Time–Frequency-Analysis-Based Blind Modulation Classification for Multiple-Antenna Systems

Abstract

Blind modulation classification is an important step in implementing cognitive radio networks. The multiple-input multiple-output (MIMO) technique is widely used in military and civil communication systems. Due to the lack of prior information about channel parameters and the overlapping of signals in MIMO systems, the traditional likelihood-based and feature-based approaches cannot be applied in these scenarios directly. Hence, in this paper, to resolve the problem of blind modulation classification in MIMO systems, the time–frequency analysis method based on the windowed short-time Fourier transform was used to analyze the time–frequency characteristics of time-domain modulated signals. Then, the extracted time–frequency characteristics are converted into red–green–blue (RGB) spectrogram images, and the convolutional neural network based on transfer learning was applied to classify the modulation types according to the RGB spectrogram images. Finally, a decision fusion module was used to fuse the classification results of all the receiving antennas. Through simulations, we analyzed the classification performance at different signal-to-noise ratios (SNRs); the results indicate that, for the single-input single-output (SISO) network, our proposed scheme can achieve 92.37% and 99.12% average classification accuracy at SNRs of −4 and 10 dB, respectively. For the MIMO network, our scheme achieves 80.42% and 87.92% average classification accuracy at −4 and 10 dB, respectively. The proposed method greatly improves the accuracy of modulation classification in MIMO networks.

CP Antenna with 2 × 4 Hybrid Coupler for Wireless Sensing and Hybrid RF Solar Energy Harvesting

“…With these specification parameters, the overall configuration can work well on the adaptive antenna system, which is then described in the configuration analysis in the sensor wireless communication system in the next subsection. Based on the configuration in the wireless sensor communication system, it can be analyzed as an adaptive antenna system which has been confirmed to provide significant advantages on single-input single-output [38,39] or multiple-input multiple-output [40,41]. This analysis has additionally proven powerful for applications such as locationbased services, positioning for tracking, and wireless sensor networks.…”

“…Assume that the antenna analysis is positioned in planar conditions with specifications according to performance tests, namely sensitive to circular propagation wave polarization and directional radiation polarization. Based on the configuration in the wireless sensor communication system, it can be analyzed as an adaptive antenna system which has been confirmed to provide significant advantages on single-input single-output [38,39] or multiple-input multiple-output [40,41]. This analysis has additionally proven powerful for applications such as location-based services, positioning for tracking, and wireless sensor networks.…”

A Survey of Blind Modulation Classification Techniques for OFDM Signals

“…Blind modulation classification (MC) determines the modulation type of the received signal, ensuring proper demodulation and retrieval of the transmitted data [ 1 , 2 , 3 , 4 ]. Recently, MC has played a significant role in both military and civilian communications, such as cognitive radio, signal intelligence, link adaptation, signal control, and SDR [ 3 , 4 , 5 , 6 , 7 ].…”

“…Blind modulation classification (MC) determines the modulation type of the received signal, ensuring proper demodulation and retrieval of the transmitted data [ 1 , 2 , 3 , 4 ]. Recently, MC has played a significant role in both military and civilian communications, such as cognitive radio, signal intelligence, link adaptation, signal control, and SDR [ 3 , 4 , 5 , 6 , 7 ]. With an intelligent receiver, blind parameter estimation and classification algorithms may be used, resulting in a substantial increase in spectral efficiency since no predefined training or pilot sequence is needed [ 8 , 9 , 10 ].…”

Classification Method of Uniform Circular Array Radar Ground Clutter Data Based on Chaotic Genetic Algorithm

“…Uniform circular array (UVA) radar is a uniform circular array radar composed of isotropic antennas, which has the advantages of space omnidirectional scanning, various search and tracking methods, and flexible beam pointing [ 1 , 2 , 3 ]. It is especially suitable for the monitoring of low and slow targets under complex terrain background.…”