CIE Homepage  |  Join CIE  |  Login CIE  |  中文 

Collections

Electromagnetic Spectrum Intelligence+
Sort by Default Latest Most read  
Please wait a minute...
  • Select all
    |
  • Intelligent game of electromagnetic spectrum
    WU Xiao-xiao, LI Gang-qiang, ZHANG Sheng-li
    Acta Electronica Sinica. 2022, 50(6): 1370-1380. https://doi.org/10.12263/DZXB.20210841
    CSCD(2)

    Cognitive radio is a key technology to solve the problem of energy efficiency in wireless communication, and spectrum sensing is of great significance for improving the efficiency of spectrum utilization. To solve the problem that the consensus-based distributed cooperative spectrum sensing algorithm is vulnerable to malicious node data injection attacks, we propose two approaches for detecting and localizing malicious nodes based on neural networks. And a collaborative peer-to-peer machine learning protocol(Gossip Learning) is adopted to facilitate training these neural network models. We simulate the process of distributed cooperative spectrum sensing on a 9-node Manhattan network, and verify the effectiveness of the proposed approaches. Numerical results illustrate that the proposed neural network-based approaches can effectively improve the performance of detecting and localizing malicious nodes. The collaborative learning strategy can enable nodes to learn more attack characteristics, and thus make the network more robust to attacks.

  • Intelligent game of electromagnetic spectrum
    LI Qiang, ZHANG Wei, JIN Qiu-yuan, YAO Xin
    Acta Electronica Sinica. 2022, 50(6): 1344-1350. https://doi.org/10.12263/DZXB.20210932
    Abstract (723) Download PDF (1621) HTML (408)   Knowledge map   Save
    CSCD(7)

    Multifunctional radar working mode recognition is important for cognitive electronic warfare. In practical applications, due to the diversity and concealment of multifunctional radar operating modes, the intercepted pulses for different operating modes is limited. Therefore, using only limited intercepted pulse records to accurately recognize the modes of the radar is a challenging but important task for radar countermeasures. To address the above problem, this paper proposes a novel recognition method by integrating the prior knowledge with the prototype network. The core of this method is to encode and embed the prior knowledge into prototype network training to obtain better recognition performance with few training samples. The simulation results show that compared with prototype networks and SVM that do not use prior knowledge, the recognition accuracy of the prototype network with prior knowledge is increased by 2.9% and 10.5%, respectively.

  • Intelligent game of electromagnetic spectrum
    ZHANG Chun-jie, LIU Yu-chen, SI Wei-jian
    Acta Electronica Sinica. 2022, 50(6): 1351-1358. https://doi.org/10.12263/DZXB.20210934
    CSCD(3)

    To address the difficulty of deinterleaving special radars with large pulse repetition interval(PRI) range and the low accuracy of PRI estimation in complex electromagnetic environment, a radar signal deinterleaving algorithm based on PRI multi-level bin and deep forest is proposed. The algorithm utilizes the PRI multi-level bin structure for PRI transformation to improve the detection rate for special radars. The PRI boundary features of radar signals are derived from the number of pulse pairs in the multi-level bin and the PRI transform results. The PRI boundary features of special radars in different environments is mixed and the features by smoothing filters are enhanced. The deep forest is trained to predict the complete PRI range and thus to correct the central PRI estimate. Finally, based on the central value of PRI and the PRI range, the pulses are searched and extracted. Simulation experiments show that the proposed algorithm can effectively deinterleaving jittered, unilinear, bilinear, sawtooth and sinusoidal radars with large PRI range. The PRI range prediction performance is improved by 14% and the PRI estimation error is reduced by 75%.

  • Intelligent game of electromagnetic spectrum
    PENG Chuang, WANG Lun-wen, HU Wei-lin
    Acta Electronica Sinica. 2022, 50(6): 1359-1369. https://doi.org/10.12263/DZXB.20210916
    Abstract (1008) Download PDF (1137) HTML (617)   Knowledge map   Save

    To solve the problem of low efficiency of electromagnetic spectrum anomaly detection, we propose a new method of spectrum anomaly detection based on depth feature fusion which combines convolutional neural networks(CNN) and long short-term memory(LSTM) Networks. Firstly, a deep feature extraction network is constructed, which includes a multi-level CNN and a LSTM. The network can extract depth features in a hierarchical manner. Then, pooling layer, concatenate layer and other operations are used to fuse the depth features to achieve high-precision prediction of spectrum data. Finally, the mean square error between the predicted data and the real data is calculated by discriminating the spectrum anomaly. The algorithm can detect multiple kinds of abnormal states under the condition of unsupervised learning. We verified our algorithm in frequency bands of public spectrum data. The results show that our algorithm can effectively realize electromagnetic spectrum anomaly detection.

