CN110996343A - Interference recognition model based on deep convolutional neural network and intelligent recognition algorithm - Google Patents
Interference recognition model based on deep convolutional neural network and intelligent recognition algorithm Download PDFInfo
- Publication number
- CN110996343A CN110996343A CN201911307930.0A CN201911307930A CN110996343A CN 110996343 A CN110996343 A CN 110996343A CN 201911307930 A CN201911307930 A CN 201911307930A CN 110996343 A CN110996343 A CN 110996343A
- Authority
- CN
- China
- Prior art keywords
- interference
- neural network
- convolutional neural
- model
- deep convolutional
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Image Analysis (AREA)
- Noise Elimination (AREA)
Abstract
An interference recognition model and an intelligent recognition algorithm based on a deep convolutional neural network are characterized in that: the receiver for interference recognition collects data of interference signals sent by a single or a plurality of interference machines, a frequency spectrum waterfall graph of the receiver serving as a receiving end is used as a network input layer for a plurality of training, and after a training model with enough fitting degree is achieved, the frequency spectrum waterfall graph is used as network input for online recognition according to a trained storage model and the frequency spectrum waterfall of the receiving end. The method is combined with other structures or methods, so that the model is complete, the physical significance is clear, the algorithm is designed reasonably and effectively, and the interference identification scene based on the deep convolutional neural network algorithm can be well depicted.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to an interference identification model and an intelligent identification algorithm based on a deep convolutional neural network.
Background
The communication countermeasure refers to an electromagnetic countermeasure performed by both adversaries in the field of radio communication by using a common radio communication device and a special communication countermeasure device. As frequency-using equipment in communication environments is increasing day by day, communication countermeasure has become a hot topic, and intensive research on how to better avoid the influence of enemies and other parties on their own frequency-using has become important. With the rapid development of machine learning, the intelligence level of various devices is continuously improved, and intelligent interference and intelligent anti-interference also become one of the research subjects in the communication field. The communication interference resistance comprises two aspects: firstly, a certain means is utilized to disturb or destroy the investigation equipment of an enemy; secondly, electromagnetic reinforcement and interference suppression measures are adopted for own communication, and the anti-reconnaissance and anti-interference capability of own communication equipment is enhanced. Wherein the anti-interference capability mainly refers to the capability of suppressing communication interference of an enemy. However, most of research on interference signal identification is focused on feature extraction of different interference signals of different communication systems, and research on classification algorithms is less, which also shows the importance of feature extraction in methods of interference identification based on feature extraction, and has a larger research space for general interference signal classification algorithms such as convolutional neural networks. The receiver combines the received spectrum information with the intelligent agent into a new method of interference pattern recognition.
Due to the complex dynamic characteristics of coexistence of communication and interference in the environment, the intelligent interference identification method becomes one of the important solutions of the interference identification problem, the deep convolutional neural network becomes a hot classification tool (refer to LeCun Y, Bottou L, Bengio Y, et al, Gradient-based learning applied to the IEEE [ J ] Proceedings of the IEEE,1998,86(11): 2278-.
Disclosure of Invention
In order to solve the problems, the invention provides an interference identification model and an intelligent identification algorithm based on a deep convolutional neural network, and an interference identification scene based on a deep learning algorithm is well described.
In order to overcome the defects in the prior art, the invention provides a solution for an interference recognition model and an intelligent recognition algorithm based on a deep convolutional neural network, which comprises the following specific steps:
an interference recognition model based on a deep convolutional neural network, comprising:
the interference identification model based on the deep convolutional neural network is characterized as follows: the receiver for interference recognition collects data of interference signals sent by a single or a plurality of interference machines, a frequency spectrum waterfall graph of the receiver serving as a receiving end is used as a network input layer for a plurality of training, and after a training model with enough fitting degree is achieved, the frequency spectrum waterfall graph is used as network input for online recognition according to a trained storage model and the frequency spectrum waterfall of the receiving end.
Power spectral density s of the receiver as a receiving sidet(f) Is expressed by equation (1):
in equation (1), the jth jammer may select its frequency at the t-th sampling
And power spectral density function
When the receiver senses the full frequency band, the interference signal and the noise are received simultaneously; gjIs from jammer to receiveThe channel link gain of the receiver, f is the frequency of the receiver, n (f) is the PSD function of the noise, J is a positive integer, J is a positive integer and is the number of jammers, and t is a positive integer and represents the sequence number of the receiver sampling times.
