CN108805039A - The Modulation Identification method of combination entropy and pre-training CNN extraction time-frequency image features - Google Patents
The Modulation Identification method of combination entropy and pre-training CNN extraction time-frequency image features Download PDFInfo
- Publication number
- CN108805039A CN108805039A CN201810506714.8A CN201810506714A CN108805039A CN 108805039 A CN108805039 A CN 108805039A CN 201810506714 A CN201810506714 A CN 201810506714A CN 108805039 A CN108805039 A CN 108805039A
- Authority
- CN
- China
- Prior art keywords
- time
- frequency
- image
- radar signal
- frequency image
- 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.)
- Pending
Links
- 238000012549 training Methods 0.000 title claims abstract description 38
- 238000000605 extraction Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 25
- 238000013508 migration Methods 0.000 claims abstract description 16
- 230000005012 migration Effects 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 230000009466 transformation Effects 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 20
- 239000002245 particle Substances 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 10
- 238000005314 correlation function Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000000717 retained effect Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims 2
- 239000004615 ingredient Substances 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 claims 1
- 230000017105 transposition Effects 0.000 claims 1
- 239000000284 extract Substances 0.000 abstract description 10
- 230000005855 radiation Effects 0.000 abstract description 4
- 238000012706 support-vector machine Methods 0.000 description 25
- 238000000513 principal component analysis Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
本发明属于雷达辐射源信号调制识别技术领域,具体涉及联合熵与预训练CNN提取时频图像特征的调制识别方法。首先将待识别的9类雷达信号集进行时频变换得到时频图像;然后基于MatConvNet官网提供的预训练卷积神经网络模型imagenet‑vgg‑verydeep‑19,由其Input输入层至fc6全连接层构成FT‑VGGNet‑fc6特征迁移提取模块;接着将调整后图像送入特征迁移提取模块,输出雷达信号时频图像特征;再对调整后图像进行灰度化,人工提取处理后图像的Renyi熵;接下来按照一定比例划分训练集与测试集,并选取训练集对SVM分类器进行训练;最后,利用训练后的SVM分类器对时频图像的训练集进行识别,利用多信噪比下9类雷达信号组成的数据集验证FT‑VGGNET‑fc6‑SVM分类器的识别率。
The invention belongs to the technical field of radar radiation source signal modulation recognition, and in particular relates to a modulation recognition method for extracting time-frequency image features by combining entropy and pre-trained CNN. Firstly, time-frequency transformation is performed on the 9 types of radar signal sets to be identified to obtain a time-frequency image; then, based on the pre-trained convolutional neural network model imagenet‑vgg‑verydeep‑19 provided by MatConvNet official website, the input layer is connected to the fc6 fully connected layer Constitute the FT-VGGNet-fc6 feature migration extraction module; then send the adjusted image into the feature migration extraction module, and output the radar signal time-frequency image features; then grayscale the adjusted image, and manually extract the Renyi entropy of the processed image; Next, divide the training set and test set according to a certain ratio, and select the training set to train the SVM classifier; finally, use the trained SVM classifier to identify the training set of time-frequency images, and use the multi-signal-to-noise ratio under 9 categories A dataset composed of radar signals validates the recognition rate of the FT‑VGGNET‑fc6‑SVM classifier.
Description
技术领域technical field
本发明属于雷达辐射源信号调制识别技术领域,具体涉及联合熵与预训练CNN提取时频图像特征的调制识别方法。The invention belongs to the technical field of radar radiation source signal modulation recognition, and in particular relates to a modulation recognition method for extracting time-frequency image features by combining entropy and pre-trained CNN.
背景技术Background technique
雷达辐射源信号调制识别是电子对抗及电子侦察中的重要环节,在电子战中具有十分重要的地位和作用。应用较普遍的雷达辐射源信号调制识别方法有基于五种参数的信号调制识别方法、基于时频图像的脉内调制识别方法和基于CNN的信号调制识别方法。Radar emitter signal modulation identification is an important link in electronic countermeasures and electronic reconnaissance, and plays a very important role in electronic warfare. The commonly used radar radiation source signal modulation recognition methods include the signal modulation recognition method based on five parameters, the intrapulse modulation recognition method based on time-frequency images, and the signal modulation recognition method based on CNN.
传统的基于五种参数(载频、脉冲到达时间、脉冲幅度、脉冲宽度和脉冲到达方向)的调制识别方法在经过多次测量后可获得脉冲的其他特征参数,但是没有考虑新体制雷达的脉内调制特性,不能实现有效识别。同时,此方法过多依赖数据库中原有信息,对库中不存在的雷达不能进行识别且不能自学习,因此在新体制雷达面前收效甚微。The traditional modulation recognition method based on five parameters (carrier frequency, pulse arrival time, pulse amplitude, pulse width, and pulse arrival direction) can obtain other characteristic parameters of the pulse after multiple measurements, but it does not consider the pulse of the new system radar. Due to the internal modulation characteristics, effective identification cannot be realized. At the same time, this method relies too much on the original information in the database, and cannot identify radars that do not exist in the database and cannot self-learn, so it has little effect in front of new system radars.
基于时频图像的脉内调制识别方法是应用较为广泛的,它可以将雷达信号通过时频分布转换为时频图像,对图像预处理后提取特征,在其后端接入支持向量机(SVM)分类器,即使在低信噪比下也能获得较为可观的识别率。但是此方法需要人工提取图像特征,人工提取特征速度慢。此外,若人工提取特征信息不当必将导致识别出现偏差,最终导致其识别率低。The intra-pulse modulation recognition method based on time-frequency images is widely used. It can convert radar signals into time-frequency images through time-frequency distribution, extract features after image preprocessing, and access support vector machine (SVM) at its back end. ) classifier, even at a low signal-to-noise ratio can obtain a considerable recognition rate. However, this method requires manual extraction of image features, and the speed of manual feature extraction is slow. In addition, improper manual extraction of feature information will inevitably lead to deviations in recognition, which will eventually lead to a low recognition rate.
相比于上述两种方法,基于CNN的信号调制识别方法在对雷达辐射源信号进行调制识别时,CNN可以自动完成时频图像特征的提取,实现了特征提取的高度自动化。但是利用CNN提取特征后输出特征量过多,出现冗余信息会导致系统的有效性有所降低,且其提取的特征在低信噪比条件下识别效果差,相应系统抗噪能力弱。同时,在面对小样本数据时,CNN全连接层间神经单元数量陡降会导致系统识别率整体下降。Compared with the above two methods, the CNN-based signal modulation recognition method can automatically complete the extraction of time-frequency image features when the signal modulation recognition method is used to recognize the radar radiation source signal, and realize a high degree of automation of feature extraction. However, after using CNN to extract features, there are too many output features, and redundant information will reduce the effectiveness of the system, and the extracted features have poor recognition effect under low signal-to-noise ratio conditions, and the corresponding system has weak anti-noise ability. At the same time, when faced with small sample data, the sharp drop in the number of neural units between fully connected layers of CNN will lead to an overall decline in the system's recognition rate.
