CN114048788A - Classification-wavelet-superposition-signal-based equipment fingerprint identification method - Google Patents
Classification-wavelet-superposition-signal-based equipment fingerprint identification method Download PDFInfo
- Publication number
- CN114048788A CN114048788A CN202210029581.6A CN202210029581A CN114048788A CN 114048788 A CN114048788 A CN 114048788A CN 202210029581 A CN202210029581 A CN 202210029581A CN 114048788 A CN114048788 A CN 114048788A
- Authority
- CN
- China
- Prior art keywords
- signal
- waveforms
- equipment
- fingerprint
- superposition
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000009467 reduction Effects 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 239000000654 additive Substances 0.000 claims description 5
- 230000000996 additive effect Effects 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 3
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000005316 response function Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000005670 electromagnetic radiation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
-
- 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
- G06F2218/12—Classification; Matching
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)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a device fingerprint identification method based on classification wavelet superposition signal noise reduction, which can perform noise reduction processing under the condition of not damaging a device fingerprint carried in a signal and then effectively extract device fingerprint characteristics from the noise-reduced signal, thereby realizing accurate device fingerprint identification. The method comprises the following steps: after receiving the signal with low signal-to-noise ratio, carrying out wave crest and trough detection on the signal waveform, and calculating all wave crest and trough positions in the signal. Then, the signal is divided into a series of sub-waveforms according to the arrangement sequence of the peaks and the valleys, and each sub-waveform is a signal segment containing different numbers of continuous peaks/valleys. And then, carrying out superposition denoising on the sub-waveforms of the same type. And finally, forming a new denoised signal by all superposed sub-waveforms, wherein the new denoised signal is used for equipment fingerprint feature extraction and equipment identity identification. The invention can effectively extract the physical layer fingerprint characteristics of the equipment under the condition of low signal-to-noise ratio, and effectively solves the problem of low signal-to-noise ratio which must be faced by the equipment identification method based on the equipment fingerprint in the practical application.
Description
Technical Field
The invention relates to the fields of intelligent equipment, Internet of things, information security and the like, in particular to a device fingerprint identification method based on classification wavelet superposition signal noise reduction.
Background
The electromagnetic radiation source inevitably introduces physical features into the device when emitting a signal. This feature is mainly caused by the power difference of the hardware elements inside the device. The physical characteristics of each device are also unique, since each electronic component has a unique power difference. This physical feature has the property of being unique and difficult to clone, just like a "fingerprint" of a device, and is therefore also referred to as a physical fingerprint feature or a radio frequency fingerprint feature. With the intensive research on the technology related to the physical fingerprint of the device, the physical fingerprint features are generally considered as unique features of the wireless device, so that the physical fingerprint features can be used for identity identification and authentication of the electromagnetic radiation source. Particularly, the device identification technology based on the physical fingerprint characteristics can accurately distinguish wireless devices even adopting the same frequency, bandwidth and modulation mode, and has very good practical value. Thus, an authentication system based on physical fingerprint features can authenticate the accessing own wireless device at the physical signal layer. Compared with the traditional equipment identity authentication method, the physical layer fingerprint technology can effectively resist forging, tampering and other attacks, and has the characteristic of physical unclonable.
However, most of the methods disclosed in the prior art for extracting physical fingerprint features of devices mainly work in high signal-to-noise ratio situations. The methods can achieve better equipment identification effect under the experimental condition of high signal-to-noise ratio, but the identification effect is poor under the condition of low signal-to-noise ratio. However, the low signal-to-noise ratio is often the case in practical communications. Therefore, the existing device physical feature extraction method cannot completely meet the requirements of practical application. An apparatus fingerprint identification method based on classification wavelet superposition signal noise reduction is urgently needed.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problems in the prior art, realize proper noise reduction processing on wireless equipment signals which normally communicate under the condition of low signal-to-noise ratio and effectively extract the physical fingerprint characteristics of the wireless equipment in the low signal-to-noise ratio signals, the invention provides a device fingerprint identification method based on classification wavelet superposition signal noise reduction.
