CN114866311B - Radio frequency fingerprint extraction method based on time sequence characterization - Google Patents
Radio frequency fingerprint extraction method based on time sequence characterization Download PDFInfo
- Publication number
- CN114866311B CN114866311B CN202210464767.4A CN202210464767A CN114866311B CN 114866311 B CN114866311 B CN 114866311B CN 202210464767 A CN202210464767 A CN 202210464767A CN 114866311 B CN114866311 B CN 114866311B
- Authority
- CN
- China
- Prior art keywords
- radio frequency
- frequency fingerprint
- signal
- calculating
- time sequence
- 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 21
- 238000012512 characterization method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 30
- 239000011159 matrix material Substances 0.000 claims abstract description 13
- 238000011084 recovery Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims abstract description 10
- 238000009499 grossing Methods 0.000 claims abstract description 6
- 230000002776 aggregation Effects 0.000 claims abstract description 5
- 238000004220 aggregation Methods 0.000 claims abstract description 5
- 238000009877 rendering Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000005065 mining Methods 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0876—Network architectures or network communication protocols for network security for authentication of entities based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/336—Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Power Engineering (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a radio frequency fingerprint extraction method based on time sequence characterization, which comprises the following steps: collecting and processing output signals of the wireless device; encoding the scaled values into cosine of vector included angles, encoding corresponding time stamps into radiuses, and converting real sequences under a Cartesian coordinate system into sequences under polar coordinates; according to the inner product definition, calculating a similar gram matrix corresponding to the sequence as a triangular term of the radio frequency fingerprint; the scaled numerical value is used as a main diagonal to obtain a corresponding diagonal matrix which is used as a recovery item of the radio frequency fingerprint; calculating the sum of the triangle item and the recovery item, and rendering into an image according to the numerical value; and smoothing the image by utilizing a segmentation aggregation approximation method, and taking the smoothed image as a radio frequency fingerprint of the wireless device. The invention solves the problems of lack of time sequence information mining and large resource consumption in the traditional radio frequency fingerprint extraction algorithm, is safe and effective, and can be used as a radio frequency fingerprint extraction method of various wireless devices.
Description
Technical Field
The invention relates to the technical field of information security, in particular to a radio frequency fingerprint extraction method based on time sequence characterization.
Background
The Internet of things is combined with big data and cloud computing, and various industries are deeply remodeled, and meanwhile, more serious challenges are brought to system safety. The openness of wireless networks makes them more vulnerable to attacks than wired networks. Authentication of wireless devices is therefore critical to maintaining system security. Physical layer authentication has become a powerful solution in wireless device access due to low cost and low latency, where radio frequency fingerprinting is one of the most core technologies in the physical layer authentication process. As an inherent property of the device circuitry hardware, radio frequency fingerprints are difficult to forge, just like biometric fingerprints, being unique identifiers of devices. In addition, the radio frequency fingerprint has universality, short-time invariance, independence and robustness, and the advantages lead the radio frequency fingerprint to be widely concerned and researched.
However, most of the existing rf fingerprint extraction schemes consider the collected signals as static data streams with mutually independent data points, and ignore the time sequence relationship of the signals as a time sequence, so that the performance of subsequent identification and authentication is insufficient. In addition, existing rf fingerprint extraction is designed under an ideal data set, i.e., the fingerprint extraction is often performed using a complete preamble. Considering conditions such as incomplete acquisition, signal deficiency and the like which are likely to occur in the acquisition process in a real scene, the practical universality of the method is often insufficient, and the problem of high calculation cost and the like can be caused by fingerprint extraction based on the complete preamble. Therefore, an efficient, lightweight and practical rf fingerprint extraction method is needed.
Disclosure of Invention
The invention aims to: in order to overcome the defects of the existing fingerprint extraction scheme, the invention provides a radio frequency fingerprint extraction method based on time sequence characterization, which is used for solving the problems of lack of time sequence information mining, insufficient practicability and high resource consumption in the existing extraction method.
