Towards recurrent neural network with multi-path feature fusion for signal modulation recognition

2022 ◽  
Zihang Lei ◽  
Mengxi Jiang ◽  
Guangsong Yang ◽  
Tianmin Guan ◽  
Peng Huang ◽  
Symmetry ◽  
2021 ◽  
Vol 13 (12) ◽  
pp. 2302
Kaiyuan Jiang ◽  
Xvan Qin ◽  
Jiawei Zhang ◽  
Aili Wang

In the noncooperation communication scenario, digital signal modulation recognition will help people to identify the communication targets and have better management over them. To solve problems such as high complexity, low accuracy and cumbersome manual extraction of features by traditional machine learning algorithms, a kind of communication signal modulation recognition model based on convolution neural network (CNN) is proposed. In this paper, a convolution neural network combines bidirectional long short-term memory (BiLSTM) with a symmetrical structure to successively extract the frequency domain features and timing features of signals and then assigns importance weights based on the attention mechanism to complete the recognition task. Seven typical digital modulation schemes including 2ASK, 4ASK, 4FSK, BPSK, QPSK, 8PSK and 64QAM are used in the simulation test, and the results show that, compared with the classical machine learning algorithm, the proposed algorithm has higher recognition accuracy at low SNR, which confirmed that the proposed modulation recognition method is effective in noncooperation communication systems.

2021 ◽  
Siyuan Cheng ◽  
Didi Yin ◽  
Dongya Zhang ◽  
Wei Zhao ◽  
Lin Jin ◽  

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Fei Lu ◽  
Zhenjiang Shi ◽  
Rijian Su

Based on the characteristics of time domain and frequency domain recognition theory, a recognition scheme is designed to complete the modulation identification of communication signals including 16 analog and digital modulations, involving 10 different eigenvalues in total. In the in-class recognition of FSK signal, feature extraction in frequency domain is carried out, and a statistical algorithm of spectral peak number is proposed. This paper presents a method to calculate the rotation degree of constellation image. By calculating the rotation degree and modifying the clustering radius, the recognition rate of QAM signal is improved significantly. Another commonly used method for calculating the rotation of constellations is based on Radon transform. Compared with the proposed algorithm, the proposed algorithm has lower computational complexity and higher accuracy under certain SNR conditions. In the modulation discriminator of the deep neural network, the spectral features and cumulative features are extracted as inputs, the modified linear elements are used as neuron activation functions, and the cross-entropy is used as loss functions. In the modulation recognitor of deep neural network, deep neural network and cyclic neural network are constructed for modulation recognition of communication signals. The neural network automatic modulation recognizer is implemented on CPU and GPU, which verifies the recognition accuracy of communication signal modulation recognizer based on neural network. The experimental results show that the communication signal modulation recognizer based on artificial neural network has good classification accuracy in both the training set and the test set.

2021 ◽  
Ruiyan Du ◽  
Fulai Liu ◽  
Jialiang Xu ◽  
Fan Gao ◽  
Zhongyi Hu ◽  

Abstract Modulation recognition is an important research area in wireless communication. It is commonly used in both military and civilian domains, such as spectrum detection and interference identification. Most existing modulation recognition algorithms have a better recognition performance at high signal noise ratio (SNR). However, when SNR decreases to -10 dB or even lower, such as the battlefield and disaster areas and other harsh environment, the recognition rate may decrease dramatically. In order to solve this problem, a modulation recognition algorithm based on denoising bidirectional recurrent neural network (DBRNN) is proposed. Firstly, the state memory ability of the signal reconstruction layer in the network is utilized to learn the temporal correlation of the modulated signal, the reconstruction of the received signal is completed and the noise in the modulated signal is suppressed. Then, the reconstructed signal is encoded and decoded by the feature reconstruction layer, in which the feature of reconstructed signal is compressed and reconstructed, thereby the influence of noise can be further reduced. Finally, the reconstructed features are identified and classified by the fully connected layer. Simulation results demonstrate that the proposed network can effectively suppress the noise in the signal. Compared with other existing algorithms, the proposed method has higher recognition accuracy in the low SNR environment.

2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

Sign in / Sign up

Export Citation Format

Share Document