The technical scheme is as follows: the invention relates to a device fingerprint identification method based on classification wavelet superposition signal noise reduction, which comprises the following steps:
the method comprises the following steps: device fingerprint feature adoption functionIndicating, signals to be identifiedAfter being transmitted by the transmitter, the equipment fingerprint carrying the transmitter obtains a transmission signal and records the transmission signal as;
Step two: the transmitted signal is received by the receiver via propagation over the wireless link, and the received signal is denoted as:
whereinIs representative of the multi-path channel response function,represents a mean of 0 and a variance ofAn additive white gaussian noise term;
step three: when the training data and the test data of the equipment are collected in a similar environment, the multipath channel responses of the training data and the test data are considered to be similar, and the multipath channel change of the received signal is small, so that the influence of the multipath channel on the received signal can be ignored, and the received signal can be simplified as follows:
step four: all signals are formed by connecting a certain number of unit waveforms, wherein positive unit waveforms in the signals form wave crests, negative unit waveforms in the signals form wave troughs, and the unit waveforms in the signals are defined as;
Step five: respectively obtaining signals by using algorithmPeak and trough values inAnd their positions:
Step seven: arranging information according to positionTo pairAlso reordering, and normalizing the peak and valley values to 1 and-1 respectively to obtain correctly arranged peak and valley information;
Step eight: according to continuous positive/negative unit waveforms in signal segmentThe number of sub-waveforms into which the signal is divided, as follows:
wherein,andrespectively representing a wave peak type sub-waveform and a wave trough type sub-waveform;representing the number of corresponding sub-waveforms;representing the number of unit waveforms included in each seed waveform;
step nine: superimposing sub-waveforms of the same type toFor example, the following steps are carried out:
Step ten: the superposed signalsAndcan be straightThe device fingerprint characteristics received as the received signal are recorded as:
step eleven: and identifying the identity of the equipment through the extracted fingerprint characteristics of the equipment.
Furthermore, only the scene that the same receiver identifies a plurality of transmitters is considered in the step two, namely the distortion of the fingerprint of the receiver on each received signal is the same, so that the influence of the fingerprint of the receiver on the fingerprint identification of the device can be ignored in the process of modeling the fingerprint system.
Further, in step three, assuming that the received signal power is 1, the received signal is receivedThe raw signal-to-noise ratio of (c) is:
further, in step eight, the definition of the same waveform segment includes two parts: (1) the waveforms of the signal segments are the same; (2) the previous unit waveform of the signal segment is the same.
Further, in the ninth step, the equivalent SNR of the signal after the sub-waveform classification superposition is:
it can be seen thatThe equivalent SNR after the superposition of the sub-waveforms is the original SNR of the received signalIs/are as followsHowever, the wavelet signal length is short, so the noise signal is not strictly 0-mean additive white gaussian noise, and the actual signal-to-noise ratio of the superimposed signal is lower than the theoretical value.
Further, the device fingerprint extraction method in the step ten includes one or more of a physical quantity extraction method, machine learning, deep learning, and a constellation method.
Has the advantages that: the invention provides a device fingerprint identification method based on classification wavelet superposition signal noise reduction, which is more suitable for signals with low signal-to-noise ratio compared with the prior art. After the receiver receives the signal with low signal-to-noise ratio, the noise reduction processing can be carried out under the condition of not damaging the physical fingerprint of the equipment, and then the physical fingerprint characteristic of the equipment is extracted from the signal after the noise reduction. The method can effectively extract the physical layer fingerprint characteristics of the equipment under the condition of low signal-to-noise ratio, and effectively solves the problem of low signal-to-noise ratio which is necessary to be faced by the equipment physical fingerprint-based equipment identification method in practical application.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a diagram illustrating the detection results of peaks and troughs of received signals under different SNR according to the present invention;
FIG. 3 is a schematic diagram of wavelet classification of ZigBee preamble signal of the present invention;
FIG. 4 is a comparison of the signal waveforms of the original received signal and the classification wavelets after superposition according to the present invention;
fig. 5 is a schematic diagram illustrating the result of improving the device identification rate at a low signal-to-noise ratio by using the method of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplification of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The present invention will be described in further detail below with reference to specific embodiments and with reference to the attached drawings.
According to the method, after a receiver receives a signal with a low signal-to-noise ratio, noise reduction processing can be performed without destroying the fingerprint of the equipment, and the physical fingerprint feature of the equipment is extracted from the noise-reduced signal and used for identity authentication.
The flow of the method is shown in figure 1:
the method comprises the following steps: device fingerprinting is a comprehensive characterization of hardware distortion within the device, used herein as a functionAnd (4) showing. Signal to be recognizedAfter passing through the ZigBee transmitter, carrying the device fingerprint of the transmitter to obtain a transmission signal which is recorded as. In this embodiment, the transmitters to be identified are 54 CC2530 ZigBee modules, and the effective signal segment for device fingerprint identification is a preamble in a ZigBee communication signal.