The technical scheme is as follows: after the signal to be identified is obtained, preprocessing is carried out on the signal to be identified, then one-dimensional data is processed into a two-dimensional image, and finally the image obtained through smoothing operation is used as a radio frequency fingerprint. The radio frequency fingerprint extraction method based on time sequence characterization comprises the following steps:
(1) Collecting and processing output signals of the wireless device;
(2) Encoding the scaled values into cosine of vector included angles, encoding corresponding time stamps into radiuses, and converting real sequences under a Cartesian coordinate system into sequences under polar coordinates;
(3) According to the inner product definition, calculating a similar gram matrix corresponding to the sequence as a triangular term of the radio frequency fingerprint;
(4) The scaled numerical value is used as a main diagonal to obtain a corresponding diagonal matrix which is used as a recovery item of the radio frequency fingerprint;
(5) Calculating the sum of the triangle item and the recovery item, and rendering into an image according to the numerical value;
(6) And smoothing the image by utilizing a segmentation aggregation approximation method, and taking the smoothed image as a radio frequency fingerprint of the wireless device.
Further, the step (1) specifically includes:
(1.1) acquiring an output signal of the wireless device;
(1.2) preprocessing the acquired signals: and performing down-conversion, oversampling, signal detection and interception, energy normalization, estimation and compensation of signal frequency offset and phase offset and I/Q path signal extraction in sequence.
(1.3) performing a min-max normalization on the preprocessed signal to scale the data to the [0,1] interval range. The min-max formula is:
wherein X represents the acquired wireless signal, X= { X 1 ,x 2 ,…,x n }。
Further, the formula of the encoding process in the step (2) is:
wherein t is i Is a time stamp, N is the total number of sampling points of the signal acquired by the signal.
Further, the step (3) specifically includes:
(3.1) defining an inner product calculation formula of any two vectors y and z as:
(3.2) calculating a gram matrix of the preprocessed signals as a triangular term according to the new inner product definition. The formula is:
where I is the unit column vector,is the wireless signal obtained after step (1),/-> Is->Transpose of->
Further, the recovery term in the step (4) specifically has the following formula:
in the method, in the process of the invention, is the wireless signal obtained after step (1),/->
Further, the step (6) specifically includes:
(6.1) setting a window ratio m (0<m is less than or equal to 1), wherein m is the ratio of the window size to the total sequence length. The size of each window is mN;
(6.2) cutting the window into segments of the original sequence in a non-overlapping manner, and calculating an average value for each segment instead of all values within the segment.
(6.3) the smoothed image size obtained isIn->Representing a rounding up operation.
The beneficial effects are that: compared with the prior art, the invention has the remarkable advantages that: the method can extract the radio frequency fingerprint of the equipment by adopting the few preamble information, and excavate the time sequence information of the signal by the time sequence representation of the similar gram matrix, thereby providing an effective and lightweight radio frequency fingerprint for the authentication and identification of the wireless equipment in the actual scene and having high practical value. The invention can be used for greatly improving the identification performance of the wireless equipment.
Drawings
Fig. 1 is a flowchart of an embodiment of a method for extracting a radio frequency fingerprint based on timing characterization according to the present invention.
Detailed Description
The embodiment provides a radio frequency fingerprint extraction method based on time sequence characterization, as shown in fig. 1, comprising the following steps:
(1) An output signal of the wireless device is collected and processed. The method specifically comprises the following steps:
(1.1) collecting an output signal of the wireless device.
When the output signal of the wireless equipment is collected, the output signal is connected with the collected signal through a direct coaxial line and an attenuator, or the signal is collected in a wireless receiving environment with a close range, a visual range and a signal-to-noise ratio higher than a preset value. In this embodiment, 15 ZigBee wireless transmission modules are selected as the target wireless devices, and numbered 1-15. And the USRP equipment is adopted to collect the sight distance transmission signals at a short distance, and the signal to noise ratio of the collected signals is 30dB. In this embodiment, 45 frames are collected for each ZigBee device, and 675 frames are collected. By manually injecting Gaussian white noise, the signal to noise ratios of the signals respectively reach 10dB,15dB,20dB,25dB and 30dB, and the total frame number is expanded to 3375 frames.
(1.2) preprocessing the output signal of each wireless device.
