CN111814703B - HB-based signal joint feature extraction method under non-reconstruction condition - Google Patents
HB-based signal joint feature extraction method under non-reconstruction condition Download PDFInfo
- Publication number
- CN111814703B CN111814703B CN202010671516.4A CN202010671516A CN111814703B CN 111814703 B CN111814703 B CN 111814703B CN 202010671516 A CN202010671516 A CN 202010671516A CN 111814703 B CN111814703 B CN 111814703B
- Authority
- CN
- China
- Prior art keywords
- order cumulant
- bispectrum
- radiation source
- signal
- order
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 13
- 230000005855 radiation Effects 0.000 claims abstract description 48
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 238000001228 spectrum Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims abstract description 3
- 101100095566 Arabidopsis thaliana SEOC gene Proteins 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 11
- 238000012706 support-vector machine Methods 0.000 claims description 8
- 238000005562 fading Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004422 calculation algorithm Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 7
- 230000001052 transient effect Effects 0.000 description 7
- 239000000654 additive Substances 0.000 description 4
- 230000000996 additive effect Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- 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
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention belongs to the field of signal processing, provides an HB-based signal combined feature extraction method under a non-reconstruction condition aiming at the problem that a single feature has an identification result which is easy to drift, and is particularly used for processing the problem of radiation source signal classification and identification. The single feature is extracted as the identification feature, and sometimes the feature classification boundary is fuzzy, which may reduce the identification effect. The joint feature of high order cumulants combined with bispectrum is used to solve this problem. The high-order cumulant can well retain information such as amplitude, phase and the like, and the bispectrum is the lowest-order high-order spectrum and has the advantage of simple calculation. The radiation source signal is first generated, and the received signal is then compressively sampled by the MWC and its amplitude is normalized. And then calculating the three-six-order cumulant and the square eight-order cumulant, and extracting the characteristics of the high-order cumulant. And meanwhile, extracting the estimation characteristics of the bispectrum coefficients of the sampling matrix. And finally, transmitting the three different high-order cumulant features and the bispectrum coefficient estimation features into an SVM classifier for classification by using the three different high-order cumulant features and the bispectrum coefficient estimation features as joint features.
Description
Technical Field
The invention belongs to the field of signal processing, relates to a signal joint feature extraction method based on HB under a non-reconstruction condition, and is particularly used for processing the problem of classification and identification of radiation source signals.
Background
A particular radiation source identification distinguishes individual emitters from other emitters by their unique characteristics, thereby identifying different emitters. The radiation source identification technology is mainly used in military communication. It becomes increasingly important as new technologies emerge, such as cognitive radio and ad hoc networks.
Based on the operating mode of the emitter, emitter identification can be performed on transient or steady state signals by the emitter identification. Transient signals, also known as on/off signals, and the resulting emitter specificity can be used to extract features. To extract the feature of the transient signal, the main method is to extract the transient signal by detecting the start point and the end point of noise. However, transient signals are short in duration and difficult to capture. It is also susceptible to interference from complex channels and affects the recognition of the transmitter. The steady state signal is transmitted between the transient start and end of the overall signal. The detection and acquisition of steady state signals is simpler than transient state signals. However, since the steady-state feature is easily broken, extraction of the steady-state feature becomes difficult. For steady state signals, various feature extraction schemes were investigated. The most common methods are based on time-frequency analysis algorithms such as short-time fourier transforms, wavelets, etc. Besides these methods, like cumulant, bispectrum is also used in large quantities.
Although the traditional characteristic extraction method can effectively extract the characteristics of the radiation source, the single characteristic sometimes causes the drift of the identification result, and the correct identification rate is reduced. The invention provides a Joint Fingerprint feature (HB) extraction algorithm based on high-order cumulant and Bispectrum coefficient estimation. The method can solve the problem that the identification result is easy to drift in the single characteristic, and improves the identification stability of the radiation source.
Disclosure of Invention
The invention provides a multi-feature combined feature identification method aiming at the problem that the identification result is easy to drift in a single feature.
The technical scheme adopted by the invention is as follows:
the signal joint feature extraction based on HB under the non-reconstruction condition mainly comprises the following steps:
step 4, extracting estimation characteristics of the bispectrum coefficients;
and 5, classifying and identifying the radiation source signals by using a Support Vector Machine (SVM).