发明内容Contents of the invention
本发明的目的是提出一种联合熵与预训练CNN提取时频图像特征的调制识别方法,利用CNN自动提取图像特征来实现提取特征自动化,应用主成分分析(PCA)对输出特征降维提高系统有效性,将降维后特征结合人工提取的Renyi熵来提高系统低信噪比条件下的识别率,且应用SVM解决深层网络小样本训练精度不高的问题,最终实现对雷达信号的精确快速识别。The purpose of the present invention is to propose a modulation recognition method that combines entropy and pre-trained CNN to extract time-frequency image features, utilizes CNN to automatically extract image features to realize automatic feature extraction, and applies principal component analysis (PCA) to reduce the output feature dimension and improve the system Effectiveness, combining the features after dimensionality reduction with the artificially extracted Renyi entropy to improve the recognition rate of the system under the condition of low signal-to-noise ratio, and applying SVM to solve the problem of low training accuracy of small samples of deep networks, and finally realize accurate and fast detection of radar signals identify.
本发明的目的是这样实现的:The purpose of the present invention is achieved like this:
联合熵与预训练CNN提取时频图像特征的调制识别方法,其特征在于,包括以下步骤:Joint entropy and pre-training CNN extract the modulation recognition method of time-frequency image feature, it is characterized in that, comprises the following steps:
步骤一 依据九类雷达信号参数,产生由CW、LFM、BPSK、COSTAS、FRANK、P1、P2、P3、P4组成的雷达信号集;所述的九类雷达信号参数包括:采样频率、采样点数、CW调制方式载频、巴克码、带宽、频率序列、起始频率、P3和P4调制方式产生的载频以及FRANK、P1、P2、调制方式产生的载频;Step 1 generates a radar signal set composed of CW, LFM, BPSK, COSTAS, FRANK, P1, P2, P3, and P4 according to nine types of radar signal parameters; the nine types of radar signal parameters include: sampling frequency, number of sampling points, CW modulation carrier frequency, Barker code, bandwidth, frequency sequence, starting frequency, carrier frequency generated by P3 and P4 modulation methods, and carrier frequencies generated by FRANK, P1, P2, and modulation methods;
步骤二 对雷达信号进行时频分析,应用CWD将待识别的雷达信号集进行时频变换得到时频图像;对应CWD公式如下:Step 2 Carry out time-frequency analysis on the radar signal, and apply CWD to perform time-frequency transformation on the radar signal set to be identified to obtain a time-frequency image; the corresponding CWD formula is as follows:
时变的局部相关函数可通过对相关函数作滑窗处理得到:The time-varying local correlation function can be obtained by performing sliding window processing on the correlation function:
当窗函数取时间冲击函数,不加限制,而在时域取瞬时值:When the window function takes the time impact function, no restriction is imposed, and the instantaneous value is taken in the time domain:
对时变局部相关函数作Fourier变换,即可得到Wigner Ville分布(WVD):The Wigner Ville distribution (WVD) can be obtained by Fourier transforming the time-varying local correlation function:
WVD可通过添加核函数得到CWD:WVD can be added by adding kernel function Get CWD:
步骤三 预训练卷积神经网络模型选用MatConvNet官网提供的imagenet-vgg-verydeep-19,将图片转换为224×224×3大小的图像;使imagenet-vgg-verydeep-19网络参数保持不变,由其Input输入层至fc6全连接层构成FT-VGGNet-fc6特征迁移提取模块;Step 3 The pre-training convolutional neural network model uses imagenet-vgg-verydeep-19 provided by the official website of MatConvNet, and converts the image into a 224×224×3 image; keep the network parameters of imagenet-vgg-verydeep-19 unchanged, by Its Input input layer to fc6 fully connected layer constitutes the FT-VGGNet-fc6 feature migration extraction module;
步骤四 将步骤三调整后的图像集送入特征迁移提取模块,产生雷达信号时频图像特征,使用保留至fc6全连接层的FT-VGGNet-fc6特征迁移提取模块可得8×512个雷达信号时频图像特征;Step 4 Send the image set adjusted in step 3 to the feature migration extraction module to generate radar signal time-frequency image features, and use the FT-VGGNet-fc6 feature migration extraction module retained to the fc6 fully connected layer to obtain 8×512 radar signals Time-frequency image features;
步骤五 FT-VGGNet-fc6特征迁移提取模块输出的特征过多,会有冗余信息出现导致训练速度和系统有效性下降,用PCA降维保留具有显著区分度的95个特征;Step 5. The FT-VGGNet-fc6 feature migration and extraction module outputs too many features, and redundant information will appear, resulting in a decrease in training speed and system effectiveness. Use PCA dimensionality reduction to retain 95 features with significant discrimination;
PCA将时频图像作为原始样本构成一个数据矩阵:PCA uses the time-frequency image as the original sample to form a data matrix:
其协方差矩阵为R=XXT,可对该协方差矩阵作特征值分解:Its covariance matrix is R=XX T , and the eigenvalue decomposition of the covariance matrix can be performed:
RM×M=U∧UT R M×M =U∧U T
式中,T表示转置,∧为协方差矩阵的特征值对角阵,U为相应的特征矩阵,对时频图像作如下变换:In the formula, T represents the transpose, ∧ is the eigenvalue diagonal matrix of the covariance matrix, U is the corresponding eigenmatrix, and the time-frequency image is transformed as follows:
PM×N=UTX=[p1,p2,…,pM]T P M×N =U T X=[p 1 ,p 2 ,…,p M ] T
式中,P为时频图像二值矩阵的主成分,p1是第一主成分,pj为第j主成分,选取前k个主成分,构成时频图像的特征矩阵;In the formula, P is the principal component of the time-frequency image binary matrix, p 1 is the first principal component, p j is the jth principal component, and the first k principal components are selected to form the feature matrix of the time-frequency image;