Wherein the preprocessing comprises the following steps: down conversion, oversampling, signal detection and interception, energy normalization, estimation and compensation of signal frequency offset and phase offset, and I/Q signal extraction. The symbol rate of the original ZigBee device is 1Mbps, the signal is directly down-converted to a baseband signal during acquisition, the sampling rate is 10Mbps, the received signal is divided into frames according to the sampling point change, each frame is subjected to energy normalization, and finally the frequency offset and phase offset processing of the signal are performed (the specific method is referred to patent 201510797097.8).
(1.3) selecting an I path signal, carrying out minimum-maximum processing on the I path signal, and scaling data to a range of a [0,1] interval, wherein the formula is as follows:
wherein X represents the preprocessed I-path signal, and X= { X 1 ,x 2 ,…,x n }。
(2) The scaled values are encoded into cosine of the vector angle, the corresponding time stamps are encoded into radius, and the real sequence in the Cartesian coordinate system is converted into the sequence in the polar coordinate system. The formula of the encoding process is:
wherein t is i Is a time stamp, N is the total number of sampling points of the signal acquired by the signal. In this embodiment, the second leading 320 sampling points are taken, i.e., n=320. In a specific application, the total number of sampling points is determined according to the signal acquisition condition.
(3) And (3) calculating a similar gram matrix corresponding to the sequence according to the inner product definition, and taking the similar gram matrix as a triangular term of the radio frequency fingerprint. The method specifically comprises the following steps:
(3.1) defining an inner product calculation formula of any two vectors y and z as:
(3.2) calculating a gram matrix of the preprocessed signals as a triangular term according to the new inner product definition. The formula is:
where I is the unit column vector,is the wireless signal obtained after step (1),/-> Is->Transpose of->
(4) The I path of signals are used as main diagonal lines to obtain corresponding diagonal matrixes, the corresponding diagonal matrixes are used as recovery terms of radio frequency fingerprints, and the formula is as follows:
in the method, in the process of the invention, is the wireless signal obtained after step (1),/->
(5) And calculating the sum of the triangle item and the recovery item, and rendering into an image according to the numerical value. In this embodiment, after this step, the image size obtained for each frame signal is 320×320.
(6) And smoothing the image by utilizing a segmentation aggregation approximation method, and taking the smoothed image as a radio frequency fingerprint of the wireless device. The method specifically comprises the following steps:
(6.1) setting a window ratio m (0<m is less than or equal to 1), wherein m is the ratio of the window size to the total sequence length. The size of each window is mN;
(6.2) cutting the window into segments of the original sequence in a non-overlapping manner, and calculating an average value for each segment instead of all values within the segment.
(6.3) the smoothed image size obtained isIn->Representing a rounding up operation.
In this embodiment, m=0.03125, and thus the size of each window is 10, and the smoothed image size is 32×32. The window ratio is used as a super parameter, and the specific size is determined according to the total number of sampling points and the subsequent classification performance.
After the above steps, the obtained data total set is 3375, according to 7:1: the scale of 2 divides the dataset into a training set, a validation set and a test set. To demonstrate the effectiveness of the present invention, a convolutional neural network was used for high-dimensional feature extraction and classification. The structure of the convolutional neural network is shown in table 1:
TABLE 1
| Network layer | Input dimension | Convolution kernel/step size/zero padding | Pooling step size | Output dimension | Excitation function |
| Conv1 | 400×400×3 | 3×3×32/3/1 | - | 134×134×32 | BN+ReLU |
| Pool1 | 134×134×32 | - | 2 | 67×67×32 | - |
| Conv2 | 32×67×67 | 3×3×64/3/1 | - | 23×23×64 | BN+ReLU |
| Pool2 | 23×23×64 | - | 2 | 11×11×64 | - |
| Conv3 | 11×11×64 | 3×3×64/2/1 | - | 6×6×64 | BN+ReLU |
| Pool3 | 6×6×64 | - | 2 | 3×3×64 | - |
| Flatten | 3×3×64 | - | - | 576 | - |
| FC1 | 576 | - | - | 64 | Dropout+ReLU |
| FC2 | 64 | - | - | 15 | Softmax |
The method can effectively improve the accuracy of identifying and classifying the low-power-consumption equipment. As shown in table 2, compared with the original signal after pretreatment, the classification accuracy is obviously improved after the time sequence characterization is performed by using the method.
