Intelligent Radar Signal Recognition and Classification

This chapter investigates a classification problem for timely and reliable identification of radar signal emitters by implementing and following a neural network (NN) based approach. A large data set of intercepted generic radar signals, containing records of their pulse train characteristics (such as operational frequencies, modulation types, pulse repetition intervals, scanning period, etc.), is used for this research. Due to the nature of the available signals, the data entries consist of a mixture of continuous, discrete and categorical data, with a considerable number of records containing missing values. To solve the classification problem, two separate approaches are investigated, implemented, tested and validated on a number of case studies. In the first approach, a listwise deletion is used to clean the data of samples containing missing values and then feed-forward neural networks are employed for the classification task. In the second one, a multiple imputation (MI) model-based method for dealing with missing data (by producing confidence intervals for unbiased estimates without loss of statistical power, i.e. by using all the available samples) is investigated. Afterwards, a feedforward backpropagation neural network is trained to solve the signal classification problem. Each of the approaches is tested and validated on a number of case studies and the results are evaluated and critically compared. The rest of the chapter is organised as follows: the next section (Introduction and Background) presents a review of related literature and relevant background knowledge on the investigated topic. In Sect. 2 (Data Analysis), a broader formulation of the problem is provided and a deeper analysis of the available data set is made. Different statistical transformation techniques are discussed and a multiple imputation method for dealing with missing data is introduced in Sect. 3 (Data Pre-Processing). Several NN topologies, training parameters, input and output coding, and data transformation techniques for facilitating the learning process are tested and evaluated on a set of case studies in Sect. 4 (Results and Discussion). Finally, Sect. 5 (Conclusion) summarises the results and provides ideas for further extension of this research.

[1]  Stephen Grossberg,et al.  A What-and-Where fusion neural network for recognition and tracking of multiple radar emitters , 2001, Neural Networks.

[2]  Andrew K. Skidmore,et al.  Earth observation for biodiversity monitoring : a review of current approaches and future opportunities for tracking progress towards the Aichi Biodiversity Targets : e-book , 2014 .

[3]  Ralf G. Herrtwich,et al.  Making Bertha See , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[4]  Evert Slob,et al.  Surface and borehole ground-penetrating-radar developments , 2010 .

[5]  Roderick J. A. Little,et al.  Statistical Analysis with Missing Data: Little/Statistical Analysis with Missing Data , 2002 .

[6]  D. Curtis Schleher,et al.  Electronic Warfare in the Information Age , 1999 .

[7]  John C. Sciortino,et al.  Autonomous ESM Systems , 1997 .

[8]  N. V. S. N. Sarma,et al.  Identification of LPI Radar signals by higher order spectra and neural network techniques , 2008, 2008 International Conference on Electronic Design.

[9]  In-Sik Choi,et al.  Performance enhancement of target recognition using feature vector fusion of monostatic and bistatic radar , 2014 .

[10]  You He,et al.  Study on radar emitter recognition signal based on rough sets and RBF neural network , 2009, International Conference on Machine Learning and Computing.

[11]  H. E. Hassan.  A new algorithm for radar emitter recognition , 2003, 3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the.

[12]  Qiang Huang,et al.  Underwater target classification using wavelet packets and neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[13]  Ting Jiang,et al.  A new sense-through-foliage target recognition method based on hybrid differential evolution and self-adaptive particle swarm optimization-based support vector machine , 2015, Neurocomputing.

[14]  T. Ince.  Polarimetric SAR Image Classification Using Radial Basis Function Neural Network , 2010 .

[15]  Li Hui,et al.  The Radar Target Recognition Research Based on Improved Neural Network Algorithm , 2014, 2014 Fifth International Conference on Intelligent Systems Design and Engineering Applications.

[16]  Behrooz Kamgar-Parsi,et al.  Automatic Data Sorting Using Neural Network Techniques. , 1996 .

[17]  Peter Goos,et al.  Sequential imputation for missing values , 2007, Comput. Biol. Chem..

[18]  N. K. Ibrahim,et al.  Artificial neural network approach in radar target classification , 2009 .

[19]  Manuel Rosa-Zurera,et al.  Artificial Neural Network-Based Clutter Reduction Systems for Ship Size Estimation in Maritime Radars , 2010, EURASIP J. Adv. Signal Process..

[20]  Marnik Vanclooster,et al.  Modeling of ground-penetrating Radar for accurate characterization of subsurface electric properties , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Philip Ross.  Thus spoke the autobahn , 2015, IEEE Spectrum.

[22]  Lin Li,et al.  Specific radar emitter recognition based on wavelet packet transform and probabilistic SVM , 2009, 2009 International Conference on Information and Automation.

[23]  Goffredo Foglia,et al.  Specific Emitter Identification: Analysis on real radar signal data , 2009, 2009 European Radar Conference (EuRAD).

[24]  Yun Lin,et al.  Radar Signal Recognition Based on Manifold Learning Method , 2014 .

[25]  David Bonacci,et al.  Sonar and radar SAR processing for parking lot detection , 2011, 2011 12th International Radar Symposium (IRS).

[26]  Chih-Min Lin,et al.  A Self-Organizing Interval Type-2 Fuzzy Neural Network for Radar Emitter Identification , 2014 .

[27]  Luigi Sambuelli,et al.  Comparison between GPR measurements and ultrasonic tomography with different inversion algorithms: an application to the base of an ancient Egyptian sculpture , 2011 .

[28]  Jason W. Osborne,et al.  Best Practices in Data Cleaning: How Outliers and “Fringeliers” Can Increase Error Rates and Decrease the Quality and Precision of Your Results , 2008 .