Step two: the transmitted signal is received by the receiver via propagation over the wireless link, and the received signal is denoted as:
whereinIs representative of the multi-path channel response function,represents a mean of 0 and a variance ofAn additive white gaussian noise term. In this embodiment, the receiver is a USRP N210 device.
Step three: when the device training data and the test data are collected under similar environment, it can be considered that their multipath channel responses are similar and the multipath channel variation of the received signal is small. Therefore, the influence of the multipath channel on the received signal can be ignored, and the received signal can be simplified as follows:
step four: all signals are formed by connecting a certain number of unit waveforms (such as half sine waves), wherein positive unit waveforms form wave crests, and negative unit waveforms form wave troughs. Defining a unit waveform in a signal as。
Step five: using various sophisticated algorithms, e.g. in Matlab function librariesAlgorithm, can obtain signals respectivelyPeak and trough values inAnd their positions:
Wherein the superscript isAndrepresenting the peaks and valleys, respectively. Fig. 2 shows the detection results of the peak and valley positions of the received signal under different signal-to-noise ratios (SNRs). It can be seen that the peak-to-valley detection is very accurate when the SNR is high (30 dB and 20 dB). But when SNR = 10dB, as shown by the black circle in fig. 2, one detection error occurs. When the SNR further drops to 0dB, two detection errors occur. When the detection of the peak and trough positions is wrong, the subsequent signal wavelet segmentation errors can be caused. That is, in the wavelet superposition stage, different wavelets are superposed. Because the device fingerprints of different wavelets have differences, the enhancement effect of the device fingerprints after superposition is lower than the effect of correct wavelet superposition. That is, the effect of the method decreases as the SNR decreases to some extent.
Step seven: arranging information according to positionTo pairAlso reordering, and normalizing the peak and valley values to 1 and-1 respectively to obtain correctly arranged peak and valley information。
Step eight: according to continuous positive/negative unit waveforms in signal segmentThe number of sub-waveforms into which the signal is divided. The following were used:
wherein,andrespectively representing a wave peak type sub-waveform and a wave trough type sub-waveform;representing the number of corresponding sub-waveforms;representing the number of unit waveforms contained in each seed waveform. In this embodiment, there are 8 different wavelets in the preamble segment of the ZigBee signal (as shown in fig. 3). Wherein, only the wave crest Type wavelets Type1 and Type4, and the wave trough Type wavelets Type1, Type2 and Type3 are in the I path signal. And the Q-path signal contains all types of wavelets.
Step nine: will be provided withSub-waveforms of the same type are superimposed toFor example, the following steps are carried out:
whereinRepresenting the superimposed noise term, as obtained。 The equivalent SNR after the superposition of the sub-waveforms is the original signal-to-noise ratio of the received signalIs/are as followsAnd (4) doubling. In this embodiment, waveforms of the wavelet-superimposed signal and the original noise signal are compared. It is apparent from the graph that the received signal waveforms are very different at SNRs of 30dB and 10 dB. But the difference in signal waveform is significantly reduced after wavelet superposition. The overlap ratio of the superimposed waveform at 10dB and the waveform at 30dB is high. Therefore, the wavelet superposition method can effectively reduce signal noise.
Step ten: in the present embodiment, the superposed signals are usedAnddirectly used as the input signal of the convolutional neural network, thereby carrying out the extraction and identification of the device fingerprint.
FIG. 5 shows use and non-useThe device fingerprint identification result of the ZigBee module using the method of the invention is compared with a graph. Where the baseline represents the result without using the method, the CSS algorithm refers to the present invention which proposes classification-based waveform stacking signal noise reduction. As shown in the figure, whenIn time, the recognition rate of the CSS algorithm is improved by about 2% to 11%. When in useAnd meanwhile, the identification accuracy is improved by 38.32%.