  • Intelligent game of electromagnetic spectrum
    ZHU Xu, YANG Jian, YANG Tao
    Acta Electronica Sinica. 2022, 50(6): 1331-1335. https://doi.org/10.12263/DZXB.20210820

    In this paper, a novel filtering quadrature coupler(FQC) with reconfigurable frequency and output direction is presented. It simply consists of four half-wavelength step impedance resonators(SIRs) loaded with varactors at the open ends for frequency tuning and between resonators for inter-stage coupling control. Admittance invertors with electrical and magnetic types are utilized to replace the transmission lines in conventional quadrature coupler for filtering response. By using the simple configuration, the proposed FQC can realize reconfigurable output directions without any switch component. Theoretical analysis has been given and a microstrip prototype has been designed, fabricated and measured to demonstrate the proposed technique. The measured results show that the proposed FQC can continuously cover the frequency range of 1.2~1.6 GHz at forward output direction with 90° phase difference and at backward output direction with -90° phase difference.

  • Intelligent game of electromagnetic spectrum
    YANG Liu, LI Qiang, SHAO Huai-zong
    Acta Electronica Sinica. 2022, 50(6): 1310-1318. https://doi.org/10.12263/DZXB.20210829
    Abstract (626) Download PDF (1014) HTML (332)   Knowledge map   Save

    In the increasingly complex electromagnetic spectrum environment, in order to realize the management and control of spectrum resources, it is necessary to determine whether the received signal is from the known or unknown radiation source. To tackle this problem, this paper proposes an algorithm named Open-MUSIC(MUltiple SIgnal Classification) to discriminate the known and unknown sources. The key idea of Open-MUSIC is to form the feature space from the known classes via a judiciously designed neural network, and then the feature space is decomposed into two orthogonal subspaces, namely the range subspace and the null subspace. Based on the projection ratio of the test signal's feature onto the two subspaces, we can accurately discriminate the known and the unknown radiation sources. Experiments on three datasets show that the performance of the Open-MUSIC is improved by more than 3% on electromagnetic data sets compared to other methods.

  • Intelligent game of electromagnetic spectrum
    BAO Jia-di, LI Yun-jie, ZHU Meng-tao, ZHANG Wei
    Acta Electronica Sinica. 2022, 50(6): 1291-1300. https://doi.org/10.12263/DZXB.20210830
    CSCD(1)

    Multi-function radars(MFRs) have great flexibilities in beam scheduling and complex modulation of radar work modes. It can perform multiple system tasks simultaneously in the radar timeline, which brings great challenges to electronic reconnaissance devices. Online detection of multiple MFR work mode changepoints accurately and rapidly is of great importance for identifying the behavioral intentions of a multi-function radar. This paper proposes an online detection method of MFR work mode changepoints. The proposed method takes the measurement noise, spurious pulses and lost pulses in real electromagnetic environment into consideration and can realize online changepoints detection of radar working mode under the observations contaminated by these non-ideal situations. Also, this method can estimate the modulation parameters of the work modes before and after the changepoints. Experimental results validate the effectiveness and superiority of the proposed method compared with the traditional changepoint detection methods.

  • Intelligent game of electromagnetic spectrum
    YANG Wei-chao, DU Yu, WEN Wei, HOU Shu-wei, XU Chang-zhi, ZHANG Jian-hua
    Acta Electronica Sinica. 2022, 50(6): 1336-1343. https://doi.org/10.12263/DZXB.20210882
    CSCD(2)

    Modulation recognition is one of the key technologies in satellite communication anti-interference and interference analysis. The existing on-board recognition methods have low intelligence degree and poor adaptability. In order to solve these problems, an intelligent recognition method based on multi-fractal spectrum and deep learning is proposed. Firstly, the multi-fractal spectrum characteristics of common satellite communication signals are analyzed, a multi-fractal eigendomain matrix is constructed. On this basis, the eigendomain matrix is combined with the deep learning residual network, and the structure of the residual network is optimized and improved according to the multi-scale idea, and the multi-layer autonomous detail feature extraction advantage of the improved residual network perfectly corresponds to the multi-scale feature characterization capability of the multi-fractal spectrum. Finally, the modulation of satellite communication signal is effectively recognized. The simulation results show that this method has good recognition performance, when the SNR is not lower than 1 dB, the average recognition rate is greater than 89%.