Discrete value sampling spectrum s in interference identification model based on deep convolutional neural networki，tDefined by formula (2):
where Δ f is the spectral resolution, fLStarting frequency, s, representing the interference bandwidth of the jammert，iRepresenting the sampled spectrum of the i-th sample received by the receiver at the t-th sample, the frequency vector perceived by the receiver being st＝st，1，st，2，...st，NN is the number of samples sampled at the t-th time, and i is a positive integer.
In a dynamic unknown environment, a frequency spectrum waterfall diagram of the receiver as a receiving end is used as an input layer of a neural network, characteristics are extracted through convolution, and after a plurality of times of supervision training, an interference recognition model is finally obtained, wherein the interference recognition model is specifically as follows:
in a dynamically unknown communication environment, the interference identification problem in the model is modeled as a convolutional layer extraction process, and the complex interference pattern existing in the environment is closely related to the historical information, so the environment state StIs defined as St＝{st，st-1，...，st-T+1Where T represents the number of historical states tracked, then StIs a thermodynamic block diagram represented by a two-dimensional matrix T multiplied by N, wherein time domain and frequency domain information is contained, and a frequency spectrum waterfall diagram is constructed.
In historical environment state information, data is used as an input layer of a designed CNN model to be subjected to iterative training, and x is defined as a data vector from the input data to the input layer and xiFor the ith element in x and representing the data input to the input layer for the ith time, y is the label vector corresponding to x, optimize the objective
Is shown in equation (3):
The intelligent recognition algorithm of the interference recognition model based on the deep convolutional neural network comprises the following steps:
step 1, initializing, namely setting the weight and bias of each network node in the deep convolutional neural network to be random and meet the value according to probability distribution, and sensing an initial environment;
step 2, inputting the data collected by the receiver into a deep convolutional neural network, wherein the deep convolutional neural network is also trained into a supervised neural network, and a certain loss function exists between the input data and the label
Thereby the device is provided with
Proposing a structural risk function Psrm(f) Is shown in equation (5):
λ is a set coefficient greater than 0, j (f) is the complexity of the model;
where η is the learning rate, ωtFor the empirical risk function weight of the t-th sample, ω is such that f is small enough that the learning rate is small enoughω(xi) The optimal solution is achieved, and the algorithm is linearly converged;
and 4, bringing in a reserved test data set sample, and carrying out online identification on the trained interference identification model based on the deep convolutional neural network.
The invention has the beneficial effects that:
(1) the network construction of the traditional feature recognition is a convolutional neural network, and the calculation complexity is reduced under the condition of not influencing the performance;
(2) the model is perfect, the physical significance is clear, and the proposed intelligent recognition algorithm based on the deep convolutional neural network realizes the considerable recognition rate of the proposed model;
(3) the method can effectively identify the interference mode and well depict the interference identification scene based on the deep convolutional neural network algorithm.
Drawings
FIG. 1 is a system model diagram of the deep convolutional neural network interference recognition model of the present invention.
Fig. 2 is a schematic structural diagram of a convolutional neural network for interference recognition of the present invention.
FIG. 3 is a flow chart of the training update process of the convolutional neural network to interference recognition in the present invention.
Fig. 4 is a graph illustrating the identification and accuracy of the fixed-frequency interference pattern in embodiment 1 of the present invention.
Fig. 5 is a graph of the identification and accuracy of the sweep frequency interference pattern in embodiment 2 of the present invention.
Detailed Description
The invention provides a deep convolutional neural network interference recognition model and an intelligent recognition algorithm, and aims to provide a scheme for solving the problem of intelligent recognition. Based on a machine learning algorithm, a frequency spectrum waterfall diagram of a receiving end is used as an input layer of a neural network, a deep convolution neural network is adopted to train and fit collected data, and supervised training is carried out on the collected data; then, the network model is trained and stored for a plurality of times, so that the interference mode can be recognized in real time.
FIG. 1 is a diagram of a model interference recognition system. In the model, a receiver collects data of a single or a plurality of jammers, a frequency spectrum waterfall diagram of a receiving end is used as a network input layer for a plurality of training, and the model can be stored after the training model with enough fitting degree is achieved.
