Since the emergence of 5G technology, the wireless communication system has had a huge data throughput, so the joint development of artificial intelligence technology and wireless communication technology is one of the current mainstream development directions. In particular the combination of deep learning technology and communication physical layer technology is the future research hotspot. The purpose of this research paper is to summarize the related algorithms of the combination of Automatic Modulation Recognition (AMR) technology and deep learning technology in the communication physical layer. In order to elicit the advantages of the modulation recognition algorithm based on deep learning, this paper firstly introduces the traditional AMR method, and then summarizes the advantages and disadvantages of the traditional algorithm. Then, the application of the deep learning algorithm in AMR is described, and the identification method based on a typical deep learning network is emphatically described. Afterwards, the existing Deep Learning (DL) modulation identification algorithm in a small sample environment is summarized. Finally, DL modulation is discussed, identifying field challenges, and future research directions.

/pdf/a-review-of-research-on-signal-modulation-recognition-based-3d0rxaoc.pdf

A Review of Research on Signal Modulation Recognition Based on Deep Learning

The cognitive radio senses and tracking the spectrum of frequency and allocate dynamically secondary users in spectral holes. Automatic modulation recognition provides preliminary information to assist in spectrum sensing. This letter proposes a MobileNetV3 for the task of modulation recognition. The MobileNetV3 is a recent network that achieved higher accuracy rates with less computation cost. Experiments showed that the proposed framework achieved higher accuracy than other state-of-art techniques in a comparable latency, which 5G and 6G required. 

MobileNetV3-based Automatic Modulation Recognition for Low-Latency Spectrum Sensing

To realize the full-frequency angular rate measurement of spacecraft based on magnetically suspended control and sensing gyroscope (MSCSG), a full-frequency angular rate measurement method of spacecraft based on multi-MSCSG weight assignment is proposed in this article. First, the main structure of MSCSG is introduced. The traditional angular rate sensing principle of MSCSG is analyzed on the basis of the working principle of Lorentz magnetic bearing, the key component of MSCSG. After introducing and analyzing the shortcomings of the two existing measurement methods, namely, four-cross configuration and virtual gyro technology, the weight function of frequency is obtained by deriving the measurement accuracy model of the two methods. The weight assignment measurement method is proposed to achieve the fusion of the advantages of the two methods and achieve high-precision angular rate measurement of spacecraft in the full-frequency band. Through simulation and semi-physical experiments, we verified that the angular rate accuracy of spacecraft measured by the proposed one can be maintained above 98% at different frequencies, and the higher the frequency, the higher the angular rate measurement accuracy of spacecraft.

A Full-Frequency Angular Rate Measurement Method of Spacecraft Based on Multi-MSCSG Weight Assignment

The cognitive radio senses and tracking the spectrum of frequency and allocate dynamically secondary users in spectral holes. Automatic modulation recognition provides preliminary information to assist in spectrum sensing. This letter proposes a MobileNetV3 for the task of modulation recognition. The MobileNetV3 is a recent network that achieved higher accuracy rates with less computation cost. Experiments showed that the proposed framework achieved higher accuracy than other state-of-art techniques in a comparable latency, which 5G and 6G required.

A Highly Controllable Cooperative Automatic Modulation Classification

Due to the shortage of radio spectrum in the current 5G and upcoming 6G systems, the cognitive radio (CR) technique is indispensable for spectrum management and can put the unutilized spectrum to good use. As the core technology of CR, blind modulation recognition (BMR) plays a pivotal role in improving spectral efficiency. However, the BMR research on MIMO-OFDM systems still lacks enough attention. Given the prosperity of deep learning, we propose a series-constellation multi-modal feature network (SC-MFNet) to recognize the modulation types of MIMO-OFDM subcarriers. Without any prior information, a blind signal separation algorithm is employed to reconstruct the impaired transmitted signal. Considering the insufficient features of signal series, we propose a segment accumulated constellation diagram (SACD) strategy to produce the striking constellation features. Moreover, the proposed multi-modal feature fusion network is employed to collect the advantages of series and SACD features, which are extracted by one-dimensional convolution (Conv1DNet) branch and improved EfficientNet branch, respectively. Experimental results demonstrate that in a realistic non-cooperative cognitive communication scenario where prior information is exempted, the proposed SC-MFNet outperforms the traditional feature-based methods and the state-of-the-art neural networks which are based on either constellation features or series features.

M. Shen

Papers

Series-Constellation Feature Based Blind Modulation Recognition for Beyond 5G MIMO-OFDM Systems With Channel Fading

Adversarial attacks and active defense on deep learning based identification of GaN power amplifiers under physical perturbation