TABLE 2
| Signal-to-noise ratio (dB) | 10 | 15 | 20 | 25 | 30 |
| Original signal | 62.9629 | 71.8518 | 75.5556 | 77.0370 | 80 |
| The method | 92.5925 | 96.2962 | 97.7778 | 99.2593 | 99.2593 |
The above disclosure is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (3)
1. The radio frequency fingerprint extraction method based on the time sequence characterization is characterized by comprising the following steps of:
(1) Collecting and processing output signals of the wireless device;
(2) Encoding the scaled values into cosine of vector included angles, encoding corresponding time stamps into radiuses, and converting real sequences under a Cartesian coordinate system into sequences under polar coordinates;
(3) According to the inner product definition, calculating a similar gram matrix corresponding to the sequence as a triangular term of the radio frequency fingerprint;
(4) The scaled numerical value is used as a main diagonal to obtain a corresponding diagonal matrix which is used as a recovery item of the radio frequency fingerprint;
(5) Calculating the sum of the triangle item and the recovery item, and rendering into an image according to the numerical value;
(6) Smoothing the image by utilizing a segmentation aggregation approximation method, and taking the smoothed image as a radio frequency fingerprint of the wireless equipment;
the step (1) specifically comprises the following steps:
(1.1) acquiring an output signal of the wireless device;
(1.2) preprocessing the acquired signals: sequentially performing down-conversion, oversampling, signal detection and interception, energy normalization, signal frequency offset and phase offset estimation and compensation and I/Q path signal extraction;
(1.3) performing a min-max normalization on the preprocessed signal, scaling the data to a [0,1] interval range, wherein a min-max formula is:
wherein X represents the acquired wireless signal, X= { X 1 ,x 2 ,…,x n }；
The coding process of the step (2) is as follows:
wherein t is i The time stamp is used, and N is the total number of sampling points of the signal acquired by the signal;
the recovery term in the step (4) specifically comprises the following formula:
in the method, in the process of the invention, is the wireless signal obtained after step (1),/->
2. The method for extracting the radio frequency fingerprint based on the time sequence representation according to claim 1, wherein the method comprises the following steps of: the step (3) specifically comprises:
(3.1) defining an inner product calculation formula of any two vectors y and z as:
(3.2) calculating a gram matrix of the preprocessed signals according to the new inner product definition, wherein the gram matrix is used as a triangular term, and the formula is as follows:
where I is the unit column vector,is the wireless signal obtained after step (1),/-> Is->Transpose of->
3. The method for extracting the radio frequency fingerprint based on the time sequence representation according to claim 1, wherein the method comprises the following steps of: in the step (6), smoothing is performed on the image by using a piecewise aggregation approximation method, which specifically includes:
(6.1) setting a window ratio m,0<m is less than or equal to 1, wherein m is the ratio of the window size to the total sequence length, and the size of each window is mN;
(6.2) cutting the window into segments of the original sequence in a non-overlapping manner, and calculating an average value of each segment to replace all values in the segment;
(6.3) the smoothed image size obtained isIn->Representing a rounding up operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210464767.4A CN114866311B (en) | 2022-04-29 | 2022-04-29 | Radio frequency fingerprint extraction method based on time sequence characterization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210464767.4A CN114866311B (en) | 2022-04-29 | 2022-04-29 | Radio frequency fingerprint extraction method based on time sequence characterization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114866311A CN114866311A (en) | 2022-08-05 |
| CN114866311B true CN114866311B (en) | 2024-03-22 |
Family
ID=82636125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210464767.4A Active CN114866311B (en) | 2022-04-29 | 2022-04-29 | Radio frequency fingerprint extraction method based on time sequence characterization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114866311B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105357014A (en) * | 2015-11-25 | 2016-02-24 | 东南大学 | Wireless equipment radio frequency fingerprint feature extraction method based on differential constellation track diagram |