FIG. 2 is a convolutional neural network model for interference recognition. The interference recognition network framework adopts a convolution neural network framework, a frequency spectrum waterfall graph is input, recognition data with a label is obtained through one layer of convolution, one layer of pooling and two layers of full connection, and then the best fitting degree is achieved through a plurality of times of training. The training model is saved and real-time interference pattern recognition can be performed by using the input data and the model.
The model is characterized as follows: the single receiver collects data of a single or a plurality of jammers, the frequency spectrum waterfall of the receiving end is used as a network input layer for a plurality of training, after a training model with enough fitting degree is achieved, the frequency spectrum waterfall of the receiving end is used as input in a dynamic position environment, and therefore online mode recognition is achieved.
Fig. 3 is a process of modeling and updating an interference recognition convolutional neural network, after the agent takes interference data of a receiving end, the interference data is brought into a designed convolutional neural network, after a plurality of iterations and observation of data fitting degree, a trained model is obtained after optimizing a network structure and training weights, and finally, collected real data is used as model input, so that a recognition result can be obtained.
According to the method, based on an Le-Net5 model, combined with the problem of intelligent interference identification, factors such as huge interference data, difficulty in data preprocessing, time-consuming learning calculation and the like are considered, a deep convolutional neural network is adopted to process and classify the interference data, network weights are continuously updated in the process, and an optimal model is obtained and applied to actual data.
The invention will be further described with reference to the following figures and examples.
As shown in fig. 1 to 5, the interference recognition model based on the deep convolutional neural network includes:
the interference identification model based on the deep convolutional neural network is characterized as follows: the receiver for interference recognition collects data of interference signals sent by a single or a plurality of interference machines, a frequency spectrum waterfall graph of the receiver serving as a receiving end is used as a network input layer for a plurality of training, and after a training model with enough fitting degree is achieved, the frequency spectrum waterfall graph is used as network input for online recognition according to a trained storage model and the frequency spectrum waterfall of the receiving end.
Power spectral density s of the receiver as a receiving sidet(f) Is expressed by equation (1):
in equation (1), the jth jammer may select its frequency at the t-th sampling
And power spectral density function
When the receiver senses the full frequency band, the interference signal and the noise are received simultaneously; giIs the channel link gain from the jammer to the receiver, f is the frequency of the receiver, n (f) is the PSD function of the noise, J is a positive integer and is the number of jammers, t is a positive integer and represents the sequence number of receiver sampling times.
Discrete value sampling spectrum s in interference identification model based on deep convolutional neural networki，tDefined by formula (2):
where Δ f is the spectral resolution, fLStarting frequency, s, representing the interference bandwidth of the jammert，iRepresenting the sampled spectrum of the i-th sample received by the receiver at the t-th sample, the frequency vector perceived by the receiver being st＝st，1，st，2，…st，NN is the number of samples sampled at the t-th time, and i is a positive integer.
In a dynamic unknown environment, a frequency spectrum waterfall diagram of the receiver as a receiving end is used as an input layer of a neural network, characteristics are extracted through convolution, and after a plurality of times of supervision training, an interference recognition model is finally obtained, wherein the interference recognition model is specifically as follows:
in a dynamically unknown communication environment, the interference identification problem in the model is modeled as a convolutional layer extraction process, and the complex interference pattern existing in the environment is closely related to the historical information, so the environment state StIs defined as St＝{st，st-1，...，st-T+1Where T represents the number of historical states tracked, then StIs a thermodynamic block diagram represented by a two-dimensional matrix T multiplied by N, wherein time domain and frequency domain information is contained, and a frequency spectrum waterfall diagram is constructed.
In historical environment state information, data is used as an input layer of a designed CNN model to be subjected to iterative training, and x is defined as a data vector from the input data to the input layer and xiFor the ith element in x and representing the data input to the input layer for the ith time, y is the label vector corresponding to x, optimize the objective
Is shown in equation (3):
The intelligent recognition algorithm of the interference recognition model based on the deep convolutional neural network comprises the following steps:
step 1, initializing, namely setting the weight and bias of each network node in the deep convolutional neural network to be random and meet the value according to probability distribution, and sensing an initial environment;
step 2, inputting the data collected by the receiver into the designed deep convolution neural network, and because the deep convolution neural network is also trained as a supervised neural network, a certain loss function exists on the input data and the label
From this an empirical risk function R is derivedsrm(f) Is shown in equation (4):
n is the number of samples, fω(x) Is equivalent to
According to the statistical theory, when fω(x) When the number of the interference recognition models is limited, the empirical risk minimization means that the obtained results of the models are close to the real values, and the interference recognition models based on the deep convolutional neural network are better; to avoid overfitting, a structural risk function R is proposedsrm(f) Is shown in equation (5):
λ is a set coefficient greater than 0, j (f) is the complexity of the model;
and 3, updating the convolutional neural network by using a formula (6) through the set training times, and repeating the step 2, wherein the corresponding optimization model is a minimized structure risk function, and the empirical risk function weight omegatThe update formula is:
where η is the learning rate, ωtFor the empirical risk function weight of the t-th sample, ω is such that f is small enough that the learning rate is small enoughω(xi) The optimal solution is achieved, and the algorithm is linearly converged;
and 4, bringing in a reserved test data set sample, and carrying out online identification on the trained interference identification model based on the deep convolutional neural network.