The invention provides a device fingerprint identification method based on classification wavelet superposition signal noise reduction, which is more suitable for signals with low signal-to-noise ratio compared with the prior art. After the receiver receives the signal with low signal-to-noise ratio, the noise reduction processing can be carried out under the condition of not damaging the physical fingerprint of the equipment, and then the physical fingerprint characteristic of the equipment is extracted from the signal after the noise reduction. The method can effectively extract the physical layer fingerprint characteristics of the equipment under the condition of low signal-to-noise ratio, and effectively solves the problem of low signal-to-noise ratio which is necessary to be faced by the equipment physical fingerprint-based equipment identification method in practical application.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. A device fingerprint identification method based on classification wavelet superposition signal noise reduction is characterized in that: the method comprises the following steps:
the method comprises the following steps: device fingerprint feature extractionUsing functionsIndicating, signals to be identifiedAfter being transmitted by the transmitter, the equipment fingerprint carrying the transmitter obtains a transmission signal and records the transmission signal as;
Step two: the transmitted signal is received by the receiver via propagation over the wireless link, and the received signal is denoted as:
whereinIs representative of the multi-path channel response function,represents a mean of 0 and a variance ofAn additive white gaussian noise term;
step three: when the training data and the test data of the equipment are collected in a similar environment, the multipath channel responses of the training data and the test data are considered to be similar, and the multipath channel change of the received signal is small, so that the influence of the multipath channel on the received signal can be ignored, and the received signal can be simplified as follows:
step four: all signals being formed by a certain number of unit wavesThe positive unit waveform in the signal forms a wave crest, the negative unit waveform in the signal forms a wave trough, and the unit waveform in the signal is defined as;
Step five: respectively obtaining signals by using algorithmPeak and trough values inAnd their positions:
Step seven: arranging information according to positionTo pairAre also reordered, andnormalizing the values of the wave crests and the wave troughs to 1 and-1 respectively to obtain correctly arranged wave crest and wave trough information;
Step eight: according to continuous positive/negative unit waveforms in signal segmentThe number of sub-waveforms into which the signal is divided, as follows:
wherein,andrespectively representing a wave peak type sub-waveform and a wave trough type sub-waveform;representing the number of corresponding sub-waveforms;representing the number of unit waveforms included in each seed waveform;
step nine: superimposing sub-waveforms of the same type toFor example, the following steps are carried out:
Step ten: the superposed signalsAndthe device fingerprint characteristics that can be directly used as the received signal are recorded as:
step eleven: and identifying the identity of the equipment through the extracted fingerprint characteristics of the equipment.
2. The method of claim 1, wherein the device fingerprint identification method based on classification wavelet superposition signal noise reduction is characterized in that: in the second step, only the scene that the same receiver identifies a plurality of transmitters is considered, namely the distortion of the fingerprint of the receiver on each received signal is the same, so that the influence of the fingerprint of the receiver on the fingerprint identification of the equipment can be ignored in the process of modeling the fingerprint system.
4. the method of claim 1, wherein the device fingerprint identification method based on classification wavelet superposition signal noise reduction is characterized in that: in step eight, the definition of the same waveform segment includes two parts: (1) the waveforms of the signal segments are the same; (2) the previous unit waveform of the signal segment is the same.
5. The method of claim 1, wherein the device fingerprint identification method based on classification wavelet superposition signal noise reduction is characterized in that: in the ninth step, the equivalent SNR of the signal after the wavelet classification superposition is as follows:
it can be seen thatThe equivalent SNR after the superposition of the sub-waveforms is the original SNR of the received signalIs/are as followsHowever, the wavelet signal length is short, so the noise signal is not strictly 0-mean additive white gaussian noise, and the actual signal-to-noise ratio of the superimposed signal is lower than the theoretical value.