Has the advantages that: 1) compared with the VMD _ SF algorithm and the EMD _ EM algorithm, the method has better identification effect under the condition that three radiation sources exist; 2) the identification difficulty is increased along with the increase of the number of the radiation sources to be identified, but the identification rate can still reach 90% when the signal-to-noise ratio of 5 radiation sources reaches 10 dB.
Drawings
FIG. 1 is a block diagram of an MWC system;
FIG. 2 is a MWC spectrum shifting diagram;
FIG. 3 is a flow chart of a HB-based signal joint feature extraction algorithm under non-reconstruction conditions;
FIG. 4 is a TSOC characteristic profile of the present invention;
FIG. 5 is a SEOC characteristic profile of the present invention;
FIG. 6 is a bispectrum coefficient estimation feature profile of the present invention;
FIG. 7 is a HB joint signature distribution plot of the invention;
FIG. 8 is a graph comparing the recognition rate of the present invention in a Gaussian white noise channel with the VMD _ SF and EMD _ EM algorithms;
FIG. 9 is a graph comparing the recognition rate of the VMD _ SF and EMD _ EM algorithms in fading channels according to the present invention;
FIG. 10 is a graph comparing the recognition rate of the present invention with VMD _ SF and EMD _ EM algorithms for 4 radiation sources;
fig. 11 is a graph comparing the recognition rate of the present invention with VMD _ SF and EMD _ EM algorithms under 5 radiation sources.
Detailed Description
1. Generating a radiation source signal
A transmitter comprises a plurality of nonlinear devices, and the established system model mainly considers the mechanism that the nonlinearity of a power amplifier generates a radiation source fingerprint. Establishing Taylor series model, orderFor the order of the Taylor polynomial, for the transmitterCan be expressed as
Wherein
Is an input signal of a power amplifier, whereinIs as followsA transmitter in time The baseband (or baseband) modulated signal of (b),is the total number of radiation sources.Is the frequency of the carrier wave and,is a time period of the sampling, and,are coefficients of taylor polynomials.Representing spokesSource power amplifierThe output signal of (1). Time of dayThe received signal can be expressed as
WhereinIs from a radiation sourceThe channel fading coefficients to the receiver are,is additive noise. Signal obtained by substituting formula (1) for formula (3)Is composed of
2. Radiation source signal preprocessing
In the signal preprocessing section, we use a Modulation Wideband Converter (MWC), and the schematic block diagram of its sampling system is shown in fig. 1. Input signalThe system is divided into m paths of input MWC sampling systems, each undersampled channel consists of a pseudo-random frequency mixing channel, a low-pass filtering (LPF) channel and a low-speed ADC channel, and the output result is a compressed sampling sequence of an original signal. Fig. 2 is a spectrum moving diagram of each channel of the MWC, after spectrum cutting, the whole frequency band is divided into L spectrums, and after moving and mixing of each sub-band, the global information of the signal in the channel is included.
WhereinIs thatAnd (5) maintaining column vectors. Avoiding the influence caused by intensity sensitivity and amplitude sensitivity when extracting the characteristics, realizing the translation compensation of the sample data by adopting an envelope alignment method, and carrying out amplitude normalization processing according to the following formula
Bispectrum is a feature widely used in higher order statistical analysis, the two-dimensional discrete Fourier transform of the third-order cumulant of a signal: (DFT, Discrete Fourier transform) is bispectrum. For a determined discrete-time signalIts third order cumulant is
3. Extracting high-order cumulant features
Extracting different high-Order Cumulants (HOC) characteristics, including three-six Order Cumulant (TSOC, Tri-six-Order Cumulant) and Square Eight Order Cumulant (SEOC, Square elevation-Order Cumulant). The CSD of the received signal is obtained via MWC compressive sampling. For theThe time-varying moment of the signal is defined as
Wherein (8) thereinReferred to as signalsThe product of the hysteresis of (a) is,is thatThe conjugate of (a) to (b),is the total number of conjugates.
Index setIs named as,Is the number of elements in a partition, and is used by the index set belonging to the partitionAnd (4) showing. According to a Moment-cumulant (MC) conversion formula,is/are as followsThe cumulative amount of order is expressed as
Therefore, we can obtain the following relationship between the moment and the accumulated quantity
TSOC, SEOC and TSOC characteristics can be respectively extracted from the parametersCan be expressed as
The TSOC and SEOC are extracted as two high-order cumulant features as in the above formula.