Since the calculation classification is less, the complicated convolution neural network model can be simplified to achieve the effect of reducing the calculation amount.
The invention is further illustrated with respect to the following examples:
example 1
The first embodiment of the invention is specifically described as follows, the system simulation adopts python language, and is based on tensiorflow deep learning framework, and the parameter setting does not affect the generality. This embodiment verifies the validity of the proposed model and method, and fig. 4 verifies the validity of the fixed-frequency interference pattern. The parameters are set to be that the frequency band of the interference is 20MHz, the frequency resolution of the frequency spectrum sensing is 100kHz, the receiver carries out full-band sensing once every 1ms and keeps the sensed frequency spectrum data for 200ms, so StThe matrix size is 200 × 200, the interference signal bandwidth is 4MHz, the signal waveform is a raised cosine wave, the roll-off coefficient is α ═ 0.5, the interference power is 30dbm, in embodiment 1, 2 fixed frequency interference modes are considered:
1. single tone interference, interference frequency is 2 MHz.
2. The multi-tone interference and the fixed interference frequency are respectively 2MHz,10MHz and 18 MHz.
Fig. 4 is a frequency spectrum waterfall graph of a fixed-frequency interference pattern in embodiment 1 of the present invention, and it can be seen from the graph that the interference appears as many vertical stripes, and the right side is a training recognition rate graph in the interference pattern, and the accuracy fluctuates above 0.9.
Example 2
The second embodiment of the invention is specifically described as follows, the system simulation adopts python language, and is based on tensierflow deep learning framework, and the parameter setting does not affect the generality. This embodiment verifies the validity of the proposed model and method, fig. 4 verifies the validity for fixed frequency interference mode, fig. 5 verifies the validity for frequency sweep interference identification. The parameters are set to be that the frequency band of the interference is 20MHz, the frequency resolution of the frequency spectrum sensing is 100kHz, the receiver carries out full-band sensing once every 1ms and keeps the sensed frequency spectrum data for 200ms, so StThe matrix size is 200 × 200, the interference signal bandwidth is 4MHz, the signal waveform is a raised cosine wave, the roll-off coefficient is α ═ 0.5, the interference power is 30dbm, in embodiment 2, the sweep interference mode is considered, the sweep interference, and the sweep rates are 0.2GHz/s and 0.5 GHz/s.
Fig. 5 is a frequency spectrum waterfall graph of the sweep interference mode in embodiment 2 of the present invention, and it can be seen from the graph that the interference appears as a diagonal line due to the linear frequency change. The right side is the training accuracy graph in this interference mode. Therefore, the model has high recognition degree and the precision fluctuates above 0.9.
In conclusion, the deep convolutional neural network interference recognition model provided by the invention fully considers the problems of complex data preprocessing, complex network structure and huge calculation amount in the interference recognition, and has more practical significance than the traditional model; the intelligent recognition algorithm based on the deep convolutional neural network interference recognition model can realize effective solution of the proposed model, can be seen from a precision curve to have high recognition rate, and effectively deals with interference pattern recognition.
The present invention has been described in an illustrative manner by the embodiments, and it should be understood by those skilled in the art that the present disclosure is not limited to the embodiments described above, but is capable of various changes, modifications and substitutions without departing from the scope of the present invention.
Claims (6)
1. An interference recognition model based on a deep convolutional neural network, comprising:
the interference identification model based on the deep convolutional neural network is characterized as follows: the receiver for interference recognition collects data of interference signals sent by a single or a plurality of interference machines, a frequency spectrum waterfall graph of the receiver serving as a receiving end is used as a network input layer for a plurality of training, and after a training model with enough fitting degree is achieved, the frequency spectrum waterfall graph is used as network input for online recognition according to a trained storage model and the frequency spectrum waterfall of the receiving end.
