is believed in Zou Xingwen proposition
Number time-frequency image be converted to grayscale image, directly using the pixel after normalization as identification feature, achieve preferable identification
Effect, but since, directly using pixel as feature, feature dimensions are larger in text, it is be easy to cause " dimension disaster ", and only to 5 in text
Kind radar emitter signal carries out Classification and Identification, needs further to verify (Zou for the validity of more type signals
It promoting culture, Zhang Gexiang, Li Ming wait a kind of radar emitter signal new Classification Method [J] data acquisition and procession of, and 2009,24
(4):487-492.).However, inevitably there is the clutter of some spike shapes in actual radar investigation environment,
The distribution character of this type clutter is different from Gaussian Profile, usually portrays it with α Stable distritation.Since non-gaussian clutter is not deposited
In each rank square of limited second order or more, so that radar emitter signal recognition methods is no longer suitable under existing Gaussian Clutter environment
With.
In conclusion problem of the existing technology is: being only applicable in the environment of Gaussian Clutter, for non-gaussian clutter
Interference, existing technology can not obtain good effect, and be only applicable to the identification of a small number of source signals, for multiple source signals
Recognition effect it is poor.
Summary of the invention
In view of the problems of the existing technology, the present invention provides radar emitter signals under a kind of non-gaussian clutter to identify
Method.
The invention is realized in this way radar emitter signal identification technology in non-gaussian clutter, the non-gaussian clutter
Middle radar emitter signal recognition methods includes:
Step 1 carries out GENERALIZED VARIATIONAL mode decomposition to signal is received, obtains K intrinsic modal components IMF；
Step 2 calculates the smooth and pseudo Wigner-Ville time-frequency distributions matrix of each intrinsic modal components, and extracts each
The R é nyi entropy latent structure feature vector T of time-frequency distributions；
Step 3 carries out Classification and Identification using SVM.
Further, described to signal progress GENERALIZED VARIATIONAL mode decomposition is received, obtain K intrinsic modal components IMF's
Process is as follows:
1) nonlinear transformation, the f (t) obtained are carried out to reception signal r (t), it may be assumed that
2) it initializesEnabling its initial value is 0, and it is that (K is whole to K that mode number is decomposed in setting
Number, is set as K=10 herein).
3) n=n+1 executes circulation；
4) basisWithMore
New uk and ωk；
5) λ is updated, i.e.,
6) discrimination precision ε is given, until reaching iteration stopping conditionEnd loop,
It obtains eachAnd centre frequency ωk, K narrowband IMF component is finally obtained by Fourier inversion.
Further, the smooth and pseudo Wigner-Ville time-frequency distributions matrix of each intrinsic modal components of calculating, and
The R é nyi entropy latent structure feature vector T of each time-frequency distributions is extracted, process is as follows
1) VMD modal components u is calculatedkSmooth and pseudo Wigner-Ville time-frequency conversion, obtain the time-frequency distributions square of signal
Battle array time-frequency distributions P (t, f)；
In formula: h (τ) and g (τ) is the even window function of two realities, and h (0)=g (0)=1.
2) the R é nyi entropy of signal time-frequency distributions P (t, f) is extracted:
α is the order of R é nyi entropy, and α=2 are arranged in the present invention；
3) construction feature vector T:
Further, Classification and Identification is carried out to the radar emitter signal in non-gaussian clutter using SVM classifier
Realize radar emitter signal type identification.
Advantages of the present invention and good effect are as follows: extract time-frequency distributions entropy feature using GENERALIZED VARIATIONAL mode decomposition and carry out thunder
Up to emitter Signals type identification；Recognition effect of the invention is preferable.
Detailed description of the invention
Fig. 1 is radar emitter signal recognition methods flow chart under a kind of non-gaussian clutter provided in an embodiment of the present invention.
Fig. 2 is radar emitter signal recognition performance schematic diagram under non-gaussian clutter provided in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
Application principle of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, radar emitter signal recognition methods packet in a kind of non-gaussian clutter provided in an embodiment of the present invention
Include following steps:
S101: GENERALIZED VARIATIONAL mode decomposition is carried out to signal is received, obtains K intrinsic modal components IMF；
S102: when calculating the smooth and pseudo Wigner-Ville time-frequency distributions matrix of each intrinsic modal components, and extracting each
The R é nyi entropy latent structure feature vector T of frequency division cloth；
S103: Classification and Identification is carried out using SVM.
Application principle of the invention is further described with reference to the accompanying drawing.