[29]  Steven A. Arcone,et al.  Stratigraphic variation within polar firn caused by differential accumulation and ice flow: interpretation of a 400 MHz short-pulse radar profile from West Antarctica , 2005, Journal of Glaciology.

[30]  Nicholas J. Horton,et al.  Multiple Imputation in Practice , 2001 .

[31]  D. Rubin,et al.  Statistical Analysis with Missing Data. , 1989 .

[32]  L. Anjaneyulu,et al.  Identification of LPI Radar signals by higher order spectra and neural network techniques , 2008 .

[33]  Chin-Teng Lin,et al.  A vector neural network for emitter identification , 2002 .

[34]  Zhutian Yang,et al.  A study on radar emitter recognition based on spds neural network , 2011 .

[35]  Gerhard Krieger,et al.  Advanced Concepts for High-Resolution Wide-Swath SAR Imaging , 2010 .

[36]  M. Skolnik,et al.  Introduction to Radar Systems , 2021, Advances in Adaptive Radar Detection and Range Estimation.

[37]  Karl Erik Olsen,et al.  Bi- and Multistatic Radar , 2006 .

[38]  James A. Anderson,et al.  Advanced signal waveform classifier , 1997, Optics & Photonics.

[39]  Mitchell Lazarus.  Radar everywhere , 2015, IEEE Spectrum.

[40]  N. Bowring,et al.  Signal processing techniques for concealed weapon detection by use of neural networks , 2012, 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel.

[41]  Yiyu Zhou,et al.  Approach based on combination of vector neural networks for emitter identification , 2010 .

[42]  Lei Wang,et al.  Feature extraction and optimization of representative-slice in ambiguity function for moving radar emitter recognition , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[43]  V. Koivunen,et al.  Automatic Radar Waveform Recognition , 2007, IEEE Journal of Selected Topics in Signal Processing.

[44]  Gregory L. Charvat,et al.  Through-Wall Imaging Radar , 2012 .

[45]  Yngvar Larsen,et al.  Sar Remote Sensing of Snow Parameters in Norwegian Areas — Current Status and Future Perspective , 2006 .

[46]  Chen Ting,et al.  Research on Rough Set-Neural Network and Its Application in Radar Signal Recognition , 2007, 2007 8th International Conference on Electronic Measurement and Instruments.

[47]  R. J. Galejs,et al.  Volume surveillance radar frequency selection , 2000, Record of the IEEE 2000 International Radar Conference [Cat. No. 00CH37037].

[48]  Zhi-Quan Luo,et al.  Online clustering algorithms for radar emitter classification , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  Uday B. Desai,et al.  Radar Signal Detection In Non-Gaussian Noise Using RBF Neural Network , 2008, J. Comput..

[50]  Francesco Soldovieri,et al.  A strategy for the determination of the dielectric permittivity of a lossy soil exploiting GPR surface measurements and a cooperative target , 2009 .

[51]  Benjamin C. Flores,et al.  Multi-Mode Radar Target Detection and Recognition Using Neural Networks , 2012 .

[52]  Erhard Rahm,et al.  Data Cleaning: Problems and Current Approaches , 2000, IEEE Data Eng. Bull..

[53]  Gexiang Zhang,et al.  A novel approach for radar emitter signal recognition , 2004, The 2004 IEEE Asia-Pacific Conference on Circuits and Systems, 2004. Proceedings..

[54]  Guo Wei,et al.  A new radar emitter recognition method based on pulse sample figure , 2011, 2011 Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[55]  Ou Li,et al.  A new algorithm for signal emitter recognition , 2010, 2010 International Conference on Image Analysis and Signal Processing.

[56]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[57]  Jingchao Li,et al.  Radar signal recognition algorithm based on entropy theory , 2014, The 2014 2nd International Conference on Systems and Informatics (ICSAI 2014).

[58]  A. Farina,et al.  Knowledge-based radar signal and data processing: a tutorial review , 2006, IEEE Signal Processing Magazine.

[59]  Duyan Bi,et al.  Multiple-Parameter Radar Signal Sorting Using Support Vector Clustering and Similitude Entropy Index , 2014, Circuits Syst. Signal Process..

[60]  Craig K. Enders,et al.  An introduction to modern missing data analyses. , 2010, Journal of school psychology.

[61]  In-Sik Choi,et al.  Natural frequency-based neural network approach to radar target recognition , 2003, IEEE Trans. Signal Process..

[62]  Richard K. Moore,et al.  Seasat—A 25-year legacy of success , 2005 .

[63]  Lorenzo Bruzzone,et al.  Earthquake Damage Assessment of Buildings Using VHR Optical and SAR Imagery , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[64]  Mark A. Richards,et al.  Fundamentals of Radar Signal Processing , 2005 .

[65]  Ian G. Cumming,et al.  Digital Processing of Synthetic Aperture Radar Data: Algorithms and Implementation , 2005 .

[66]  Craig K. Enders,et al.  Applied Missing Data Analysis , 2010 .

[67]  Dean Goodman,et al.  GPR Remote Sensing in Archaeology , 2013 .

[69]  J Francke,et al.  Applications of GPR in mineral resource evaluations , 2010, Proceedings of the XIII Internarional Conference on Ground Penetrating Radar.

[70]  J. Graham,et al.  Missing data analysis: making it work in the real world. , 2009, Annual review of psychology.

[71]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[72]  R. Persico.  Introduction to Ground Penetrating Radar: Inverse Scattering and Data Processing , 2014 .

[73]  Francesco Soldovieri,et al.  GPR Response From Buried Pipes: Measurement on Field Site and Tomographic Reconstructions , 2009, IEEE Transactions on Geoscience and Remote Sensing.