| CN105631472A (en) * | 2015-12-24 | 2016-06-01 | 东南大学 | Wireless device identity identification method based on constellation locus diagram |
| CN110380989A (en) * | 2019-07-26 | 2019-10-25 | 东南大学 | The polytypic internet of things equipment recognition methods of network flow fingerprint characteristic two-stage |
| CN114239657A (en) * | 2021-12-18 | 2022-03-25 | 中国科学技术大学 | Time sequence signal identification method based on complex value interference neural network |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10764285B2 (en) * | 2018-07-25 | 2020-09-01 | Honda Motor Co., Ltd. | Method and system for encryption using a radio frequency fingerprint |
-
2022
- 2022-04-29 CN CN202210464767.4A patent/CN114866311B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105357014A (en) * | 2015-11-25 | 2016-02-24 | 东南大学 | Wireless equipment radio frequency fingerprint feature extraction method based on differential constellation track diagram |
| CN105631472A (en) * | 2015-12-24 | 2016-06-01 | 东南大学 | Wireless device identity identification method based on constellation locus diagram |
| CN110380989A (en) * | 2019-07-26 | 2019-10-25 | 东南大学 | The polytypic internet of things equipment recognition methods of network flow fingerprint characteristic two-stage |
| CN114239657A (en) * | 2021-12-18 | 2022-03-25 | 中国科学技术大学 | Time sequence signal identification method based on complex value interference neural network |
Non-Patent Citations (3)
| Title |
|---|
| 一种基于射频指纹的通信个体识别方法;黄少驰;朱晓蕾;航天电子对抗(01);全文 * |
| 基于射频信号特征的Airmax设备指纹提取方法;季澈;彭林宁;胡爱群;王栋;数据采集与处理(02);全文 * |
| 多径传输环境下的射频指纹估计方法;王栋;胡爱群;王炎;密码学报(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114866311A (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Babu et al. | Statistical features based optimized technique for copy move forgery detection | |
| CN109495214B (en) | Channel coding type identification method based on one-dimensional inclusion structure | |
| CN110197209B (en) | Radiation source identification method based on multi-feature fusion | |
| CN102541954B (en) | Method and system for searching trademarks | |
| CN113014524B (en) | Digital signal modulation identification method based on deep learning | |
| CN107392123B (en) | Radio frequency fingerprint feature extraction and identification method based on coherent accumulation noise elimination | |
| CN111339924B (en) | Polarized SAR image classification method based on superpixel and full convolution network | |
| CN111027614B (en) | Noise enhanced radio frequency fingerprint identification method and device | |
| CN111624570A (en) | Radar target identification method based on two-dimensional convolutional neural network | |
| CN104537381A (en) | Blurred image identification method based on blurred invariant feature | |
| Wang et al. | A cooperative spectrum sensing method based on signal decomposition and K-medoids algorithm | |
| CN114866311B (en) | Radio frequency fingerprint extraction method based on time sequence characterization | |
| CN109598216B (en) | Convolution-based radio frequency fingerprint feature extraction method | |
| CN113378643B (en) | Signal countermeasure sample detection method based on random transformation and wavelet reconstruction | |
| CN107341519B (en) | Support vector machine identification optimization method based on multi-resolution analysis | |
| CN114519372B (en) | One-dimensional range profile target recognition method based on support vector machine | |
| CN111404852B (en) | Modulation mode identification method based on amplitude and spectral amplitude characteristics | |
| Yang et al. | Wireless communication jamming recognition based on lightweight residual network | |
| Huang et al. | Modulation identification method based on time-frequency analysis and support vector machine | |
| CN114584441A (en) | Digital signal modulation identification method based on deep learning | |
| CN107872413B (en) | Intelligent modulation identification method based on compressed sensing high-order cumulant | |
| CN101937511B (en) | Rapid image matching method based on stochastic parallel optimization algorithm | |
| Han | Fast fractal image compression using fuzzy classification | |
| CN108596194A (en) | A kind of image encoding method of the local binary patterns of Gauss weighting | |
| Zhou et al. | Application of Deep Learning in Signal Modulation Recognition System for Wireless Communication |
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 |