Radar emitter signal recognition methods in a kind of non-gaussian clutter provided in an embodiment of the present invention the following steps are included:
S1 carries out GENERALIZED VARIATIONAL mode decomposition to signal is received, and obtains K intrinsic modal components IMF；
Receipt signal model under non-gaussian clutter, expression formula are as follows:
R (t)=s (t)+w (t)；
Wherein, s (t) is the radar signal sent, general pulse signal (CW), linear frequency modulation (LFM) signal, phase code
(PSK) signal, frequency coding (FSK) signal, even frequency modulation frequency modulation (EQFM) signal, CW with frequency modulation (FMCW) signal, COSTAS
Frequency modulated signal.W (t) is non-gaussian related clutter.
If s (t) is general pulse signal (CW), expression formula are as follows:
Wherein: A is signal amplitude, f0For carrier frequency, T is pulse width.
If s (t) is linear frequency modulation (LFM) signal, expression formula are as follows:
Wherein: A is signal amplitude, f0For original frequency, k is chirp rate,For first phase, T is pulse width.
If s (t) is frequency coding (FSK) signal, expression formula are as follows:
Wherein: fi∈{f1,f2,L,fM, M is frequency number, and N is code element number, TpFor symbol width, u (t) is subpulse.
If s (t) is phase code (PSK) signal, expression formula are as follows:
Wherein: φi∈ { 2 π (m-1)/M, m=1,2 ..., M }, M are number of phases, and N is code element number, TpFor symbol width, u
It (t) is subpulse, fcFor carrier frequency.
If s (t) is even frequency modulation frequency modulation (EQFM) signal, expression formula are as follows:
Wherein: A is signal amplitude, f0For carrier frequency, T is pulse width, and k is the index of modulation, and B is signal bandwidth.K and T and B
Relationship are as follows: k=8B/3T2。
If s (t) is CW with frequency modulation (FMCW) signal, expression formula are as follows:
Wherein: s (t) is the signal of a cycle of symmetric triangular linear FM signal, and B is signal bandwidth, fcFor signal
Carrier frequency, tmFor signal positive frequency modulation or negative frequency modulation part-time, cycle T=2tm。
If s (t) is COSTAS frequency modulated signal, expression formula are as follows:
Wherein: TrFor the pulse repetition period, N is subpulse number, and u (t) is subpulse, fnFor n-th of subpulse frequency,
Rect (t) is rectangular function, and T is subpulse width.
W (t) is α Stable distritation related clutter, the characteristic function of w (t) are as follows:
φ (u)=exp (jau- γ | u |α[1+jβsgn(u)ω(u,α)])；
Wherein:
Wherein, parameter alpha is characterized index, for characterizing the power of pulse feature.α is smaller, and pulse feature is stronger；α is bigger, pulse
Property it is weaker, as α=2 impulsive noise degenerate be Gaussian noise.Parameter a determines the center of distribution.Parameter γ is disperse system
Number, degree of scatter of the measurement sample with respect to mean value.Parameter beta determines the crooked degree of distribution.As a=0 and γ=1, referred to as
Standard α Stable distritation can be denoted as S α S distribution as β=a=0.
GENERALIZED VARIATIONAL mode decomposition is carried out to signal is received, the process for obtaining K intrinsic modal components IMF is as follows:
1) nonlinear transformation, the f (t) obtained are carried out to reception signal r (t), it may be assumed that
2) it initializesEnabling its initial value is 0, and it is that (K is whole to K that mode number is decomposed in setting
Number, is set as K=10 herein).
3) n=n+1 executes circulation；
4) basisWithIt updates
Uk and ωk；
5) λ is updated, i.e.,
6) discrimination precision ε is given, until reaching iteration stopping conditionEnd loop obtains
It is eachAnd centre frequency ωk, K narrowband IMF component is finally obtained by Fourier inversion.
S2 calculates separately smooth and pseudo Wigner-Ville time-frequency distributions matrix to the intrinsic modal components that step S1 is obtained, and
The R é nyi entropy latent structure feature vector T for extracting each time-frequency distributions is carried out as follows:
1) VMD modal components u is calculatedkSmooth and pseudo Wigner-Ville time-frequency conversion, obtain the time-frequency distributions square of signal
Battle array time-frequency distributions P (t, f)；
In formula: h (τ) and g (τ) is the even window function of two realities, and h (0)=g (0)=1.
2) the R é nyi entropy of signal time-frequency distributions P (t, f) is extracted:
α is the order of R é nyi entropy, and α=2 are arranged in the present invention；
3) construction feature vector T:
S3 carries out Classification and Identification to R é nyi entropy feature vector using SVM classifier to realize Radar emitter
The type identification of signal.
Application effect of the invention is explained in detail below with reference to emulation.