  • Intelligent game of electromagnetic spectrum
    RAO Ning, XU Hua, JIANG Lei, SONG Bai-lin, SHI Yun-hao
    Acta Electronica Sinica. 2022, 50(6): 1319-1330. https://doi.org/10.12263/DZXB.20210818
    Abstract (1146) Download PDF (1091) HTML (719)   Knowledge map   Save
    CSCD(2)

    In order to solve the problem of jamming power allocation in battlefield cooperative communication countermeasures, this paper designs a distributed cooperative jamming power allocation method based on multi-agent deep reinforcement learning. Specifically, modeling the communication jamming power allocation as a fully cooperative multi-agent task, then the framework of centralized training and distributed decision-making is adopted to alleviate the characteristic of non-stationary environment and high dimensions in multi-agent system, reducing the communication overhead between agents as well, and introducing the maximum policy entropy criterion to control the exploration efficiency of each agent. Regarding maximizing the cumulative jamming reward and maximizing the entropy of the jamming policy as the optimization goal, then accelerates the learning of cooperative strategies. Simulation results indicate the proposed distributed method can effectively solve the high-dimensional cooperative jamming power allocation problem. Compared with the existing centralized allocation method, it has faster learning speed and less volatility, and the jamming efficiency is 16.8% higher than that of the centralized method under the same conditions.

  • Intelligent game of electromagnetic spectrum
    ZHANG Wei, WANG Sha-fei, LIN Jing-ran, LI Qiang, SHAO Huai-zong
    Acta Electronica Sinica. 2022, 50(6): 1281-1290. https://doi.org/10.12263/DZXB.20210805
    Abstract (1159) Download PDF (989) HTML (765)   Knowledge map   Save
    CSCD(2)

    The artificial intelligence technology(e.g., deep learning) is an effective approach to electromagnetic target(ET) recognition. However, in the recognition of multi-mode ETs, when the training samples with a certain mode are missing or rare, the recognition rate with this mode will be significantly degraded. The reason mainly lies in that the data distance between different modes of the same ET may exceed the data distance between different ETs. To remedy this, a cross-modal ET recognition approach via Siamese network is developed in this paper. Following the framework of metric learning, we design the network structure and the loss function carefully, so that the recognition training process intentionally drives the Siamese network to enlarge the data distance between different ETs while shorten the distance between different modes of the same ET. Consequently, the multi-mode ETs can still be successfully recognized by employing certain distance-based decision criterion, even with imbalanced training data sets for different modes. The numerical results based on realistic data show that with same data sets and network size, the cross-modal recognition rate of the proposed approach is 20% higher than that of the classical convolutional neural network approach, and that of the popular data-enhancement approaches.

  • Intelligent game of electromagnetic spectrum
    SONG Bai-lin, XU Hua, QI Zi-sen, RAO Ning, PENG Xiang
    Acta Electronica Sinica. 2022, 50(6): 1301-1309. https://doi.org/10.12263/DZXB.20210814
    CSCD(2)

    In order to solve the problem of collaborative decision-making of frequency-hopping communication jamming in collaborative electronic warfare, based on deep reinforcement learning, a collaborative jamming decision-making algorithm based on actor-critic algorithm framework is proposed, which fuses dominant functions by building a collaborative decision-making model of "overall optimization and making decision station by station". An expert experience mechanism is embedded in the reward function to improve the exploration ability of the algorithm, and the decision network is optimized by the distributed execution-centralized training method, so that the algorithm can output the jamming scheme with the highest resource utilization rate and greatly improve the efficiency of decision-making. The simulation results show that, compared with the existing intelligent decision algorithms, the jamming scheme presented in this paper can save 8% of the interference resources and improve the decision efficiency by more than 50%, which is of great practical value.