Aircarft Signal Feature Extraction and Recognition Based on Deep Learning

Radio signal recognition has a wide application in future communication systems and the vehicular communication, whose core is the extraction of signal features such as electromagnetic fingerprints. With the rapid development of artificial intelligence technology, deep learning has made amazing breakthroughs in image recognition, speech recognition and other fields. Deep learning is applied to electromagnetic fingerprint extraction in this paper. Firstly, thousands of the downlink aircraft communications addressing and reporting system (ACARS) signals used for communication between civil aircraft and airport tower are collected and generated. Then a pre-transformation network suitable for electromagnetic signals is constructed to convert one-dimensional signals into two-dimensional feature maps, and afterwards the feature maps are input into the convolutional neural network (CNN) for classification. By adopting the attention modules, the classification results were improved by a few percentage points over the baseline with a little cost. The method proposed in this paper achieves an accuracy rate of 94.1% and can obtain the aircraft type in a shorter time than traditional method. Moreover, the robustness of the proposed model in response to additive Gaussian white noise (AWGN) and phase deviation is studied and tested.

[1]  M. Pajovic,et al.  Channel Estimation and User Identification With Deep Learning for Massive Machine-Type Communications , 2021, IEEE Transactions on Vehicular Technology.

[2]  Kai-Ten Feng,et al.  Design and Implementation for Deep Learning Based Adjustable Beamforming Training for Millimeter Wave Communication Systems , 2021, IEEE Transactions on Vehicular Technology.

[3]  Gengxin Zhang,et al.  Deep Learning Aided Spectrum Prediction for Satellite Communication Systems , 2020, IEEE Transactions on Vehicular Technology.

[4]  Lei Zhu,et al.  Individual Identification Technology of Communication Radiation Sources Based on Deep Learning , 2020, 2020 IEEE 20th International Conference on Communication Technology (ICCT).

[5]  Yonggui Li,et al.  A Brief Review on Deep Learning in Application of Communication Signal Processing , 2020, 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP).

[6]  Alan J. Michaels,et al.  Training data augmentation for deep learning radio frequency systems , 2020 .

[7]  Zhong-Yu Liu,et al.  A Wireless Outdoor Fingerprint Locating Method Based on Ray-tracing Model , 2020, 2020 9th Asia-Pacific Conference on Antennas and Propagation (APCAP).

[8]  Minglu Li,et al.  MagPrint: Deep Learning Based User Fingerprinting Using Electromagnetic Signals , 2020, IEEE INFOCOM 2020 - IEEE Conference on Computer Communications.

[9]  Hatim Alhazmi,et al.  5G Signal Identification Using Deep Learning , 2020, 2020 29th Wireless and Optical Communications Conference (WOCC).

[10]  Khalid A. Qaraqe,et al.  Spectrum Sensing and Signal Identification With Deep Learning Based on Spectral Correlation Function , 2020, IEEE Transactions on Vehicular Technology.

[11]  Adita Kulkarni,et al.  DeepChannel: Wireless Channel Quality Prediction Using Deep Learning , 2020, IEEE Transactions on Vehicular Technology.

[12]  Cheng Liu,et al.  Fingerprint Identification of Short Wave Transmitter Based on Deep Learning , 2019, 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP).

[13]  Jung-Min Jerry Park,et al.  Estimating the Required Training Dataset Size for Transmitter Classification Using Deep Learning , 2019, 2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[14]  Taghi M. Khoshgoftaar,et al.  A survey on Image Data Augmentation for Deep Learning , 2019, Journal of Big Data.

[15]  Shilian Zheng,et al.  Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification , 2019, IEEE Access.

[16]  Danijela Cabric,et al.  Deep Learning Based Transmitter Identification using Power Amplifier Nonlinearity , 2018, 2019 International Conference on Computing, Networking and Communications (ICNC).

[17]  Yair Weiss,et al.  Why do deep convolutional networks generalize so poorly to small image transformations? , 2018, J. Mach. Learn. Res..

[18]  Jan Matuszewski,et al.  Radar signal identification using a neural network and pattern recognition methods , 2018, 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET).

[19]  Bishal Thapa,et al.  Machine Learning Approach to RF Transmitter Identification , 2017, IEEE Journal of Radio Frequency Identification.

[20]  Gang Sun,et al.  Squeeze-and-Excitation Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[21]  Sofie Pollin,et al.  Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors , 2017, IEEE Transactions on Cognitive Communications and Networking.

[22]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[23]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Erich Elsen,et al.  Deep Speech: Scaling up end-to-end speech recognition , 2014, ArXiv.

[25]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[26]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[27]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[28]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.