CN112134634B - Random forest algorithm-based spectrum sensing method, system and medium - Google Patents
Random forest algorithm-based spectrum sensing method, system and medium Download PDFInfo
- Publication number
- CN112134634B CN112134634B CN202010930938.9A CN202010930938A CN112134634B CN 112134634 B CN112134634 B CN 112134634B CN 202010930938 A CN202010930938 A CN 202010930938A CN 112134634 B CN112134634 B CN 112134634B
- Authority
- CN
- China
- Prior art keywords
- random forest
- signal
- sub
- sample set
- samples
- 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
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 36
- 238000001228 spectrum Methods 0.000 title claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000003066 decision tree Methods 0.000 claims abstract description 27
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 3
- 238000010276 construction Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 5
- 238000009825 accumulation Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 2
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000001149 cognitive effect Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/382—Monitoring; Testing of propagation channels for resource allocation, admission control or handover
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
-
- 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
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention provides a spectrum sensing method, a system and a medium based on a random forest algorithm, comprising the following steps: step 1: receiving signals through an antenna, and converting a signal training data set into a characteristic sample set according to a high-order cumulant calculation formula; step 2: constructing a decision tree, and screening the characteristic sample set to form a sub-sample set and a sub-feature set; and step 3: calculating the average value of each feature in the sub-sample set; and 4, step 4: calculating the information gain rate according to the characteristics and the average value, and taking the characteristics with the maximum information gain rate as split nodes; and 5: dividing a sub-sample set according to the split nodes and constructing a decision tree; step 6: constructing a random forest according to the decision tree; and 7: and testing the random forest by using the sample set to be tested to obtain the modulation type of the test sample signal. The algorithm of the invention trains the signal classifier in an off-line mode and integrates the signal classifier into a radio frequency front-end module of the cognitive radio system, thereby reducing the time cost of the radio system.
Description
Technical Field
The invention relates to the technical field of spectrum sensing, in particular to a spectrum sensing method, a spectrum sensing system and a spectrum sensing medium based on a random forest algorithm.
Background
Decision tree: the decision tree is a decision analysis method which is used for solving the probability that the expected value of the net present value is greater than or equal to zero by forming the decision tree on the basis of the known occurrence probability of various conditions, evaluating the risk of the project and judging the feasibility of the project, and is a graphical method for intuitively applying probability analysis. Decision trees are a very common classification method. It is a supervised learning, which is to say that given a stack of samples, each sample having a set of attributes and a class, which are determined in advance, a classifier is obtained by learning, which classifier is able to give the correct classification to the newly emerging object.
Random forest: the random forest algorithm is an integrated machine learning algorithm that integrates a plurality of weak classifiers (decision trees). When a regression problem is processed, the random forest fuses the output results of a plurality of decision trees, and the average number is taken as the output result of the algorithm; when the classification problem is processed, a voting mechanism is adopted, and the result of the random forest algorithm is the category with the largest number of votes in the output results of the decision trees. In this way, the random forest algorithm overcomes the over-fitting problem of the decision tree, and greatly improves the judgment accuracy
High order cumulant: the higher order accumulation amount refers to an accumulation amount of an order greater than the second order. Its spectrum, i.e. the spectrum of higher order cumulants, refers to the multidimensional fourier transform of the corresponding higher order cumulants. The higher-order cumulant can suppress not only the influence of gaussian noise but also the influence of symmetrically distributed noise automatically.
Software radio: is a radio broadcast communication technology that is based on software defined wireless communication protocols rather than being implemented by hard-wiring. The frequency bands, air interface protocols and functions may be upgraded by software downloads and updates without complete hardware replacement.
Cognitive radio: compared with the software defined radio, the software defined radio has intelligent functions which are not provided by the software defined radio, such as: sensing information from the environment through artificial intelligence techniques, dynamically using spectrum, changing the transmission power of the wireless communication system in real time, etc.