步骤六 对调整后的时频图像进行图像灰度化,三分量为R、G和B的彩色图像像素对应该点的亮度可用灰度化公式计算为:Step 6 Perform image grayscale on the adjusted time-frequency image, and the brightness of the color image pixel corresponding to the point with three components of R, G, and B can be calculated by the grayscale formula as follows:
I=0.3B+0.59G+0.11RI=0.3B+0.59G+0.11R
步骤七 提取灰度图像中能提高系统识别率尤其低信噪比条件下识别率的Renyi熵,并使之与降维后的95个特征共同归一化组合构成100个新的雷达信号时频图像特征;时频图像的Renyi熵表示为:Step 7 Extract the Renyi entropy in the grayscale image that can improve the recognition rate of the system, especially under the condition of low signal-to-noise ratio, and make it normalized and combined with the 95 features after dimensionality reduction to form 100 new radar signal time-frequency Image features; the Renyi entropy of the time-frequency image is expressed as:
式中,Pα(t,f)表示信号的时频分布;对于Renyi熵阶数α的选取,不考虑非整数阶α产生复数的熵值的情况,选取阶数为3、5、7、9、11的Renyi熵作为信号的识别特征;In the formula, P α (t,f) represents the time-frequency distribution of the signal; for the selection of the Renyi entropy order α, regardless of the case that the non-integer order α produces complex entropy values, the selected order is 3, 5, 7, The Renyi entropy of 9 and 11 is used as the identification feature of the signal;
步骤八 针对九种雷达信号,选取每类雷达信号在信噪比为0dB时时频图像各300张,将雷达信号时频图像特征按7:3的比例随机分为训练集和测试集;Step 8: For nine kinds of radar signals, select 300 time-frequency images for each type of radar signal when the signal-to-noise ratio is 0dB, and randomly divide the time-frequency image features of radar signals into a training set and a test set in a ratio of 7:3;
步骤九 划分训练集与测试集,将粒子群算法(PSO)与人工蜂群算法(ABC)结合,联合应用两算法计算适应值,每独立计算一次比较取最优,直到到达最大迭代次数取最优值,实现两算法联合对SVM参数寻优,并选取训练集对SVM分类器进行训练;Step 9 Divide the training set and the test set, combine the particle swarm optimization algorithm (PSO) and the artificial bee colony algorithm (ABC), and jointly apply the two algorithms to calculate the fitness value. Each independent calculation is compared and the best is taken until the maximum number of iterations is reached. The optimal value realizes the joint optimization of the SVM parameters by the two algorithms, and selects the training set to train the SVM classifier;
粒子群算法PSO粒子的搜索行为受到群内其他粒子的搜索行为的影响而易陷入局部最优解,而人工蜂群算法ABC局部搜索能力较弱且收敛速度比较慢;ABC算法能弥补PSO算法陷入局部解,两者的结合提高PSO算法的寻优能力,相关公式如下:The search behavior of PSO particles in the particle swarm algorithm is affected by the search behavior of other particles in the group, and it is easy to fall into the local optimal solution, while the artificial bee colony algorithm ABC has weak local search ability and slow convergence speed; Local solution, the combination of the two improves the optimization ability of the PSO algorithm, and the related formula is as follows:
粒子群中粒子位置及速度的更新为:The update of the particle position and velocity in the particle swarm is:
人工蜂群算法中搜索方程为:The search equation in artificial bee colony algorithm is:
vij=xij+φij(xij-xkj)v ij =x ij +φ ij (x ij -x kj )
首先要将种群规模、PSO速度范围、ABC蜜源数及参数、ABC算法和PSO算法的(C,σ)及初始适应值进行初始化;然后划分为2个独立子种群并联合应用ABC算法和PSO算法计算适应值,每独立计算一次比较取最优;最后将两者达到最大迭代次数时的最优适应值作为SVM最优参数,实现应用两个算法的联合对SVM的参数寻优;First, the population size, PSO speed range, ABC nectar source number and parameters, (C, σ) and initial fitness value of ABC algorithm and PSO algorithm should be initialized; then divided into two independent subpopulations and jointly applied ABC algorithm and PSO algorithm Calculate the fitness value, and take the best for each independent calculation; finally, the optimal fitness value when the two reach the maximum number of iterations is used as the optimal parameter of SVM, and realize the joint optimization of the parameters of SVM by applying the two algorithms;
将训练集特征结合相应类别标签输入上述SVM参数寻优算法进行交叉验证,确定SVM的σ和C,根据最佳参数使用训练集对SVM进行训练;Input the features of the training set and the corresponding category labels into the above SVM parameter optimization algorithm for cross-validation, determine the σ and C of the SVM, and use the training set to train the SVM according to the best parameters;
步骤十:选取信噪比为-3~8dB情况下的9类雷达信号时频图像共32400张图片,其中,每类雷达信号单一信噪比下的时频图像各300张;从数据集的每类雷达信号单一信噪比下随机选210张,共22680张作为训练集,数据集每类雷达信号单一信噪比下剩余的90张,共9720张作为测试集;利用训练后的SVM分类器对时频图像的训练集进行识别,并验证FT-VGGNET-fc6-SVM分类器的识别率。Step 10: Select a total of 32,400 time-frequency images of 9 types of radar signals with a signal-to-noise ratio of -3 to 8dB, among which, 300 time-frequency images of each type of radar signal with a single signal-to-noise ratio; Randomly select 210 images of each type of radar signal with a single signal-to-noise ratio, a total of 22,680 images as a training set, and the remaining 90 images of each type of radar signal with a single signal-to-noise ratio, a total of 9,720 images are used as a test set; use the trained SVM classification The machine recognizes the training set of time-frequency images, and verifies the recognition rate of the FT-VGGNET-fc6-SVM classifier.