In order to assess performance of the invention, emulation experiment below uses 7 kinds of above-mentioned signals.Using SVM into
Row Classification and Identification.The parameter setting of above-mentioned 7 kinds of signals is as follows: FSK and psk signal use 13 Barker codes, LFM frequency deviation
5MHZ, FRANK polyphase codes compression of signal pulse ratio are 64.In the broad sense SNR ranges of 5~20dB, believe in each broad sense
It makes an uproar than under, every kind of signal generates 200 emitter Signals, amount to 1400 experiment samples, wherein 700 are training set, 700
For test set.Its simulation result as shown in Fig. 2, when broad sense signal-to-noise ratio be greater than 5dB when, the discrimination of various types of signal reach 65% with
On, especially when broad sense signal-to-noise ratio is greater than 10dB, the discrimination of various types of signal reaches 90% or more, it is seen then that identification of the invention
Effect is preferable.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (5)
1. radar emitter signal recognition methods in a kind of non-gaussian clutter, which is characterized in that thunder in the non-gaussian clutter
Include: up to emitter Signals Recognition method
Step 1 carries out GENERALIZED VARIATIONAL mode decomposition to signal is received, obtains intrinsic modal components IMF；
Step 2, calculates the smooth and pseudo Wigner-Ville time-frequency distributions matrix of each intrinsic modal components, and extracts each time-frequency
The R é nyi entropy latent structure feature vector T of distribution；
Step 3 carries out Classification and Identification using SVM.
2. radar emitter signal recognition methods in a kind of non-gaussian clutter as described in claim 1, which is characterized in that described
GENERALIZED VARIATIONAL mode decomposition is carried out to signal is received, the process for obtaining intrinsic modal components IMF is as follows:
1) nonlinear transformation, the f (t) obtained are carried out to reception signal r (t), it may be assumed that
2) it initializesEnabling its initial value is 0, and will setting decompose mode number be K (K is integer, this
Place is set as K=10).
3) n=n+1 executes circulation；
4) basisWithUpdate ukAnd ωk；
5) λ is updated, i.e.,
6) discrimination precision ε is given, until reaching iteration stopping conditionEnd loop,
It obtains eachAnd centre frequency ωk, K narrowband IMF component is finally obtained by Fourier inversion.
3. radar emitter signal recognition methods in a kind of non-gaussian clutter as described in claim 1, which is characterized in that calculate
The smooth and pseudo Wigner-Ville time-frequency distributions matrix of each intrinsic modal components, and the R é nyi entropy for extracting each time-frequency distributions is special
Construction feature vector T is levied, process is as follows
1) VMD modal components u is calculatedkSmooth and pseudo Wigner-Ville time-frequency conversion, obtain the time-frequency distributions matrix time-frequency of signal
It is distributed P (t, f)；
In formula: h (τ) and g (τ) is the even window function of two realities, and h (0)=g (0)=1.
2) the R é nyi entropy of signal time-frequency distributions P (t, f) is extracted:
α is the order of R é nyi entropy, and α=2 are arranged in the present invention；
3) construction feature vector T:
。
4. radar emitter signal recognition methods in a kind of non-gaussian clutter as described in claim 1, which is characterized in that utilize
SVM classifier carries out the modulation that Classification and Identification realizes radar signal to the radar emitter signal in non-gaussian clutter
The identification of type.
5. radar emitter signal identification in a kind of non-Gaussian clutter environment described in a kind of application Claims 1 to 5 any one
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810261342.7A CN110163040B (en) | 2018-03-28 | 2018-03-28 | Radar radiation source signal identification technology in non-Gaussian clutter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810261342.7A CN110163040B (en) | 2018-03-28 | 2018-03-28 | Radar radiation source signal identification technology in non-Gaussian clutter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110163040A true CN110163040A (en) | 2019-08-23 |
| CN110163040B CN110163040B (en) | 2022-12-30 |
Family
ID=67636411
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810261342.7A Active CN110163040B (en) | 2018-03-28 | 2018-03-28 | Radar radiation source signal identification technology in non-Gaussian clutter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110163040B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401168A (en) * | 2020-03-06 | 2020-07-10 | 上海神添实业有限公司 | Multi-layer radar feature extraction and selection method for unmanned aerial vehicle |
| CN112287796A (en) * | 2020-10-23 | 2021-01-29 | 电子科技大学 | Radiation source identification method based on VMD-Teager energy operator |
| CN113343897A (en) * | 2021-06-25 | 2021-09-03 | 中国电子科技集团公司第二十九研究所 | Method for accelerating signal processing based on slope change of radiation signal |