6. The method of claim 1, wherein the device fingerprint identification method based on classification wavelet superposition signal noise reduction is characterized in that: the device fingerprint extraction method in the step ten comprises one or more methods of a physical quantity extraction method, machine learning, deep learning and a constellation diagram method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210029581.6A CN114048788B (en) | 2022-01-12 | 2022-01-12 | Classification-wavelet-superposition-signal-based equipment fingerprint identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210029581.6A CN114048788B (en) | 2022-01-12 | 2022-01-12 | Classification-wavelet-superposition-signal-based equipment fingerprint identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114048788A true CN114048788A (en) | 2022-02-15 |
CN114048788B CN114048788B (en) | 2022-04-22 |
Family
ID=80196298
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210029581.6A Active CN114048788B (en) | 2022-01-12 | 2022-01-12 | Classification-wavelet-superposition-signal-based equipment fingerprint identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114048788B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116017447A (en) * | 2022-12-15 | 2023-04-25 | 南京莱斯网信技术研究院有限公司 | Physical feature-based identity recognition method for Internet of vehicles communication equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108809355A (en) * | 2018-07-04 | 2018-11-13 | 南京东科优信网络安全技术研究院有限公司 | A method of in low signal-to-noise ratio extraction equipment physical fingerprint feature |
CN110349593A (en) * | 2019-07-25 | 2019-10-18 | 江门市华恩电子研究院有限公司 | The method and system of semanteme based on waveform Time-Frequency Analysis and the dual identification of vocal print |
CN110346763A (en) * | 2019-07-17 | 2019-10-18 | 东南大学 | A kind of antinoise radio-frequency fingerprint recognition methods for radar LFM signal |
CN113052013A (en) * | 2021-03-08 | 2021-06-29 | 中国人民解放军63891部队 | Radio frequency fingerprint identification method for radio station modulation signals |
-
2022
- 2022-01-12 CN CN202210029581.6A patent/CN114048788B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108809355A (en) * | 2018-07-04 | 2018-11-13 | 南京东科优信网络安全技术研究院有限公司 | A method of in low signal-to-noise ratio extraction equipment physical fingerprint feature |
CN110346763A (en) * | 2019-07-17 | 2019-10-18 | 东南大学 | A kind of antinoise radio-frequency fingerprint recognition methods for radar LFM signal |
CN110349593A (en) * | 2019-07-25 | 2019-10-18 | 江门市华恩电子研究院有限公司 | The method and system of semanteme based on waveform Time-Frequency Analysis and the dual identification of vocal print |
CN113052013A (en) * | 2021-03-08 | 2021-06-29 | 中国人民解放军63891部队 | Radio frequency fingerprint identification method for radio station modulation signals |
Non-Patent Citations (2)
Title |
---|
林讳等: "基于小波降噪的短波通信信号协议识别特征提取算法", 《信息工程大学学报》 * |
陈建林: "基于波形分析的自动声纹识别技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116017447A (en) * | 2022-12-15 | 2023-04-25 | 南京莱斯网信技术研究院有限公司 | Physical feature-based identity recognition method for Internet of vehicles communication equipment |
Also Published As
Publication number | Publication date |
---|---|
CN114048788B (en) | 2022-04-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110855591B (en) | QAM and PSK signal intra-class modulation classification method based on convolutional neural network structure | |
Wang et al. | A convolutional neural network-based RF fingerprinting identification scheme for mobile phones | |
CN111444805B (en) | Improved multi-scale wavelet entropy digital signal modulation identification method | |
CN114422311B (en) | Signal modulation recognition method and system combining deep neural network and expert priori features | |
Jeong et al. | Spectrogram-based automatic modulation recognition using convolutional neural network | |
CN114048788B (en) | Classification-wavelet-superposition-signal-based equipment fingerprint identification method | |
CN108090462A (en) | A kind of Emitter Fingerprint feature extracting method based on box counting dimension | |
CN113219415A (en) | Interference source individual identification method based on envelope fingerprint characteristics | |
He et al. | Specific emitter identification via sparse Bayesian learning versus model-agnostic meta-learning | |
CN111027614A (en) | Noise-enhanced radio frequency fingerprint identification method and device | |
Haji Bagheri Fard et al. | Rogue device discrimination in ZigBee networks using wavelet transform and autoencoders | |
CN113343868A (en) | Radiation source individual identification method and device, terminal and storage medium | |
Hazza et al. | Robustness of digitally modulated signal features against variation in HF noise model | |
CN113271273B (en) | Modulation identification method based on wiener filtering preprocessing | |
CN116132991A (en) | Radio frequency fingerprint authentication method, device and storage medium of RKE system | |
Hazra et al. | PLIO: physical layer identification using one-shot learning | |
CN115809426A (en) | Radiation source individual identification method and system | |
CN114050840A (en) | Equipment fingerprint identification method based on unit waveform cross-correlation signal noise reduction | |
CN113347175B (en) | Method and system for fingerprint feature extraction and equipment identity identification of optical communication equipment | |
CN111814703B (en) | HB-based signal joint feature extraction method under non-reconstruction condition | |
CN112996001A (en) | Physical layer secure communication method based on radio frequency fingerprint image scrambling | |
Zheng et al. | Deep learning for cooperative radio signal classification | |
Wen et al. | RF transmitter identification and classification based on deep residual shrinkage network | |
CN115622849B (en) | Intelligent deceptive attack prevention method based on 5G signal MCS blind identification | |
CN114595711B (en) | Radio frequency tag authentication method based on direction sensitivity characteristics |
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 |