与现有技术相比,本发明的优点在于:Compared with the prior art, the present invention has the advantages of:
1、提出了将Renyi熵与CNN提取时频图像特征联合,接入SVM并结合迁移学习理论对雷达信号进行调制识别,克服了CNN与SVM各自的局限性,相较于目前识别算法其识别速度更快、识别率更高(尤其低信噪比下)、有效性更好以及识别系统鲁棒性更高;1. It is proposed to combine Renyi entropy with CNN to extract time-frequency image features, access SVM and combine transfer learning theory to modulate and recognize radar signals, which overcomes the respective limitations of CNN and SVM. Compared with the current recognition algorithm, its recognition speed Faster, higher recognition rate (especially at low signal-to-noise ratio), better effectiveness and higher robustness of the recognition system;
2、CNN作为深层网络能获取更具代表性的信息,从而使调制识别特征更加全面有效,应用CNN自动提取图像特征,解决了人工提取特征速度慢和提取特征不全面的问题,且能够提高系统稳定性;2. As a deep network, CNN can obtain more representative information, so that the modulation recognition features are more comprehensive and effective. The application of CNN to automatically extract image features solves the problems of slow and incomplete extraction of features manually, and can improve the performance of the system. stability;
3、图像输入构建的FT-VGGNet-fc6特征迁移模块,CNN提取输出特征量级大,应用PCA降维可以有效地找出最主要的95个特征,去除冗余及无效信息,使识别系统的有效性远远超越单纯应用CNN调制识别的系统;3. The FT-VGGNet-fc6 feature migration module constructed by image input, CNN extracts large-scale output features, and the application of PCA dimensionality reduction can effectively find out the most important 95 features, remove redundant and invalid information, and make the recognition system more efficient. The effectiveness far exceeds the system that simply applies CNN modulation recognition;
4、Renyi熵具有熵特征公有的强抗噪能力,尤其在低信噪比下识别率高于基于其他特征所得识别率,所以在CNN提取特征降维后再人工提取预处理图像中Renyi熵,共同归一化使两者结合会提高识别系统的抗噪能力;4. Renyi entropy has the strong anti-noise ability common to entropy features, especially at low signal-to-noise ratios, the recognition rate is higher than that based on other features. Therefore, Renyi entropy in preprocessed images is manually extracted after CNN extracts feature dimensionality reduction. Co-normalization makes the combination of the two improve the noise immunity of the recognition system;
5、利用SVM需要非常小量的训练样本就可以得到类别模式的特点,有效避免了卷积神经网络由于样本类别数过少导致全连接层间神经单元数量陡降的问题,且应用SVM能使系统泛化性能与鲁棒性得到有效提升;5. Using SVM requires a very small amount of training samples to obtain the characteristics of the category pattern, which effectively avoids the problem of a steep drop in the number of neural units between fully connected layers of the convolutional neural network due to too few sample categories, and the application of SVM can make The generalization performance and robustness of the system are effectively improved;
6、设置好的FT-VGGNET-fc6-SVM在面对小样本时对SVM分类器训练即可应用,而面对大量数据时可固定特征抽取参数进行特征迁移,使得雷达信号数据集可以利用大型数据库训练整个网络,以此得到更有区分度和鲁棒性更高的特征。6. The set FT-VGGNET-fc6-SVM can be applied to the SVM classifier training when facing a small sample, and when facing a large amount of data, the feature extraction parameters can be fixed for feature migration, so that the radar signal data set can use large The database trains the entire network to obtain more discriminative and robust features.
附图说明Description of drawings
图1是本发明涉及的imagenet-vgg-verydeep-19网络结构图;Fig. 1 is the imagenet-vgg-verydeep-19 network structural diagram that the present invention relates to;
图2是本发明联合熵与预训练CNN提取时频图像特征的调制识别流程图;Fig. 2 is the modulation recognition flow chart of joint entropy and pre-training CNN extraction time-frequency image feature of the present invention;
图3是本发明的FT-VGGNET-fc6-SVM分类器的测试结果图。Fig. 3 is a test result graph of the FT-VGGNET-fc6-SVM classifier of the present invention.
具体实施方式Detailed ways
下面结合附图对本发明做进一步描述:The present invention will be further described below in conjunction with accompanying drawing:
首先将待识别的9类雷达信号集进行Choi-Williams分布(CWD)时频变换得到时频图像;然后基于MatConvNet官网提供的预训练卷积神经网络模型imagenet-vgg-verydeep-19,将时频图像大小调整至224×224×3,使预训练网络模型的参数保持不变,由其Input输入层至fc6全连接层构成FT-VGGNet-fc6特征迁移提取模块;接着将调整后图像送入特征迁移提取模块,输出雷达信号时频图像特征,应用PCA对特征降维至95个特征;再对调整后图像进行灰度化,人工提取处理后图像的Renyi熵,将降维特征与Renyi熵共同归一化后组合构成新的雷达信号时频图像特征;接下来按照一定比例划分训练集与测试集,将粒子群算法(PSO)与人工蜂群算法(ABC)结合,联合应用两算法计算适应值,每独立计算一次比较取最优,直到到达最大迭代次数取最优值,实现两算法联合对SVM参数寻优,并选取训练集对SVM分类器进行训练;最后,利用训练后的SVM分类器对时频图像的训练集进行识别,利用多信噪比下9类雷达信号组成的数据集验证FT-VGGNET-fc6-SVM分类器的识别率。First, the Choi-Williams distribution (CWD) time-frequency transformation is performed on the 9 types of radar signal sets to be identified to obtain a time-frequency image; then based on the pre-trained convolutional neural network model imagenet-vgg-verydeep-19 provided by MatConvNet official website, the time-frequency The image size is adjusted to 224×224×3, so that the parameters of the pre-trained network model remain unchanged, and the FT-VGGNet-fc6 feature migration extraction module is composed of its Input input layer to the fc6 fully connected layer; then the adjusted image is sent to the feature The migration extraction module outputs the time-frequency image features of the radar signal, and applies PCA to reduce the feature dimension to 95 features; then grayscales the adjusted image, manually extracts the Renyi entropy of the processed image, and combines the dimensionality reduction feature with the Renyi entropy After normalization, a new radar signal time-frequency image feature is formed; next, the training set and the test set are divided according to a certain ratio, and the particle swarm optimization algorithm (PSO) and the artificial bee colony algorithm (ABC) are combined, and the two algorithms are jointly applied to calculate the adaptive Value, each independent calculation is compared to take the optimal value, until the maximum number of iterations is reached to take the optimal value, realize the joint optimization of the SVM parameters by the two algorithms, and select the training set to train the SVM classifier; finally, use the trained SVM to classify The FT-VGGNET-fc6-SVM classifier is used to identify the training set of time-frequency images, and the recognition rate of the FT-VGGNET-fc6-SVM classifier is verified by using a data set composed of 9 types of radar signals under multiple signal-to-noise ratios.
具体包括以下步骤:Specifically include the following steps:
步骤一:依据表1提供的9类雷达信号参数值,产生由CW、LFM、BPSK、COSTAS、FRANK、P1、P2、P3、P4组成的雷达信号集。Step 1: Generate a radar signal set consisting of CW, LFM, BPSK, COSTAS, FRANK, P1, P2, P3, and P4 according to the 9 types of radar signal parameter values provided in Table 1.
