Year-end Sale % OFF 
Abstract
In complex electromagnetic environments, electromagnetic signal classification rates are low as long time have to be the cost to extract features. To cope with the issue, in this paper, an electromagnetic signal classification method is proposed based on deep sparse capsule networks. In the proposed method, received signals are frequency reduced and sampled processing first. Subsequently, a cross ambiguity function based on linear canonical transformation, a cross ambiguity function based on linear canonical domain, and higher-order spectrum are estimated, respectively. The maximum value of each section of the cross ambiguity function is combined with the maximum value of equally spaced cross sections of higher order amplitude spectrum to obtain the two-dimensional feature information. Finally, electromagnetic signals are classified by the deep sparse capsule networks. The simulation results show that the proposed method not only has good classification performance but also can automatically get a hierarchical feature representation by learning. Moreover, the corresponding time cost can be effectively reduced.
Highlights
Electromagnetic signals are fundamental and widely used in wireless communications and radar [1]–[5]
To overcome the aforementioned problems, this paper proposes a electromagnetic signal classification method based on deep sparse capsule networks
SIMULATION RESULTS AND ANALYSIS In order to verify the effectiveness of the proposed method, the simulation experiment using MATLAB and the eight types of electromagnetic signals including constant wave (CW), linear frequency modulation (LFM), frequency shift keying (FSK), binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), LFM-BPSK, FSK-BPSK, and non-linear frequency modulation (NLFM) are considered
Summary
Electromagnetic signals are fundamental and widely used in wireless communications and radar [1]–[5]. The sparsity of spectral features, high-order statistical features, and compression sensing algorithm are adopted in [16] to realize the modulation recognition This method requires the phase and frequency deviation of the signal to be zero. The authors in [27] employ the convolutional neural network (CNN) to classify the pulse modulated electromagnetic signal and extract the deep features of the image automatically. In [29], features are extracted from the VOLUME 7, 2019 received data of Choi-Williams time-frequency distribution (CWD) images and the classifier was Elman neural network (ENN) This network model will increase the structural complexity of the network model, and the recognition accuracy is acquired at the cost of time. To overcome the aforementioned problems, this paper proposes a electromagnetic signal classification method based on deep sparse capsule networks.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