And (3) authorizing a frequency band: the country has regulation on radio frequency, the authorized frequency band is generally used by important departments such as military, aviation and the like, and generally, the authorized frequency band cannot be used by people, if the authorized frequency band is used privately, certain trouble or loss can be brought to aviation and military, and legal responsibility is seriously taken.
A main user: in a cognitive radio system, users entitled to use a licensed frequency band are provided.
Spectrum holes: the part of the licensed band that is temporarily unused by the primary user.
The existing research mainly focuses on detecting the existence of a main user in an authorized frequency band and searching for a frequency spectrum hole, so that the efficient utilization of frequency spectrum resources is realized. However, with the progress of software radio, it is not possible to meet the diversified development requirements in the communication field by simply sensing the presence or absence of a primary user, and it is necessary to sense more electromagnetic information, such as signal parameters of a received signal or spatial electromagnetic environment parameters. The invention solves the problem of how to detect the modulation type of the received signal in real time.
Patent document CN102611509A (application number: 201110021713.2) discloses a spectrum sensing method, a spectrum sensing device, and a database, wherein the spectrum sensing method includes: sending a frequency spectrum sensing request message to a database so that the database can acquire target sensing frequency point information and a corresponding target sensing software identifier, receiving a frequency spectrum sensing response message from the database, acquiring target sensing software corresponding to the target sensing software identifier, operating the target sensing software, and performing frequency spectrum sensing on the target sensing frequency point.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a spectrum sensing method, a spectrum sensing system and a spectrum sensing medium based on a random forest algorithm.
The spectrum sensing method based on the random forest algorithm provided by the invention comprises the following steps:
step 1: receiving signals through an antenna, and converting a signal training data set into a characteristic sample set according to a high-order cumulant calculation formula;
step 2: constructing a decision tree, and screening the characteristic sample set to form a sub-sample set and a sub-feature set;
and step 3: calculating the average value of each feature in the sub-sample set;
and 4, step 4: calculating an information gain rate according to each feature and the average value in the sub-feature set, and taking the feature with the largest information gain rate as a split node;
and 5: dividing the sub-sample set according to the split nodes to complete the construction of the decision tree;
step 6: constructing a random forest according to the decision tree for sensing subsequent received signals;
and 7: and testing the random forest by using the sample set to be tested to obtain the modulation type of the test sample signal.
Preferably, the higher order cumulant calculation formula is:
C20＝cum(s[n],s[n])＝M20
C21＝cum(s[n],s*[n])＝M21
C41＝cum(s[n],s[n],s[n],s*[n])＝M41-3M20M21
wherein C is20Representing a second order cumulative amount of the received signal; m20Representing second moments of the received signal; cum (x, x) denotes the union of the received signalsAn accumulation function; s [ n ]]Indicating a main user signal; n represents the number of sampling points of the main user signal; s*[n]Is s [ n ]]Conjugated forms of (a);
the characteristics of any received signal are represented as:
xia feature matrix representing the ith received signal; i denotes an ith received signal; n represents the number of received signal samples.
Preferably, the step 2 comprises: randomly extracting N times from N samples in a replacement manner, randomly extracting M times from M characteristics in a replacement manner, and removing repeated samples and repeated characteristics to form a sub-sample set and a sub-characteristic set.
Preferably, the step 5 comprises: if the divided sample types belong to the same class, splitting the node into leaf nodes; and if the classified samples are not pure, repeating the step 3 and the step 4 until the samples cannot be classified, and completing the construction of the decision tree.
Preferably, the step 6 includes: judging whether the number of the decision trees reaches a preset tree, if not, repeatedly executing the steps 2 to 5; and if the number reaches the set number, finishing the random forest construction.
Preferably, the modulation type of the test sample signal obtained through the test is compared with the actual modulation type of the test sample signal to obtain the algorithm accuracy of the random forest, and parameters of the decision forest, including the number of decision trees, are adjusted according to the accuracy, so that the algorithm accuracy meets the preset requirement.