表1Table 1
步骤二:对雷达信号这类非平稳信号的分析处理不能单单局限于时域或频域,要对雷达信号进行时频分析,而CWD能在获得较好地时间、频率分辨率的同时有效抑制交叉项,应用CWD将待识别的雷达信号集进行时频变换得到时频图像,对应CWD公式如下:Step 2: The analysis and processing of non-stationary signals such as radar signals cannot be limited to the time domain or frequency domain only. Time-frequency analysis should be performed on radar signals, and CWD can effectively suppress while obtaining better time and frequency resolution. Intersection term, applying CWD to time-frequency transform the radar signal set to be identified to obtain a time-frequency image, the corresponding CWD formula is as follows:
时变的局部相关函数可通过对相关函数作滑窗处理得到:The time-varying local correlation function can be obtained by performing sliding window processing on the correlation function:
当窗函数取时间冲击函数,不加限制,而在时域取瞬时值:When the window function takes the time impact function, no restriction is imposed, and the instantaneous value is taken in the time domain:
对时变局部相关函数作Fourier变换,即可得到Wigner Ville分布(WVD):The Wigner Ville distribution (WVD) can be obtained by Fourier transforming the time-varying local correlation function:
WVD可通过添加核函数得到CWD:WVD can be added by adding kernel function Get CWD:
步骤三:预训练卷积神经网络模型选用MatConvNet官网提供的imagenet-vgg-verydeep-19,由于imagenet-vgg-verydeep-19模型需要输入固定大小的三原色(RGB)图像,因此需要将图片转换为224×224×3大小的图像。使imagenet-vgg-verydeep-19网络参数保持不变,由其Input输入层至fc6全连接层构成FT-VGGNet-fc6特征迁移提取模块。Step 3: The pre-training convolutional neural network model uses imagenet-vgg-verydeep-19 provided by MatConvNet official website. Since the imagenet-vgg-verydeep-19 model needs to input a fixed-size three-primary-color (RGB) image, it is necessary to convert the image to 224 ×224×3 size image. Keep the imagenet-vgg-verydeep-19 network parameters unchanged, and form the FT-VGGNet-fc6 feature migration extraction module from its Input input layer to the fc6 fully connected layer.
步骤四:将步骤三调整后的图像集送入特征迁移提取模块,产生雷达信号时频图像特征,使用保留至fc6全连接层的FT-VGGNet-fc6特征迁移提取模块可得Step 4: Send the image set adjusted in Step 3 into the feature migration extraction module to generate radar signal time-frequency image features, and use the FT-VGGNet-fc6 feature migration extraction module reserved to the fc6 fully connected layer to obtain
8×512个雷达信号时频图像特征。8×512 radar signal time-frequency image features.
步骤五:FT-VGGNet-fc6特征迁移提取模块输出的特征过多,会有冗余信息出现导致训练速度和系统有效性下降,可用PCA降维保留具有显著区分度的95个特征。具体而言,PCA将时频图像作为原始样本构成一个数据矩阵:Step 5: The FT-VGGNet-fc6 feature migration and extraction module outputs too many features, and redundant information will appear, resulting in a decrease in training speed and system effectiveness. PCA dimensionality reduction can be used to retain 95 features with significant discrimination. Specifically, PCA takes the time-frequency image as the original sample to form a data matrix:
其协方差矩阵为R=XXT,可对该协方差矩阵作特征值分解:Its covariance matrix is R=XX T , and the eigenvalue decomposition of the covariance matrix can be performed:
RM×M=U∧UT (6)R M × M = U∧U T (6)
式中,T表示转置,∧为协方差矩阵的特征值对角阵,U为相应的特征矩阵,对时频图像作如下变换:In the formula, T represents the transpose, ∧ is the eigenvalue diagonal matrix of the covariance matrix, U is the corresponding eigenmatrix, and the time-frequency image is transformed as follows:
PM×N=UTX=[p1,p2,…,pM]T (7)P M×N =U T X=[p 1 ,p 2 ,…,p M ] T (7)
式中,P为时频图像二值矩阵的主成分,p1是第一主成分,pj为第j主成分,选取前k个主成分,构成时频图像的特征矩阵。In the formula, P is the principal component of the time-frequency image binary matrix, p 1 is the first principal component, p j is the jth principal component, and the first k principal components are selected to form the feature matrix of the time-frequency image.
步骤六:对调整后的时频图像进行图像灰度化,三分量为R、G和B的彩色图像像素对应该点的亮度可用灰度化公式计算为:Step 6: Perform image grayscale on the adjusted time-frequency image, and the brightness of the color image pixel corresponding to the point with three components of R, G, and B can be calculated by the grayscale formula as follows:
I=0.3B+0.59G+0.11R (8)I=0.3B+0.59G+0.11R (8)
步骤七:提取灰度图像中能提高系统识别率尤其低信噪比条件下识别率的Renyi熵,并使之与降维后的95个特征共同归一化组合构成100个新的雷达信号时频图像特征。时频图像的Renyi熵表示为:Step 7: Extract the Renyi entropy in the grayscale image that can improve the recognition rate of the system, especially under the condition of low signal-to-noise ratio, and make it normalized and combined with the 95 features after dimensionality reduction to form 100 new radar signals frequency image features. The Renyi entropy of the time-frequency image is expressed as:
式中,Pα(t,f)表示信号的时频分布。对于Renyi熵阶数α的选取,本实施例不考虑非整数阶α产生复数的熵值的情况,主要选取阶数为3、5、7、9、11的Renyi熵作为信号的识别特征。In the formula, P α (t, f) represents the time-frequency distribution of the signal. For the selection of the Renyi entropy order α, this embodiment does not consider the case that the non-integer order α produces complex entropy values, and mainly selects the Renyi entropy with orders 3, 5, 7, 9, and 11 as the identification feature of the signal.
步骤八:针对9种雷达信号,选取每类雷达信号在信噪比为0dB时时频图像各300张,将雷达信号时频图像特征按7:3的比例随机分为训练集和测试集。Step 8: For 9 kinds of radar signals, select 300 time-frequency images for each type of radar signal when the signal-to-noise ratio is 0dB, and randomly divide the time-frequency image features of the radar signals into a training set and a test set in a ratio of 7:3.