| CN113723244A (en) * | 2021-08-20 | 2021-11-30 | 中国电子科技集团公司第二十八研究所 | Radar radiation source signal separation method based on improved variational modal decomposition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279390A (en) * | 2011-05-06 | 2011-12-14 | 西南交通大学 | Intra-pulse modulation and recognition method of low signal-to-noise radar radiation source signal |
| CN106529478A (en) * | 2016-11-08 | 2017-03-22 | 中国人民解放军空军工程大学 | Radar radiation source signal identification method according to three-dimensional entropy characteristic |
| CN106778610A (en) * | 2016-12-16 | 2017-05-31 | 哈尔滨工程大学 | A kind of intra-pulse modulation recognition methods based on time-frequency image feature |
-
2018
- 2018-03-28 CN CN201810261342.7A patent/CN110163040B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279390A (en) * | 2011-05-06 | 2011-12-14 | 西南交通大学 | Intra-pulse modulation and recognition method of low signal-to-noise radar radiation source signal |
| CN106529478A (en) * | 2016-11-08 | 2017-03-22 | 中国人民解放军空军工程大学 | Radar radiation source signal identification method according to three-dimensional entropy characteristic |
| CN106778610A (en) * | 2016-12-16 | 2017-05-31 | 哈尔滨工程大学 | A kind of intra-pulse modulation recognition methods based on time-frequency image feature |
Non-Patent Citations (1)
| Title |
|---|
| 白航等: "基于时频分布Rényi熵特征的雷达辐射源识别", 《电路与系统学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111401168A (en) * | 2020-03-06 | 2020-07-10 | 上海神添实业有限公司 | Multi-layer radar feature extraction and selection method for unmanned aerial vehicle |
| CN111401168B (en) * | 2020-03-06 | 2023-11-17 | 上海神添实业有限公司 | Multilayer radar feature extraction and selection method for unmanned aerial vehicle |
| CN112287796A (en) * | 2020-10-23 | 2021-01-29 | 电子科技大学 | Radiation source identification method based on VMD-Teager energy operator |
| CN112287796B (en) * | 2020-10-23 | 2022-03-25 | 电子科技大学 | Radiation source identification method based on VMD-Teager energy operator |
| CN113343897A (en) * | 2021-06-25 | 2021-09-03 | 中国电子科技集团公司第二十九研究所 | Method for accelerating signal processing based on slope change of radiation signal |
| CN113343897B (en) * | 2021-06-25 | 2022-06-07 | 中国电子科技集团公司第二十九研究所 | Method for accelerating signal processing based on slope change of radiation signal |
| CN113723244A (en) * | 2021-08-20 | 2021-11-30 | 中国电子科技集团公司第二十八研究所 | Radar radiation source signal separation method based on improved variational modal decomposition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110163040B (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163040A (en) | Radar emitter signal identification technology in non-gaussian clutter | |
| CN107301432B (en) | Self-adaptive radiation source modulation identification method based on time-frequency analysis | |
| CN110133599B (en) | Intelligent radar radiation source signal classification method based on long-time and short-time memory model | |
| CN108512797B (en) | Radar communication integrated signal design method based on orthogonal frequency division multiplexing | |
| CN107135176B (en) | Image domain communication signal modulation identification method based on fractional low-order cyclic spectrum | |
| CN111175718B (en) | Automatic target recognition method and system for ground radar combining time-frequency domains | |
| Li et al. | Radar signal recognition algorithm based on entropy theory | |
| Weinberg et al. | Bayesian framework for detector development in Pareto distributed clutter | |
| Li | A novel recognition algorithm based on holder coefficient theory and interval gray relation classifier | |
| CN103954961B (en) | Stepped frequency radar obstruction super-resolution one-dimensional image method | |
| CN106443625A (en) | Object identification method based on high-resolution one-dimensional image information fusion | |
| Zhang et al. | Radar emitter signal recognition based on resemblance coefficient features | |
| Hou et al. | Reducing micro‐Doppler effect in compressed sensing ISAR imaging for aircraft using limited pulses | |
| Zhang et al. | Complexity feature extraction of radar emitter signals | |
| Sobolewski et al. | Automatic modulation recognition techniques based on cyclostationary and multifractal features for distinguishing LFM, PWM and PPM waveforms used in radar systems as example of artificial intelligence implementation in test | |
| Chen et al. | Feature extraction using wavelet transform for radar emitter signals | |
| CN104237864A (en) | Distance extension target detection method on basis of matched fuzzy function | |
| CN109581370A (en) | Multipolarization HRRP scattering centers extraction method based on multidirectional amount ANM | |
| Xue et al. | Cognitive‐Based High Robustness Frequency Hopping Strategy for UAV Swarms in Complex Electromagnetic Environment | |
| CN114710215A (en) | Method for fast blind detection of frequency hopping signal | |
| Doody et al. | Low‐frequency synthetic aperture radar data‐dome collection with the Bright Sapphire II instrument | |
| Mingqiu et al. | Radar signal feature extraction based on wavelet ridge and high order spectral analysis | |
| CN103886327B (en) | Polarized SAR image classification method based on 2D-KPCA | |
| Wang et al. | 2D scattering centre intensity pre‐estimated method based on matrix pencil method | |
| Liu et al. | Specific Emitter Identification Method based on Deep Ensemble Learning |
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 |