Communication Signal Modulation Mechanism Based on Artificial Feature Engineering Deep Neural Network Modulation Identifier

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 crossentropy 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.

[1]  Yu-Dong Yao,et al.  Modulation Classification Based on Signal Constellation Diagrams and Deep Learning , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Menghan Chen,et al.  Digital Signal Modulation Classification using Data Conversion Method based on Convolutional Neural Network , 2020, Journal of Physics: Conference Series.

[3]  DenseNet-ResNet-LSTM model for modulation recognition of communication signal , 2020 .

[4]  Linhui Sun,et al.  Deep and shallow features fusion based on deep convolutional neural network for speech emotion recognition , 2018, Int. J. Speech Technol..

[5]  Wei Lin,et al.  HTTP Tunnel Trojan Detection Model Based on Deep Learning , 2019 .

[6]  M. Richterová.  Signal Modulation Recognizer Based on Method of Artificial Neural Networks , 2005 .

[7]  Peng Wu,et al.  Automatic Modulation Classification Based on Deep Learning for Software-Defined Radio , 2020 .

[8]  Tao Zhang,et al.  A novel seizure diagnostic model based on kernel density estimation and least squares support vector machine , 2018, Biomed. Signal Process. Control..

[9]  Jijiang Yang,et al.  Performance of deep neural network-based artificial intelligence method in diabetic retinopathy screening: a systematic review and meta-analysis of diagnostic test accuracy. , 2020, European journal of endocrinology.

[10]  Xiaoru Bi.  A Method for Modulation Recognition of Maritime Search and Rescue Communication Signal Based on Neural Network , 2020, Journal of Coastal Research.

[11]  Zhang Yue,et al.  Cyclic Cumulant Based On Communication Signal Multilayer Neural Network Modulation Pattern Recognition , 2018, 2018 IEEE 3rd International Conference on Cloud Computing and Internet of Things (CCIOT).

[12]  Xiangjie Kong,et al.  Realizing the Potential of Internet of Things for Smart Tourism with 5G and AI , 2020, IEEE Network.

[13]  Syed Hassan Ahmed,et al.  Guest Editorial: Special Section on Advanced Deep Learning Algorithms for Industrial Internet of Things , 2021, IEEE Trans. Ind. Informatics.

[14]  Joaquin Gonzalez-Rodriguez,et al.  An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition , 2017, PloS one.

[15]  Wei Wei,et al.  Intelligent Internet of Things System for Smart Home Optimal Convection , 2021, IEEE Transactions on Industrial Informatics.

[16]  Suqin Wu,et al.  Communication modulation recognition algorithm based on STFT mechanism in combination with unsupervised feature-learning network , 2019, Peer-to-Peer Networking and Applications.

[17]  V. V. Yerigeri.  Classification of Fruit Family Based On Features Extraction Using PNN Classification , 2018 .

[18]  Farbod Razzazi,et al.  A Self Training Approach to Automatic Modulation Classification Based on Semi-supervised Online Passive Aggressive Algorithm , 2015, Wirel. Pers. Commun..

[19]  Yiming Chen,et al.  Feature Extraction Method of Radiation Source in Deep Learning Based on Square Integral Bispectrum , 2020 .

[20]  Jun Won Choi,et al.  Deep neural network-based automatic modulation classification technique , 2016, 2016 International Conference on Information and Communication Technology Convergence (ICTC).

[21]  Junhu Ruan,et al.  A Model for Joint Planning of Production and Distribution of Fresh Produce in Agricultural Internet of Things , 2021, IEEE Internet of Things Journal.

[22]  Arunkumar Rajendran,et al.  Multi-retinal disease classification by reduced deep learning features , 2017, Neural Computing and Applications.

[23]  Fathi E. Abd El-Samie,et al.  Modulation classification in the presence of adjacent channel interference using convolutional neural networks , 2020, Int. J. Commun. Syst..

[24]  Kai Yu,et al.  Deep features for automatic spoofing detection , 2016, Speech Communication.

[25]  Jian Guo,et al.  A New Feature Extraction Algorithm Based on Entropy Cloud Characteristics of Communication Signals , 2015 .

[26]  Mahmoud Omid,et al.  An Artificial Neural Network‐Based Method to Identify Five Classes of Almond According to Visual Features , 2016 .

[27]  Yifan Li,et al.  A method to detect sleep apnea based on deep neural network and hidden Markov model using single-lead ECG signal , 2018, Neurocomputing.