步骤九:粒子群算法(PSO)粒子的搜索行为受到群内其他粒子的搜索行为的影响而易陷入局部最优解,而人工蜂群算法(ABC)局部搜索能力较弱且收敛速度比较慢。ABC算法能弥补PSO算法陷入局部解,两者的结合可以提高PSO算法的寻优能力,相关公式如下:Step 9: Particle swarm optimization (PSO) particle search behavior is affected by the search behavior of other particles in the group and easily falls into a local optimal solution, while artificial bee colony algorithm (ABC) has weak local search ability and slow convergence speed. The ABC algorithm can make up for the PSO algorithm falling into a local solution. The combination of the two can improve the optimization ability of the PSO algorithm. The related formula is as follows:
粒子群中粒子位置及速度的更新为:The update of the particle position and velocity in the particle swarm is:
人工蜂群算法中搜索方程为:The search equation in artificial bee colony algorithm is:
vij=xij+φij(xij-xkj) (11)v ij =x ij +φ ij (x ij -x kj ) (11)
首先要将种群规模、PSO速度范围、ABC蜜源数及参数、ABC算法和PSO算法的(C,σ)及初始适应值进行初始化;然后划分为2个独立子种群并联合应用ABC算法和PSO算法计算适应值,每独立计算一次比较取最优;最后将两者达到最大迭代次数时的最优适应值作为SVM最优参数,实现应用两个算法的联合对SVM的参数寻优。First, the population size, PSO speed range, ABC nectar source number and parameters, (C, σ) and initial fitness value of ABC algorithm and PSO algorithm should be initialized; then divided into two independent subpopulations and jointly applied ABC algorithm and PSO algorithm The fitness value is calculated, and the optimal value is selected for each independent calculation; finally, the optimal fitness value when the two reach the maximum number of iterations is used as the optimal parameter of the SVM, and the joint optimization of the SVM parameters is realized by applying the two algorithms.
将训练集特征结合相应类别标签输入上述SVM参数寻优算法进行交叉验证,确定SVM的σ和C,根据最佳参数使用训练集对SVM进行训练。The characteristics of the training set combined with the corresponding category labels are input into the above SVM parameter optimization algorithm for cross-validation, the σ and C of the SVM are determined, and the SVM is trained using the training set according to the best parameters.
步骤十:选取信噪比为-3~8dB情况下的9类雷达信号时频图像共32400张图片,其中,每类雷达信号单一信噪比下的时频图像各300张。从数据集的每类雷达信号单一信噪比下随机选210张,共22680张作为训练集,数据集每类雷达信号单一信噪比下剩余的90张,共9720张作为测试集。利用训练后的SVM分类器对时频图像的训练集进行识别,并验证FT-VGGNET-fc6-SVM分类器的识别率。Step 10: Select a total of 32,400 time-frequency images of 9 types of radar signals with a signal-to-noise ratio of -3 to 8dB, among which, 300 time-frequency images of each type of radar signal with a single signal-to-noise ratio. Randomly select 210 images from each type of radar signal with a single signal-to-noise ratio in the data set, a total of 22,680 images as a training set, and the remaining 90 images with a single signal-to-noise ratio for each type of radar signal in the data set, a total of 9,720 images as a test set. Use the trained SVM classifier to recognize the training set of time-frequency images, and verify the recognition rate of the FT-VGGNET-fc6-SVM classifier.
图3给出FT-VGGNet-fc6-SVM分类器的测试结果,其识别率随着信噪比的增加呈上升趋势,到5dB之后趋于平滑。在-3dB取得了87%的识别率,之后呈稳步上升趋势,并在7dB时达到99%以上,表明了本发明对雷达辐射源信号调制识别率(尤其低信噪比下)较高。此外,本发明测试稳定,识别率未出现大幅度的波动,表明了本发明稳定性与鲁棒性较好,具有很好的实用性。Figure 3 shows the test results of the FT-VGGNet-fc6-SVM classifier, and its recognition rate increases with the increase of the signal-to-noise ratio, and tends to be smooth after 5dB. A recognition rate of 87% was obtained at -3dB, and then it showed a steady upward trend, and reached more than 99% at 7dB, indicating that the present invention has a higher recognition rate (especially at low signal-to-noise ratio) for radar emitter signal modulation. In addition, the test of the present invention is stable, and the recognition rate does not fluctuate greatly, which shows that the present invention has good stability and robustness, and has good practicability.
本发明提供了一种联合熵与预训练CNN提取时频图像特征的调制识别方法,具体实现该技术方案的方法和途径很多,以上所述仅是本发明的优选实施方式。本实施例中未明确的各组成部分均可用现有技术加以实现。The present invention provides a modulation recognition method that combines entropy and pre-trained CNN to extract time-frequency image features. There are many methods and approaches to realize this technical solution, and the above is only a preferred embodiment of the present invention. All components that are not specified in this embodiment can be realized by existing technologies.
Claims (1)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810340339 | 2018-04-17 | ||
CN2018103403394 | 2018-04-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108805039A true CN108805039A (en) | 2018-11-13 |
Family
ID=64092840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810506714.8A Pending CN108805039A (en) | 2018-04-17 | 2018-05-24 | The Modulation Identification method of combination entropy and pre-training CNN extraction time-frequency image features |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108805039A (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109597043A (en) * | 2018-11-16 | 2019-04-09 | 江苏科技大学 | Radar Signal Recognition method based on quantum particle swarm convolutional neural networks |
CN109871757A (en) * | 2019-01-11 | 2019-06-11 | 中国船舶重工集团公司第七二四研究所 | A kind of radar signal intra-pulse modulation kind identification method based on joint time-frequency feature |
CN110008900A (en) * | 2019-04-02 | 2019-07-12 | 北京市遥感信息研究所 | A Region-to-target Candidate Target Extraction Method for Visible Light Remote Sensing Images |
CN110008899A (en) * | 2019-04-02 | 2019-07-12 | 北京市遥感信息研究所 | A method for candidate target extraction and classification of visible light remote sensing images |
CN110048980A (en) * | 2019-04-19 | 2019-07-23 | 中国电子科技集团公司第三十六研究所 | A kind of blind demodulation method of digital communication and device |
CN110243885A (en) * | 2019-07-09 | 2019-09-17 | 东营智图数据科技有限公司 | A kind of low yield gas well mouth of oil well hydrated comples ion method based on time-frequency characteristics |
CN110417694A (en) * | 2019-06-07 | 2019-11-05 | 吉林大学 | A communication signal modulation method identification method |
CN110532932A (en) * | 2019-08-26 | 2019-12-03 | 哈尔滨工程大学 | A kind of multi -components radar emitter signal intra-pulse modulation mode recognition methods |
CN110632132A (en) * | 2019-07-09 | 2019-12-31 | 东营智图数据科技有限公司 | High-yield gas-oil well wellhead liquid water content prediction method based on multi-sensor measurement and deep convolutional neural network |
CN112084906A (en) * | 2020-08-27 | 2020-12-15 | 上海朱光亚战略科技研究院 | Radar pulse signal classification method and device, computer equipment and storage medium |
CN112115821A (en) * | 2020-09-04 | 2020-12-22 | 西北工业大学 | A Multi-Signal Intelligent Modulation Pattern Recognition Method Based on Wavelet Approximation Coefficient Entropy |