The spectrum sensing system based on the random forest algorithm provided by the invention comprises:
an off-line training module: recording data samples of historical received signals, filtering, amplifying and moving down a frequency spectrum, converting the data samples of the received signals into baseband data samples, calculating high-order cumulant of the data to obtain characteristic samples for machine learning training, and training and learning by using a random forest algorithm to obtain a signal classifier;
an online identification module: and after receiving the signals, judging the signal types according to the signal classifier, and outputting the results for signal processing.
According to the present invention, a computer-readable storage medium is provided, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method as described above.
Compared with the prior art, the invention has the following beneficial effects:
1. the algorithm can train a signal classifier in an off-line mode and integrate the signal classifier into a radio frequency front-end module of a cognitive radio system, so that the time cost of the radio system is reduced;
2. through simulation experiments and analysis, the invention can find that the provided algorithm can still more accurately realize spectrum sensing under the condition of low signal-to-noise ratio.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
fig. 1 is a diagram of a perceptual system model.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
Example (b):
the invention researches a spectrum sensing algorithm based on a random forest, which utilizes the characteristics of a sensing signal formed by high-order cumulant as the basis for judging the existence of a main user and the modulation mode of the main user signal, and uses a C4.5 algorithm to train and form a random forest classifier, thereby overcoming the over-fitting problem caused by a single classifier of a decision tree algorithm.
The method comprises the following specific implementation steps:
step 1: and converting the signal training data set into a high-order cumulant characteristic sample set according to a high-order cumulant calculation formula.
The higher order cumulant calculation formula is as follows:
C20＝cum(s[n],s[n])＝M20
C21＝cum(s[n],s*[n])＝M21
C41＝cum(s[n],s[n],s[n],s*[n])＝M41-3M20M21
the characteristics of any received signal may be expressed as:
step 2: a decision tree is constructed. Randomly extracting N times from the N characteristic samples in a replacement mode, randomly extracting M times from the M characteristic samples in a replacement mode, and removing repeated samples and repeated characteristics to form a sub-sample set and a sub-feature set.
And 3, step 3: since the high-order cumulant is a continuous variable, the average value of each feature in the sub-feature set in the sub-sample set needs to be calculated, and the average value is used as a node splitting basis.
And 4, step 4: according to the characteristics and abs (C)x) The class information entropy, the condition information entropy, the information gain, the split information entropy and the information gain rate are calculated according to the size relation and the data of the sub-sample set. And selecting the characteristics of the maximum information gain rate as the basis of the node splitting.
And 5: and dividing the sub-sample set according to the split node, and if the divided sample types belong to the same class, converting the node into a leaf node. And if the classified samples are not pure, repeating the steps 3 and 4 until the samples cannot be classified, and completing the construction of the decision tree.
Step 6: judging whether the number of decision trees reaches a preset tree or not, and if not, repeating the steps 2 to 5; and if the number reaches the set number, finishing the random forest construction.
And 7: the constructed random forest was tested using a test sample set.
FIG. 1 is a model diagram of a perception system, which is mainly composed of an off-line training module and an on-line recognition module. The off-line training module firstly records data samples of historical received signals, and then performs data preprocessing operations such as filtering, amplification, spectrum downward movement and the like on the data samples to change the received signal data samples into baseband data samples. And then calculating the high-order cumulant of the data to obtain a feature sample for machine learning training, and finally training and learning by using a random forest algorithm to obtain a signal classifier. The on-line identification module receives the signal, and after a series of data processing, the signal classifier can be used for conveniently and quickly judging the signal type and outputting the result for subsequent signal processing work.
Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (7)
1. A spectrum sensing method based on a random forest algorithm is characterized by comprising the following steps:
step 1: receiving signals through an antenna, and converting a signal training data set into a characteristic sample set according to a high-order cumulant calculation formula;
and 2, step: constructing a decision tree, and screening the characteristic sample set to form a sub-sample set and a sub-feature set;
and step 3: calculating the average value of each feature in the sub-sample set;
and 4, step 4: calculating an information gain rate according to each feature and the average value in the sub-feature set, and taking the feature with the largest information gain rate as a split node;
and 5: dividing the sub-sample set according to the split nodes to complete the construction of the decision tree;
step 6: constructing a random forest according to the decision tree for sensing subsequent received signals;
and 7: testing the random forest by using a sample set to be tested to obtain the modulation type of a test sample signal;
the high-order cumulant calculation formula is as follows:
C20＝cum(s[n],s[n])＝M20
C21＝cum(s[n],s*[n])＝M21
C41＝cum(s[n],s[n],s[n],s*[n])＝M41-3M20M21
wherein C is20Representing a second order cumulative amount of the received signal; m is a group of20Representing second moments of the received signal; cum (x, x) represents a joint accumulation function of the received signals; s [ n ]]Indicating a main user signal; n represents the number of sampling points of the main user signal; s is*[n]Is s [ n ]]Conjugated forms of (a);
the characteristics of any received signal are represented as:
xia feature matrix representing the ith received signal; i represents the ith received signal; n represents the number of received signal samples.
2. The spectrum sensing method based on the random forest algorithm according to the claim 1, wherein the step 2 comprises the following steps: randomly extracting N times from N samples in a replacement manner, randomly extracting M times from M characteristics in a replacement manner, and removing repeated samples and repeated characteristics to form a sub-sample set and a sub-characteristic set.
3. The spectrum sensing method based on the random forest algorithm according to the claim 1, wherein the step 5 comprises the following steps: if the divided sample types belong to the same class, splitting the node into leaf nodes; and if the classified samples are not pure, repeating the step 3 and the step 4 until the samples cannot be classified, and completing the construction of the decision tree.
4. The spectrum sensing method based on the random forest algorithm according to the claim 1, wherein the step 6 comprises the following steps: judging whether the number of the decision trees reaches the preset number of decisions, if not, repeatedly executing the steps 2 to 5; and if the number reaches the set number, finishing the construction of the random forest.
5. The spectrum sensing method based on the random forest algorithm as claimed in claim 1, wherein the modulation type of the test sample signal obtained through testing is compared with the actual modulation type of the test sample signal to obtain the algorithm accuracy of the random forest, and parameters of the decision forest, including the number of decision trees, are adjusted according to the accuracy to enable the algorithm accuracy to meet the preset requirement.
6. A spectrum sensing system based on a random forest algorithm is characterized in that the spectrum sensing method based on the random forest algorithm, which is disclosed by any one of claims 1 to 5, is adopted, and comprises the following steps:
an off-line training module: recording data samples of historical received signals, filtering, amplifying and carrying out spectrum downward movement, converting the data samples of the received signals into baseband data samples, calculating high-order cumulant of the data to obtain characteristic samples for machine learning training, and training and learning by using a random forest algorithm to obtain a signal classifier;
an online identification module: and after receiving the signals, judging the signal types according to the signal classifier, and outputting the results for signal processing.
7. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010930938.9A CN112134634B (en) | 2020-09-07 | 2020-09-07 | Random forest algorithm-based spectrum sensing method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010930938.9A CN112134634B (en) | 2020-09-07 | 2020-09-07 | Random forest algorithm-based spectrum sensing method, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112134634A CN112134634A (en) | 2020-12-25 |
| CN112134634B true CN112134634B (en) | 2022-07-12 |
Family
ID=73847438
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010930938.9A Active CN112134634B (en) | 2020-09-07 | 2020-09-07 | Random forest algorithm-based spectrum sensing method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112134634B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115037392B (en) * | 2022-03-08 | 2023-07-18 | 西安电子科技大学 | Signal detection method, terminal, medium and aircraft based on random forest |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845339A (en) * | 2016-12-13 | 2017-06-13 | 电子科技大学 | A kind of mobile phone individual discrimination method based on bispectrum and EMD fusion features |
| CN107395590A (en) * | 2017-07-19 | 2017-11-24 | 福州大学 | A kind of intrusion detection method classified based on PCA and random forest |
| CN109447131A (en) * | 2018-09-30 | 2019-03-08 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | Similar high-dimensional target information identification method and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8688759B2 (en) * | 2006-06-16 | 2014-04-01 | Bae Systems Information And Electronic Systems Integration Inc. | Efficient detection algorithm system for a broad class of signals using higher-order statistics in time as well as frequency domains |
| KR20170096874A (en) * | 2016-02-17 | 2017-08-25 | 삼성전자주식회사 | Apparatus and method for generating weight estimation model, and Apparatus and method for estimating weight |
| US10408913B2 (en) * | 2017-08-09 | 2019-09-10 | Swfl, Inc. | Systems and methods for physical detection using radio frequency noise floor signals and deep learning techniques |
-
2020
- 2020-09-07 CN CN202010930938.9A patent/CN112134634B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106845339A (en) * | 2016-12-13 | 2017-06-13 | 电子科技大学 | A kind of mobile phone individual discrimination method based on bispectrum and EMD fusion features |
| CN107395590A (en) * | 2017-07-19 | 2017-11-24 | 福州大学 | A kind of intrusion detection method classified based on PCA and random forest |
| CN109447131A (en) * | 2018-09-30 | 2019-03-08 | 华东计算技术研究所（中国电子科技集团公司第三十二研究所） | Similar high-dimensional target information identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于随机森林的认知网络频谱感知算法研究;王鑫;《中国博士学位论文全文数据库（信息科技辑）》;20181015;正文第3-5章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112134634A (en) | 2020-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Duarte et al. | Vehicle classification in distributed sensor networks | |
| CN111832417B (en) | Signal modulation pattern recognition method based on CNN-LSTM model and transfer learning | |
| CN107830996B (en) | Fault diagnosis method for aircraft control surface system | |
| CN110334591A (en) | A kind of detection of unmanned plane Frequency Hopping Signal and recognition methods based on clustering | |
| CN108055094B (en) | Unmanned aerial vehicle manipulator frequency spectrum feature identification and positioning method | |
| Liu | Multi-feature fusion for specific emitter identification via deep ensemble learning | |
| CN109473119B (en) | Acoustic target event monitoring method | |
| CN111832462B (en) | Frequency hopping signal detection and parameter estimation method based on deep neural network | |
| CN111209960B (en) | CSI system multipath classification method based on improved random forest algorithm | |
| CN112699793A (en) | Fatigue driving detection optimization identification method based on random forest | |
| CN106203437B (en) | Individual driving behavior recognition methods and device | |
| CN114760172B (en) | Method and device for identifying radio frequency baseband comprehensive characteristic signals | |
| CN112528774B (en) | Intelligent unknown radar signal sorting system and method in complex electromagnetic environment | |
| CN112134634B (en) | Random forest algorithm-based spectrum sensing method, system and medium | |
| CN110764152B (en) | Device and method for rapid detection and identification of unmanned aerial vehicle | |
| CN116633601A (en) | Detection method based on network traffic situation awareness | |
| CN113449682B (en) | Method for identifying radio frequency fingerprints in civil aviation field based on dynamic fusion model | |
| CN114980122A (en) | Small sample radio frequency fingerprint intelligent identification system and method | |
| CN111708890B (en) | Search term determining method and related device | |
| CN112885330A (en) | Language identification method and system based on low-resource audio | |
| CN116756225A (en) | Situation data information processing method based on computer network security | |
| CN110826425A (en) | VHF/UHF frequency band radio signal modulation mode identification method based on deep neural network | |
| CN110071884A (en) | A kind of Modulation Recognition of Communication Signal method based on improvement entropy cloud feature | |
| CN113688953B (en) | Industrial control signal classification method, device and medium based on multilayer GAN network | |
| CN115809426A (en) | Radiation source individual identification method and system |
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 |