FIGS. 4 and 5 show a comparison of the TSOC characteristic and the SEOC characteristic of three radiation source units with different Taylor coefficients, wherein the Taylor coefficient of the radiation source 1 isThe Taylor coefficient of the radiation source 2 isThe Taylor coefficient of the radiation source 3 isThe baseband modulation modes are all 8 QAM. Fig. 4 is a TSOC characteristic distribution diagram in which the horizontal axis represents the number of signal points of the radiation source and the vertical axis represents the TSOC characteristic value. It can be seen that the three radiation source signals can be roughly classified and identified, but the boundary is confused, and if the boundary is interfered by the outside, the identification rate is reduced. The TSOC single characteristic is used as a classification judgment basis to be unfavorable for the classification of the radiation source signal. Fig. 5 is an SEOC characteristic distribution diagram in which the horizontal axis represents the number of signal points of the radiation source and the vertical axis represents the SEOC characteristic value. In the figure, the mean value of the SEOC characteristic values of the radiation source signal 1 is 11.4, the mean value of the SEOC characteristic values of the radiation source signal 2 is 10.9, and the mean value of the SEOC characteristic values of the radiation source signal 3 is 12.0. The SEOC characteristic values of the three signals are more confusing, but still feasible as one of the joint characteristics,if the feature classification identification is used alone, the result is seriously distorted.
4. Extracting bispectrum coefficient estimation features
Equation (7) has given the discrete-time signalThird order cumulant ofCalculation formula, thereforeDouble spectrum ofIs composed of
The bispectrum is to represent one frequency by two other frequencies, and the invention adopts a direct estimation method to carry outAnd performing double-spectrum estimation. Sampling the dataIs divided intoSegments, each segment comprisingThe data between two adjacent ends can have overlap, and are recorded as convenient description. DFT coefficient calculation for each segment of data
Wherein,. Is provided withCalculating triple correlation of each DFT coefficient for sampling rate to obtain correlation sequence
WhereinIs shown asTriple correlation of segment data,. The bispectrum coefficient of the sample data is estimated as
Fig. 6 shows the distribution of the estimated characteristic of the bispectrum coefficient, in which the horizontal axis represents the number of signal points of the radiation source and the vertical axis represents the estimated characteristic value of the bispectrum coefficient. We can see that the radiation source signal 1 can be effectively distinguished from the other two signals, but still avoid the boundary confusion of the radiation source signal 2 and the radiation source signal 3. Fig. 7 is a HB joint feature distribution diagram, which shows three-dimensional features, and three coordinate axes respectively show the TSOC feature, the SEOC feature, and the bispectrum coefficient estimation feature. It can be clearly seen that when three features are combined into a combined three-dimensional feature, the different radiation source individuals can be completely distinguished.
5. Classification and identification of radiation source signals by using Support Vector Machine (SVM)
The support vector machine is a supervised learning classifier for the two-classification problem. Training set,Is a training vector that is a function of,is a class of tags. We consider the simplest case where positive and negative label data can be represented by a simple hyperplaneSo as to separate the components of the mixture,
wherein,is the normal vector of the hyperplane;is the perpendicular distance from the origin to the hyperplane. Of support vector machinesThe purpose is to optimize the hyperplane to its edgesTo a maximum ofRepresenting the closest distance of the positive point to the hyperplane,representing the closest distance of the negative point to the hyperplane). The hyperplane thus found serves as a separation boundary for different classes of data. For the case where the number of classes is greater than 2, in general, the multi-classification problem can be handled by reducing it to a few bi-classification problems.
And (3) identifying the joint features given by the figure 7 by using the SVM to obtain an identification result. Fig. 8 is a graph comparing the recognition rate of the present invention and VMD _ SF and EMD _ EM algorithms through an additive white gaussian noise channel in the case of class 3 radiation source signals. It can be seen from the figure that the recognition accuracy of the invention is higher at each SNR than the other two algorithms, and at SNR = -5db, the correct recognition rate of the invention is 90%, the recognition rate is 20% higher than VMD _ SF, and 21% higher than EMD _ EM. Under low SNR, the recognition effect of the recognition algorithm based on HB in the radiation source recognition field is better than that of the other two algorithms.