CN112308008A (en) * | 2020-11-12 | 2021-02-02 | 电子科技大学 | Radar radiation source individual identification method based on working mode open set of transfer learning |
CN112733811A (en) * | 2020-09-23 | 2021-04-30 | 青岛科技大学 | Underwater sound signal modulation mode inter-class identification method based on improved dense neural network |
CN112801003A (en) * | 2021-02-05 | 2021-05-14 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle radiation source modulation pattern recognition method and device |
CN112950922A (en) * | 2021-01-26 | 2021-06-11 | 浙江得图网络有限公司 | Fixed-point returning method for sharing electric vehicle |
CN113076925A (en) * | 2021-04-23 | 2021-07-06 | 扬州大学 | M-QAM signal modulation mode identification method based on CNN and ELM |
CN113376608A (en) * | 2021-05-27 | 2021-09-10 | 哈尔滨工程大学 | Convolutional neural network-based radar radiation source structure identification method |
CN114330441A (en) * | 2021-12-28 | 2022-04-12 | 厦门大学 | A method and system for underwater acoustic JANUS signal recognition based on time-spectrum and transfer learning |
US11341598B2 (en) | 2020-06-05 | 2022-05-24 | International Business Machines Corporation | Interpretation maps with guaranteed robustness |
CN114792443A (en) * | 2022-04-25 | 2022-07-26 | 扬州大学 | Intelligent device gesture recognition control method based on image recognition |
CN115720184A (en) * | 2022-10-08 | 2023-02-28 | 西安电子科技大学 | A small-sample signal modulation type identification method based on characteristic distribution |
US11687777B2 (en) | 2020-08-27 | 2023-06-27 | International Business Machines Corporation | Certifiably robust interpretation |
CN116684233A (en) * | 2023-06-15 | 2023-09-01 | 哈尔滨工程大学 | Communication signal modulation identification method based on image significance detection |
CN116776230A (en) * | 2023-08-22 | 2023-09-19 | 北京海格神舟通信科技有限公司 | Method and system for identifying signal based on feature imprinting and feature migration |
CN117129947A (en) * | 2023-10-26 | 2023-11-28 | 成都金支点科技有限公司 | Planar transformation method radar signal identification method based on mininet |
CN119728358A (en) * | 2024-12-04 | 2025-03-28 | 中国人民解放军军事航天部队航天工程大学 | A small sample communication modulation recognition preprocessing method and system based on complex denoising network |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104809358A (en) * | 2015-05-21 | 2015-07-29 | 哈尔滨工业大学 | Radar radiation source identification method based on phase noise unintentional modulation characteristic |
CN106778610A (en) * | 2016-12-16 | 2017-05-31 | 哈尔滨工程大学 | A kind of intra-pulse modulation recognition methods based on time-frequency image feature |
CN107301432A (en) * | 2017-07-11 | 2017-10-27 | 哈尔滨工程大学 | Adaptive radiation source Modulation Identification method based on time frequency analysis |
-
2018
- 2018-05-24 CN CN201810506714.8A patent/CN108805039A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104809358A (en) * | 2015-05-21 | 2015-07-29 | 哈尔滨工业大学 | Radar radiation source identification method based on phase noise unintentional modulation characteristic |
CN106778610A (en) * | 2016-12-16 | 2017-05-31 | 哈尔滨工程大学 | A kind of intra-pulse modulation recognition methods based on time-frequency image feature |
CN107301432A (en) * | 2017-07-11 | 2017-10-27 | 哈尔滨工程大学 | Adaptive radiation source Modulation Identification method based on time frequency analysis |
Non-Patent Citations (4)
Title |
---|
FAN HU 等: ""Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery"", 《REMOTE SENS》 * |
刘康宁: ""基于时频分析的雷达信号调制方式识别技术研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
宁爱平 等: ""ABC-PSO算法优化混合核SVM参数及应用"", 《数学的实践与认识》 * |
高敬鹏 等: ""基于时频分析的自适应PCA辐射源调制识别"", 《应用科技》 * |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109597043A (en) * | 2018-11-16 | 2019-04-09 | 江苏科技大学 | Radar Signal Recognition method based on quantum particle swarm convolutional neural networks |
CN109597043B (en) * | 2018-11-16 | 2023-05-26 | 江苏科技大学 | Radar signal recognition method based on quantum particle swarm convolutional neural network |
CN109871757A (en) * | 2019-01-11 | 2019-06-11 | 中国船舶重工集团公司第七二四研究所 | A kind of radar signal intra-pulse modulation kind identification method based on joint time-frequency feature |
CN110008900B (en) * | 2019-04-02 | 2023-12-12 | 北京市遥感信息研究所 | Method for extracting candidate target from visible light remote sensing image from region to target |
CN110008900A (en) * | 2019-04-02 | 2019-07-12 | 北京市遥感信息研究所 | A Region-to-target Candidate Target Extraction Method for Visible Light Remote Sensing Images |
CN110008899A (en) * | 2019-04-02 | 2019-07-12 | 北京市遥感信息研究所 | A method for candidate target extraction and classification of visible light remote sensing images |
CN110008899B (en) * | 2019-04-02 | 2021-02-26 | 北京市遥感信息研究所 | Method for extracting and classifying candidate targets of visible light remote sensing image |
CN110048980A (en) * | 2019-04-19 | 2019-07-23 | 中国电子科技集团公司第三十六研究所 | A kind of blind demodulation method of digital communication and device |
CN110417694A (en) * | 2019-06-07 | 2019-11-05 | 吉林大学 | A communication signal modulation method identification method |
CN110632132A (en) * | 2019-07-09 | 2019-12-31 | 东营智图数据科技有限公司 | High-yield gas-oil well wellhead liquid water content prediction method based on multi-sensor measurement and deep convolutional neural network |
CN110243885A (en) * | 2019-07-09 | 2019-09-17 | 东营智图数据科技有限公司 | A kind of low yield gas well mouth of oil well hydrated comples ion method based on time-frequency characteristics |
CN110532932A (en) * | 2019-08-26 | 2019-12-03 | 哈尔滨工程大学 | A kind of multi -components radar emitter signal intra-pulse modulation mode recognition methods |
CN110532932B (en) * | 2019-08-26 | 2022-12-13 | 哈尔滨工程大学 | A method for identifying intra-pulse modulation of multi-component radar signals |
US11341598B2 (en) | 2020-06-05 | 2022-05-24 | International Business Machines Corporation | Interpretation maps with guaranteed robustness |
CN112084906A (en) * | 2020-08-27 | 2020-12-15 | 上海朱光亚战略科技研究院 | Radar pulse signal classification method and device, computer equipment and storage medium |
US11687777B2 (en) | 2020-08-27 | 2023-06-27 | International Business Machines Corporation | Certifiably robust interpretation |
CN112115821B (en) * | 2020-09-04 | 2022-03-11 | 西北工业大学 | A Multi-Signal Intelligent Modulation Pattern Recognition Method Based on Wavelet Approximation Coefficient Entropy |
