Attention-Based Radar PRI Modulation Recognition With Recurrent Neural Networks

Analyzing radar signals is a critical task in modern Electronic Warfare (EW) environments. However, the pulse streams emitted by radars have flexible features and complex patterns which are difficult to be identified from a statistical perspective. To solve this problem, pulse repetition interval (PRI) is used as a distinguishing parameter of emitters to be identified. However, traditional PRI modulation recognition methods can only deal with simple PRI modulations and their performance will further degrade with the increasing number of emitters or noisy environments. In this paper, we introduce an attention-based recognition framework based on recurrent neural network (RNN) to categorize pulse streams with complex PRI modulations and in environments with high ratios of missing and spurious pulses. Simulation results show that our model is robust to noisy environments and has a better performance than conventional methods.

[1]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[2]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[3]  Huseyin Arslan,et al.  Cognitive radio, software defined radio, and adaptiv wireless systems , 2007 .

[4]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[5]  Hong Gu,et al.  Weak maneuvering target detection in random pulse repetition interval radar , 2020, Signal Process..

[6]  Ilya Sutskever,et al.  Learning Recurrent Neural Networks with Hessian-Free Optimization , 2011, ICML.

[7]  Jerry L. Eaves,et al.  Principles of Modern Radar , 1987 .

[8]  Suilao Li,et al.  Error Analysis and Compensation of MEMS Rotation Modulation Inertial Navigation System , 2018, IEEE Sensors Journal.

[9]  Wang Wei,et al.  A method for extracting radar words of multi-function radar at data level , 2013 .

[10]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[11]  Hua Wu,et al.  Feature extraction for complicated radar PRI modulation modes based on auto-correlation function , 2016, 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC).

[12]  Masaaki Kobayashi,et al.  Improved algorithm for estimating pulse repetition intervals , 2000, IEEE Trans. Aerosp. Electron. Syst..

[13]  Philip S. Yu,et al.  Classification, Denoising, and Deinterleaving of Pulse Streams With Recurrent Neural Networks , 2019, IEEE Transactions on Aerospace and Electronic Systems.

[14]  Fenglong Ma,et al.  Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks , 2017, KDD.

[15]  Deyi Xiong,et al.  A GRU-Gated Attention Model for Neural Machine Translation , 2017, ArXiv.

[16]  Xiang Wang,et al.  Toward Convolutional Neural Networks on Pulse Repetition Interval Modulation Recognition , 2018, IEEE Communications Letters.

[17]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[18]  Eric Norgren.  Pulse Repetition Interval Modulation Classification using Machine Learning , 2019 .

[19]  Ulla Ruotsalainen,et al.  Hierarchical classification of dynamically varying radar pulse repetition interval modulation patterns , 2010, Neural Networks.

[20]  Jie Yang,et al.  Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios , 2019, IEEE Transactions on Vehicular Technology.

[21]  Bowen Zhou,et al.  Attentive Pooling Networks , 2016, ArXiv.

[22]  Mark Lutz,et al.  Learning Python , 1999 .

[23]  John T Serences,et al.  Enhanced attentional gain as a mechanism for generalized perceptual learning in human visual cortex. , 2014, Journal of neurophysiology.

[24]  Xiaoji Niu,et al.  Civilian Vehicle Navigation: Required Alignment of the Inertial Sensors for Acceptable Navigation Accuracies , 2008, IEEE Transactions on Vehicular Technology.

[25]  Fernando Rangel de Sousa,et al.  Precise techniques to detect superimposed radar pulses on ESM systems , 2018 .

[26]  Ali Kara,et al.  Improvements on deinterleaving of radar pulses in dynamically varying signal environments , 2017, Digit. Signal Process..

[27]  Yanchao Liu,et al.  An improved algorithm for PRI modulation recognition , 2017, 2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC).

[28]  에드워드 비. 커트렐,et al.  Advanced navigation techniques for portable devices , 2005 .

[29]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[30]  P. S. Ray.  A novel pulse TOA analysis technique for radar identification , 1998 .

[31]  Ming Zhou,et al.  Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification , 2014, ACL.

[32]  Amir Mansour Pezeshk,et al.  A robust method for PRI modulation recognition , 2010, IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS.

[33]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[34]  Robert W. Heath,et al.  IEEE 802.11ad-Based Radar: An Approach to Joint Vehicular Communication-Radar System , 2017, IEEE Transactions on Vehicular Technology.

[35]  Omer Levy,et al.  word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method , 2014, ArXiv.

[36]  Hugh Griffiths,et al.  ELINT: the Interception and Analysis of Radar Signals R.G. Wiley Artech House, 46 Gillingham Street, London, SW1V 1AH. 2006. 451pp. Illustrated. £82.00. ISBN 1-58053-925-4. , 2007, The Aeronautical Journal (1968).

[37]  J-P. Kauppi,et al.  An efficient set of features for pulse repetition interval modulation recognition , 2009 .

[38]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[39]  Jing Huang,et al.  Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction , 2017, RecSys.

[40]  Nikhil Ketkar,et al.  Deep Learning with Python , 2017 .

[41]  Ali Kara,et al.  A wavelet-based feature set for recognizing pulse repetition interval modulation patterns , 2016 .

[42]  Mohammad Hossein Sedaaghi,et al.  A new method for detecting jittered PRI in histogram-based methods , 2018, TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES.

[43]  Omer Levy,et al.  Neural Word Embedding as Implicit Matrix Factorization , 2014, NIPS.

[44]  Barak A. Pearlmutter.  Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[45]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[46]  H. K. Mardia.  New techniques for the deinterleaving of repetitive sequences , 1989 .

[47]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[48]  G. P. Noone,et al.  A neural approach to automatic pulse repetition interval modulation recognition , 1999, 1999 Information, Decision and Control. Data and Information Fusion Symposium, Signal Processing and Communications Symposium and Decision and Control Symposium. Proceedings (Cat. No.99EX251).