2. The deep convolutional neural network-based interference recognition model of claim 1, wherein the power spectral density s of the receiver as a receiving endt(f) Is expressed by equation (1):
in equation (1), the jth jammer may select its frequency f at the t-th samplingt jAnd power spectral density function
When the receiver senses the full frequency band, the interference signal and the noise are received simultaneously; gjIs the channel link gain from the jammer to the receiver, f is the frequency of the receiver, n (f) is the PSD function of the noise, J is a positive integer and is the number of jammers, t is a positive integer and represents the sequence number of receiver sampling times.
3. The deep convolutional neural network-based interference recognition model of claim 1, wherein the spectrum s of discrete value samples in the deep convolutional neural network-based interference recognition modeli，tDefined by formula (2):
where Δ f is the spectral resolution, fLStarting frequency, s, representing the interference bandwidth of the jammert，iRepresenting the sampled spectrum of the i-th sample received by the receiver at the t-th sample, the frequency vector perceived by the receiver being st＝st，1，st，2，...，st，NN is the number of samples sampled at the t-th time, and i is a positive integer.
4. The interference recognition model based on the deep convolutional neural network of claim 1, wherein in a dynamic unknown environment, a frequency spectrum waterfall diagram of the receiver as a receiving end is used as an input layer of the neural network, and after convolution extraction of features and several times of supervision training, an interference recognition model is finally obtained, which is specifically as follows:
in a dynamically unknown communication environment, the interference identification problem in the model is modeled as a convolutional layer extraction process, and the complex interference pattern existing in the environment is closely related to the historical information, so the environment state StIs defined as St＝{st，st-1，...，st-T+1Where T represents the number of historical states tracked, then StIs a thermodynamic block diagram represented by a two-dimensional matrix T multiplied by N, wherein time domain and frequency domain information is contained, and a frequency spectrum waterfall diagram is constructed.
5. The deep convolutional neural network-based interference recognition model of claim 1, wherein in the historical environmental state information, data is iteratively trained as an input layer of a designed CNN model, and x is defined as a data vector of input data to the input layer, xiFor the ith element in x and representing the data input to the input layer for the ith time, y is the label vector corresponding to x, optimize the objective
Is shown in equation (3):
6. An intelligent recognition algorithm of an interference recognition model based on a deep convolutional neural network is characterized by comprising the following steps:
step 1, initializing, namely setting the weight and bias of each network node in the deep convolutional neural network to be random and meet the value according to probability distribution, and sensing an initial environment;
step 2, inputting the data collected by the receiver into a deep convolutional neural network, wherein the deep convolutional neural network is also trained into a supervised neural network, and a certain loss function exists between the input data and the label
Thereby the device is provided with
Proposing a structural risk function Rsrm(f) Is shown in equation (5):
λ is a set coefficient greater than 0, j (f) is the complexity of the model;
and 3, updating the convolutional neural network by using a formula (6) through the set training times, and repeating the step 2, wherein the corresponding optimization model is a minimized structure risk function, and the empirical risk function weight omegatThe update formula is:
where η is the learning rate, ωtFor the empirical risk function weight of the t-th sample, ω is such that f is small enough that the learning rate is small enoughω(xi) The optimal solution is achieved, and the algorithm is linearly converged;
and 4, bringing in a reserved test data set sample, and carrying out online identification on the trained interference identification model based on the deep convolutional neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911307930.0A CN110996343B (en) | 2019-12-18 | 2019-12-18 | Intelligent recognition system and recognition method of interference recognition model based on deep convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911307930.0A CN110996343B (en) | 2019-12-18 | 2019-12-18 | Intelligent recognition system and recognition method of interference recognition model based on deep convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110996343A true CN110996343A (en) | 2020-04-10 |