CN112115821A (en) * | 2020-09-04 | 2020-12-22 | 西北工业大学 | A Multi-Signal Intelligent Modulation Pattern Recognition Method Based on Wavelet Approximation Coefficient Entropy |
CN112733811A (en) * | 2020-09-23 | 2021-04-30 | 青岛科技大学 | Underwater sound signal modulation mode inter-class identification method based on improved dense neural network |
CN112308008A (en) * | 2020-11-12 | 2021-02-02 | 电子科技大学 | Radar radiation source individual identification method based on working mode open set of transfer learning |
CN112950922A (en) * | 2021-01-26 | 2021-06-11 | 浙江得图网络有限公司 | Fixed-point returning method for sharing electric vehicle |
CN112801003B (en) * | 2021-02-05 | 2022-06-17 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle radiation source modulation pattern recognition method |
CN112801003A (en) * | 2021-02-05 | 2021-05-14 | 江苏方天电力技术有限公司 | Unmanned aerial vehicle radiation source modulation pattern recognition method and device |
CN113076925B (en) * | 2021-04-23 | 2023-09-05 | 扬州大学 | M-QAM signal modulation mode identification method based on CNN and ELM |
CN113076925A (en) * | 2021-04-23 | 2021-07-06 | 扬州大学 | M-QAM signal modulation mode identification method based on CNN and ELM |
CN113376608A (en) * | 2021-05-27 | 2021-09-10 | 哈尔滨工程大学 | Convolutional neural network-based radar radiation source structure identification method |
CN114330441A (en) * | 2021-12-28 | 2022-04-12 | 厦门大学 | A method and system for underwater acoustic JANUS signal recognition based on time-spectrum and transfer learning |
CN114330441B (en) * | 2021-12-28 | 2024-09-13 | 厦门大学 | A method and system for underwater acoustic JANUS signal recognition based on time-frequency spectrum and transfer learning |
CN114792443A (en) * | 2022-04-25 | 2022-07-26 | 扬州大学 | Intelligent device gesture recognition control method based on image recognition |
CN115720184B (en) * | 2022-10-08 | 2024-04-19 | 西安电子科技大学 | A method for identifying modulation types of small sample signals based on feature distribution |
CN115720184A (en) * | 2022-10-08 | 2023-02-28 | 西安电子科技大学 | A small-sample signal modulation type identification method based on characteristic distribution |
CN116684233A (en) * | 2023-06-15 | 2023-09-01 | 哈尔滨工程大学 | Communication signal modulation identification method based on image significance detection |
CN116684233B (en) * | 2023-06-15 | 2024-10-18 | 哈尔滨工程大学 | A communication signal modulation recognition method based on image saliency detection |
CN116776230A (en) * | 2023-08-22 | 2023-09-19 | 北京海格神舟通信科技有限公司 | Method and system for identifying signal based on feature imprinting and feature migration |
CN116776230B (en) * | 2023-08-22 | 2023-11-14 | 北京海格神舟通信科技有限公司 | Method and system for identifying signal based on feature imprinting and feature migration |
CN117129947A (en) * | 2023-10-26 | 2023-11-28 | 成都金支点科技有限公司 | Planar transformation method radar signal identification method based on mininet |
CN117129947B (en) * | 2023-10-26 | 2023-12-26 | 成都金支点科技有限公司 | Planar transformation method radar signal identification method based on mininet |
CN119728358A (en) * | 2024-12-04 | 2025-03-28 | 中国人民解放军军事航天部队航天工程大学 | A small sample communication modulation recognition preprocessing method and system based on complex denoising network |
CN119728358B (en) * | 2024-12-04 | 2025-05-23 | 中国人民解放军军事航天部队航天工程大学 | Small sample communication modulation recognition preprocessing method and system based on complex noise reduction network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108805039A (en) | The Modulation Identification method of combination entropy and pre-training CNN extraction time-frequency image features | |
CN110826630B (en) | Feature-level fusion recognition method of radar jamming signal based on deep convolutional neural network | |
Li et al. | Semisupervised human activity recognition with radar micro-Doppler signatures | |
CN107784320B (en) | Target Recognition Method of Radar One-Dimensional Range Image Based on Convolutional Support Vector Machine | |
CN109254274B (en) | A Radar Radiator Identification Method Based on Feature Fusion | |
CN112764024B (en) | Radar target identification method based on convolutional neural network and Bert | |
CN109800692B (en) | Visual SLAM loop detection method based on pre-training convolutional neural network | |
US10699192B1 (en) | Method for optimizing hyperparameters of auto-labeling device which auto-labels training images for use in deep learning network to analyze images with high precision, and optimizing device using the same | |
CN110443143A (en) | The remote sensing images scene classification method of multiple-limb convolutional neural networks fusion | |
CN110175560A (en) | A kind of radar signal intra-pulse modulation recognition methods | |
CN109902615B (en) | Multi-age-group image generation method based on countermeasure network | |
CN108416290A (en) | Radar signal feature method based on residual error deep learning | |
CN109446877A (en) | A kind of radar emitter signal Modulation Identification method of joint multidimensional characteristic migration fusion | |
CN114299398B (en) | A Small-Sample Remote Sensing Image Classification Method Based on Self-Supervised Contrastive Learning | |
CN110175551A (en) | A kind of sign Language Recognition Method | |
CN103268607B (en) | A kind of common object detection method under weak supervision condition | |
CN114529939B (en) | Pedestrian recognition method based on millimeter wave Lei Dadian cloud clustering and deep learning | |
CN113657491A (en) | Neural network design method for signal modulation type recognition | |
CN113743505A (en) | An improved SSD object detection method based on self-attention and feature fusion | |
CN108764331A (en) | Joint classification device multi signal Modulation Identification method based on Fourier Transform of Fractional Order | |
CN113420775A (en) | Image classification method under extremely small quantity of training samples based on adaptive subdomain field adaptation of non-linearity | |
CN115565019A (en) | Single-channel high-resolution SAR image ground object classification method based on deep self-supervision generation countermeasure | |
CN114897002A (en) | Intrapulse Modulation Identification Method of Low Intercept Probability Radar Signal Based on LPINet | |
CN108875532A (en) | A kind of video actions detection method based on sparse coding and length posterior probability | |
CN103456017B (en) | Image partition method based on the semi-supervised weight Kernel fuzzy clustering of subset |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181113 |