Fig. 9 is a comparison graph of the recognition rates of the fading channel of the present invention and VMD _ SF and EMD _ EM algorithms under the condition of 3 types of radiation source signals, and compared with fig. 8, the recognition rates of the three algorithms in the fading channel are all decreased, the recognition rate of the present invention can reach more than 90% after SNR >8db, and the recognition rates of the VMD _ SF and EMD _ EM algorithms are 81% and 73% respectively when SNR =20db, so that it can be seen that the present invention can still successfully recognize radiation source individuals under the fading channel.
Fig. 10 is a graph of the identification performance of the present invention and VMD _ SF and EMD _ EM algorithms through an additive white gaussian noise channel in the case of class 4 radiation source signals. Fig. 11 shows a graph of the recognition performance through an additive white gaussian noise channel in the case of a class 5 radiation source signal. It can be seen from the figure that the recognition rates of all three algorithms are reduced as the number of radiation sources increases, but the recognition rate of the present invention is always the highest compared to the other two algorithms.
Claims (3)
1. A signal joint feature extraction method based on HB under the non-reconstruction condition is characterized by comprising the following steps:
step 1, generating a radiation source signal;
step 2, preprocessing the radiation source signal;
step 3, extracting high-order cumulant features, wherein the formula for extracting the high-order cumulant is
And obtaining the relation between the moment and the cumulant through the formula as
Next, the three-Sixth Order Cumulant (TSOC, Tri-six-Order Cumulant) and the Square Eight Order Cumulant (SEOC, Square elevation-Order Cumulant) are extracted as characteristics, wherein
Step 4, extracting estimation characteristics of bispectrum coefficients, firstly sampling dataSegmentation, as
The DFT coefficients for each piece of data are then found,
then, according to the triple correlation of each DFT coefficient, a correlation sequence is obtained,
finally, the estimation characteristics of the bispectrum coefficient are obtained,
and 5, using a Support Vector Machine (SVM) and adopting a combined characteristic consisting of three-six-order cumulant, square eight-order cumulant and double-spectrum coefficient as input to classify and identify the radiation source signals.
2. The method according to claim 1, wherein the HB-based signal joint feature extraction method under the non-reconstruction condition is characterized in that: step 1, modulating QAM signals in the process of generating signalsPerforming Taylor nonlinear processing, and adding fading coefficientAnd noiseGenerating a source signal, isAnd is and。
3. the method according to claim 1, wherein the HB-based signal joint feature extraction method under the non-reconstruction condition is characterized in that: receiving signals in step 2After MWC compression sampling, one is obtained Dimension matrix, denoted asAnd is made ofWill beThe amplitude is obtained after the normalization processing of the amplitude is carried out,
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010671516.4A CN111814703B (en) | 2020-07-13 | 2020-07-13 | HB-based signal joint feature extraction method under non-reconstruction condition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010671516.4A CN111814703B (en) | 2020-07-13 | 2020-07-13 | HB-based signal joint feature extraction method under non-reconstruction condition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111814703A CN111814703A (en) | 2020-10-23 |
CN111814703B true CN111814703B (en) | 2022-05-24 |
Family
ID=72842281
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010671516.4A Active CN111814703B (en) | 2020-07-13 | 2020-07-13 | HB-based signal joint feature extraction method under non-reconstruction condition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111814703B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115186714B (en) * | 2022-07-15 | 2023-07-21 | 中国人民解放军国防科技大学 | Network card frequency spectrum fingerprint feature amplification method based on feature correlation and self-adaptive decomposition |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470194A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院声学研究所 | Torpedo target recognition method |
CN104316317A (en) * | 2014-10-08 | 2015-01-28 | 西北工业大学 | Gear system multi-fault diagnosis method based on COM assemblies |
CN105137498A (en) * | 2015-09-17 | 2015-12-09 | 鲁东大学 | Underground target detection and recognition system and method based on feature fusion |