| CN110996343B CN110996343B (en) | 2023-06-30 |
Family
ID=70095337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911307930.0A Active CN110996343B (en) | 2019-12-18 | 2019-12-18 | Intelligent recognition system and recognition method of interference recognition model based on deep convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110996343B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562597A (en) * | 2020-06-02 | 2020-08-21 | 南京敏智达科技有限公司 | Beidou satellite navigation interference source identification method based on BP neural network |
| CN111669248A (en) * | 2020-06-04 | 2020-09-15 | 上海特金无线技术有限公司 | Unmanned aerial vehicle signal suppression method and device, electronic equipment and storage medium |
| CN111786738A (en) * | 2020-07-01 | 2020-10-16 | 中国人民解放军陆军工程大学 | Anti-interference learning network structure based on long-term and short-term memory and learning method |
| CN112435356A (en) * | 2020-11-04 | 2021-03-02 | 南京航天工业科技有限公司 | ETC interference signal identification method and detection system |
| CN112491442A (en) * | 2020-11-17 | 2021-03-12 | 中山大学 | Self-interference elimination method and device |
| CN113067653A (en) * | 2021-03-17 | 2021-07-02 | 北京邮电大学 | Spectrum sensing method and device, electronic equipment and medium |
| CN113138201A (en) * | 2021-03-24 | 2021-07-20 | 北京大学 | Metamaterial Internet of things system and method for wireless passive environment state detection |
| CN114358064A (en) * | 2021-12-23 | 2022-04-15 | 中国人民解放军海军工程大学 | Interference detection device and method based on deep support vector data description |
| CN114598403A (en) * | 2022-03-31 | 2022-06-07 | 中国人民解放军陆军工程大学 | Data link broadband noise electromagnetic signal interference prediction method and system |
| CN115243288A (en) * | 2022-07-11 | 2022-10-25 | 中国人民解放军国防科技大学 | Interference identification method and device based on multi-node cooperative sensing |
| CN116271539A (en) * | 2023-05-15 | 2023-06-23 | 苏州维伟思医疗科技有限公司 | Method for identifying shockable rhythm, wearable cardioverter-defibrillator and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108509911A (en) * | 2018-04-03 | 2018-09-07 | 电子科技大学 | Interference signal recognition methods based on convolutional neural networks |
| CN108764013A (en) * | 2018-03-28 | 2018-11-06 | 中国科学院软件研究所 | A kind of automatic Communication Signals Recognition based on end-to-end convolutional neural networks |
| CN108777872A (en) * | 2018-05-22 | 2018-11-09 | 中国人民解放军陆军工程大学 | A kind of anti-interference model of depth Q neural networks and intelligent Anti-interference algorithm |
| CN109961017A (en) * | 2019-02-26 | 2019-07-02 | 杭州电子科技大学 | A kind of cardiechema signals classification method based on convolution loop neural network |
-
2019
- 2019-12-18 CN CN201911307930.0A patent/CN110996343B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108764013A (en) * | 2018-03-28 | 2018-11-06 | 中国科学院软件研究所 | A kind of automatic Communication Signals Recognition based on end-to-end convolutional neural networks |
| CN108509911A (en) * | 2018-04-03 | 2018-09-07 | 电子科技大学 | Interference signal recognition methods based on convolutional neural networks |
| CN108777872A (en) * | 2018-05-22 | 2018-11-09 | 中国人民解放军陆军工程大学 | A kind of anti-interference model of depth Q neural networks and intelligent Anti-interference algorithm |
| CN109961017A (en) * | 2019-02-26 | 2019-07-02 | 杭州电子科技大学 | A kind of cardiechema signals classification method based on convolution loop neural network |
Non-Patent Citations (1)
| Title |
|---|
| 陈雪等: "一种优化的卷积神经网络调制识别算法", 《电讯技术》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111562597A (en) * | 2020-06-02 | 2020-08-21 | 南京敏智达科技有限公司 | Beidou satellite navigation interference source identification method based on BP neural network |
| CN111669248A (en) * | 2020-06-04 | 2020-09-15 | 上海特金无线技术有限公司 | Unmanned aerial vehicle signal suppression method and device, electronic equipment and storage medium |
| CN111786738A (en) * | 2020-07-01 | 2020-10-16 | 中国人民解放军陆军工程大学 | Anti-interference learning network structure based on long-term and short-term memory and learning method |
| CN111786738B (en) * | 2020-07-01 | 2022-06-03 | 中国人民解放军陆军工程大学 | Anti-interference learning network structure based on long-term and short-term memory and learning method |
| CN112435356A (en) * | 2020-11-04 | 2021-03-02 | 南京航天工业科技有限公司 | ETC interference signal identification method and detection system |
| CN112491442A (en) * | 2020-11-17 | 2021-03-12 | 中山大学 | Self-interference elimination method and device |
| CN113067653A (en) * | 2021-03-17 | 2021-07-02 | 北京邮电大学 | Spectrum sensing method and device, electronic equipment and medium |
| CN113138201B (en) * | 2021-03-24 | 2022-05-20 | 北京大学 | Metamaterial Internet of things system and method for wireless passive environment state detection |
| CN113138201A (en) * | 2021-03-24 | 2021-07-20 | 北京大学 | Metamaterial Internet of things system and method for wireless passive environment state detection |
| CN114358064A (en) * | 2021-12-23 | 2022-04-15 | 中国人民解放军海军工程大学 | Interference detection device and method based on deep support vector data description |
| CN114358064B (en) * | 2021-12-23 | 2022-06-21 | 中国人民解放军海军工程大学 | Interference detection device and method based on deep support vector data description |
| CN114598403A (en) * | 2022-03-31 | 2022-06-07 | 中国人民解放军陆军工程大学 | Data link broadband noise electromagnetic signal interference prediction method and system |
| CN114598403B (en) * | 2022-03-31 | 2024-03-12 | 中国人民解放军陆军工程大学 | Data link broadband noise electromagnetic signal interference prediction method and system |
| CN115243288A (en) * | 2022-07-11 | 2022-10-25 | 中国人民解放军国防科技大学 | Interference identification method and device based on multi-node cooperative sensing |
| CN115243288B (en) * | 2022-07-11 | 2024-05-03 | 中国人民解放军国防科技大学 | Interference identification method and device based on multi-node cooperative sensing |
| CN116271539A (en) * | 2023-05-15 | 2023-06-23 | 苏州维伟思医疗科技有限公司 | Method for identifying shockable rhythm, wearable cardioverter-defibrillator and storage medium |
| CN116271539B (en) * | 2023-05-15 | 2023-09-08 | 苏州维伟思医疗科技有限公司 | Method for identifying shockable rhythm, wearable cardioverter-defibrillator and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110996343B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110996343A (en) | Interference recognition model based on deep convolutional neural network and intelligent recognition algorithm | |
| CN108777872B (en) | Intelligent anti-interference method and intelligent anti-interference system based on deep Q neural network anti-interference model | |
| Zhang et al. | An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation | |
| CN113435247B (en) | Intelligent recognition method, system and terminal for communication interference | |
| CN110166154B (en) | Software radio frequency spectrum monitoring and identifying method based on neural network | |
| CN114449452A (en) | Indoor positioning algorithm for heterogeneous equipment | |
| Hu et al. | Meta-reinforcement learning for trajectory design in wireless UAV networks | |
| CN116047427B (en) | Small sample radar active interference identification method | |
| CN114881093B (en) | Signal classification and identification method | |
| CN112949820A (en) | Cognitive anti-interference target detection method based on generation of countermeasure network | |
| CN114358389A (en) | Short-term power load prediction method combining VMD decomposition and time convolution network | |
| Cai et al. | Jamming pattern recognition using spectrum waterfall: A deep learning method | |
| CN114764577A (en) | Lightweight modulation recognition model based on deep neural network and method thereof | |
| Chen et al. | Energy-aware path planning for obtaining fresh updates in UAV-IoT MEC systems | |
| Zhang et al. | Automatic classification and recognition method based on partially-connected differentiable architecture search for ISAC systems | |
| CN116566777A (en) | Frequency hopping signal modulation identification method based on graph convolution neural network | |
| CN116471154A (en) | Modulation signal identification method based on multi-domain mixed attention | |
| CN116680608A (en) | Signal modulation identification method based on complex graph convolutional neural network | |
| CN116304621A (en) | Smart grid false data injection attack positioning method based on frequency spectrum domain data driving | |
| CN116165886A (en) | Multi-sensor intelligent cooperative control method, device, equipment and medium | |
| CN112946567B (en) | Moving target fingerprint indoor positioning method based on domain antagonism neural network | |
| Feng et al. | FCGCN: Feature Correlation Graph Convolution Network for Few-Shot Individual Identification | |
| Ye et al. | Research on machine learning algorithm based on contour matching modal matrix | |
| Wang et al. | Exploration on Automatic Management of GIS Using TL-CNN and IoT | |
| CN110691319A (en) | Method for realizing high-precision indoor positioning of heterogeneous equipment in self-adaption mode in use field |
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 |