CN109165678A (en) * | 2018-07-28 | 2019-01-08 | 中国人民解放军战略支援部队信息工程大学 | Emitter Recognition and device based on bispectrum 3-D image textural characteristics |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6993440B2 (en) * | 2002-04-22 | 2006-01-31 | Harris Corporation | System and method for waveform classification and characterization using multidimensional higher-order statistics |
-
2020
- 2020-07-13 CN CN202010671516.4A patent/CN111814703B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470194A (en) * | 2007-12-26 | 2009-07-01 | 中国科学院声学研究所 | Torpedo target recognition method |
CN104316317A (en) * | 2014-10-08 | 2015-01-28 | 西北工业大学 | Gear system multi-fault diagnosis method based on COM assemblies |
CN105137498A (en) * | 2015-09-17 | 2015-12-09 | 鲁东大学 | Underground target detection and recognition system and method based on feature fusion |
CN109165678A (en) * | 2018-07-28 | 2019-01-08 | 中国人民解放军战略支援部队信息工程大学 | Emitter Recognition and device based on bispectrum 3-D image textural characteristics |
Non-Patent Citations (5)
Title |
---|
《Higher-order spectra and independent component analysis used for identification and SNR enhancement of acoustic emission signals》;J.G. De la Rosa et. al.;《MELECON 2006 - 2006 IEEE Mediterranean Electrotechnical Conference》;20060724;全文 * |
《基于三阶累积量图像纹理特征和SVM 的发动机故障诊断》;丁雷,曾锐利;《军事交通学院学报》;20180731;全文 * |
《基于调制宽带转换器的特定辐射源识别算法》;解建兰;《现代计算机》;20200505;全文 * |
《基于高阶累积量的数字调制信号识别》;张弛;吴瑛;周欣;《数据采集与处理》;20100930;全文 * |
《雷达目标特征提取与识别研究》;马元锋;《中国优秀硕士学位论文全文数据库 (信息科技辑)》;20070815;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111814703A (en) | 2020-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105678273B (en) | The starting point detection algorithm of radio-frequency fingerprint identification technology transient signal | |
Like et al. | Signal classification in fading channels using cyclic spectral analysis | |
Oyedare et al. | Estimating the required training dataset size for transmitter classification using deep learning | |
CN111163460B (en) | Radio frequency fingerprint extraction method based on multiple interval difference constellation trajectory diagram | |
CN111310700B (en) | Intermediate frequency sampling sequence processing method for radiation source fingerprint feature recognition | |
CN109359523B (en) | Satellite navigation interference type identification method based on SVM multi-classification algorithm | |
CN107392123B (en) | Radio frequency fingerprint feature extraction and identification method based on coherent accumulation noise elimination | |
Jeong et al. | Spectrogram-based automatic modulation recognition using convolutional neural network | |
CN105429719A (en) | Strong interference signal detection method based on power spectrum and multiple dimensioned wavelet transformation analysis | |
Satija et al. | Cyclostationary features based modulation classification in presence of non Gaussian noise using sparse signal decomposition | |
CN111814703B (en) | HB-based signal joint feature extraction method under non-reconstruction condition | |
CN114255487B (en) | Internet of things equipment identity authentication method based on semi-supervised radio frequency fingerprint extraction | |
Yang et al. | Radio frequency fingerprint identification based on stream differential constellation trace figures | |
West et al. | A wideband signal recognition dataset | |
Wang et al. | A new method of automatic modulation recognition based on dimension reduction | |
Liu et al. | A novel signal separation algorithm for wideband spectrum sensing in cognitive networks | |
Yin et al. | Co-channel multi-signal modulation classification based on convolution neural network | |
Wang et al. | A spatiotemporal multi-stream learning framework based on attention mechanism for automatic modulation recognition | |
Hazza et al. | Robustness of digitally modulated signal features against variation in HF noise model | |
CN113242201B (en) | Wireless signal enhanced demodulation method and system based on generation classification network | |
CN115378776A (en) | MFSK modulation identification method based on cyclic spectrum parameters | |
Ding et al. | Radio frequency fingerprint extraction based on singular values and singular vectors of time-frequency spectrum | |
Wang et al. | Novel radio-frequency fingerprint recognition scheme using multiwavelets-based cyclic-spectrum graph analysis | |
CN107341519A (en) | A kind of SVMs identification optimization method based on multiresolution analysis | |
Shi et al. | A radio frequency fingerprint identification method for wireless devices based on ShuffleNet-SVM |
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 |