Novel deep learning approaches are achieving state-of-the-art accuracy in the area of radar target recognition, enabling applications beyond the scope of human-level performance. This book provides an introduction to the unique aspects of machine learning for radar signal processing that any scientist or engineer seeking to apply these technologies ought to be aware of.
The book begins with three introductory chapters on radar systems and phenomenology, machine learning principles, and optimization for training common deep neural network (DNN) architectures. Subsequently, the book summarizes radar-specific issues relating to the different domain representations in which radar data may be presented to DNNs and synthetic data generation for training dataset augmentation. Further chapters focus on specific radar applications, which relate to DNN design for micro-Doppler analysis, SAR-based automatic target recognition, radar remote sensing, and emerging fields, such as data fusion and image reconstruction.
Edited by an acknowledged expert, and with contributions from an international team of authors, this book provides a solid introduction to the fundamentals of radar and machine learning, and then goes on to explore a range of technologies, applications and challenges in this developing field. This book is also a valuable resource for both radar engineers seeking to learn more about deep learning, as well as computer scientists who are seeking to explore novel applications of machine learning.
In an era where the applications of RF sensing are multiplying by the day, this book serves as an easily accessible primer on the nuances of deep learning for radar applications.
Author(s): Sevgi Zubeyde Gurbuz
Series: Radar, Sonar and Navigation
Publisher: SciTech Publishing
Year: 2021
Language: English
Pages: 418
City: London
Contents
About the editor
Acknowledgements
Prologue: perspectives on deep learning of RF data | Sevgi Zubeyde Gurbuz and Eric S. Mason
P.1 The need for novel DNN architectures
P.2 Physics–aware ML that exploits RF data richness
P.3 RF sensing problems that can benefit from DL
P.4 Overview of this book
Part I. Fundamentals
1. Radar systems, signals, and phenomenology | Sevgi Zubeyde Gurbuz, Shunqiao Sun, and David Tahmoush
1.1 Physics of electromagnetic scattering
1.2 Basic radar measurements and waveforms
1.3 Real and synthetic aperture radar processing
1.4 Radar data denoising for machine learning
1.5 Radar data representations for machine learning
1.6 Additional reading
References
2. Basic principles of machine learning | Ali Cafer Gurbuz and Fauzia Ahmad
2.1 Learning from data
2.2 Ingredients of an ML algorithm
2.3 Basic techniques of supervised and unsupervised learning
2.4 Evaluation of a machine learning algorithm
2.5 Conclusion
References
3. Theoretical foundations of deep learning | Stefan Brüggenwirth and Simon Wagner
3.1 Introduction
3.2 Perceptron
3.3 Sigmoid perceptron
3.4 Multilayer perceptron
3.5 Gradient descent
3.6 Backpropagation
3.7 Improvements
3.8 The short history of deep learning
3.9 Convolutional neural networks
3.10 Autoencoders
3.11 Advanced training techniques and further applications of deep learning
References
Part II. Special topics
4. Radar data representation for classification of activities of daily living | Baris Erol and Moeness G. Amin
4.1 Introduction
4.2 Radar signal model and domain suitability
4.3 Multilinear subspace learning
4.4 Optimization considerations for multidimensional methods
4.5 Boosting the MPCA
4.6 Experimental results
4.7 Conclusion
References
5. Challenges in training DNNs for classification of radar micro-Doppler signatures | Sevgi Z. Gurbuz, Moeness G. Amin, Mehmet S. Seyfioglu, and Baris Erol
5.1 Theory of training complex models
5.2 Training with small amounts of real data
5.3 Cross-frequency training using data from other radars
5.4 Transfer learning using pretrained networks
5.5 Training with synthetic data from kinematic models
5.6 Training with synthetic data generated by adversarial neural networks
5.7 Conclusion
References
6. Machine learning techniques for SAR data augmentation | Benjamin Lewis, Theresa Scarnati, Michael Levy, John Nehrbass, Edmund Zelnio, and Elizabeth Sudkamp
6.1 Introduction
6.2 Data generation and the SAMPLE dataset
6.3 Deep learning evaluation and baseline
6.4 Addressing the synthetic/measurement gap with deep neural networks
6.5 Conclusion
Acknowledgments
References
Part III. Applications
7. Classifying micro-Doppler signatures using deep convolutional neural networks | Youngwook Kim
7.1 Micro-Doppler and its representation
7.2 Micro-Doppler classification using a deep convolutional neural network
7.3 Classification of micro-Doppler signatures using transfer learning
7.4 Conclusion
References
8. Deep neural network design for SAR/ISAR-based automatic target recognition | Simon Wagner and Stefan Brüggenwirth
8.1 Introduction
8.2 Deep learning methods used for target recognition
8.3 Datasets
8.4 Classification system
8.5 Experimental results
8.6 Summary and conclusion
References
9. Deep learning for passive synthetic aperture radar imaging | Samia Kazemi, Eric Mason, Bariscan Yonel, and Birsen Yazici
9.1 Introduction
9.2 DL for inverse problem
9.3 Problem statement
9.4 Bayesian and optimization-inspired DL for radar imaging
9.5 Passive SAR imaging for unknown transmission waveform
9.6 Passive SAR imaging for unknown transmission waveform and transmitter location
9.7 Numerical results
9.8 Conclusion
Acknowledgment
Appendix
A.1 Partial derivatives when transmission direction is known
B.1 Partial derivatives when transmission direction is unknown
References
10. Fusion of deep representations in multistatic radar networks | Jarez Satish Patel, Francesco Fioranelli, Matthew Ritchie and Hugh Griffiths
10.1 Introduction
10.2 Experimental multistatic radar system
10.3 Data fusion
10.4 Deep neural network implementations
10.5 Jamming effects in multistatic radar
10.6 Conclusion
References
11. Application of deep learning to radar remote sensing | John Rogers, Lucas Cagle, John E. Ball, Mehmet Kurum and Sevgi Z. Gurbuz
11.1 Open questions in DL for radar remote sensing
11.2 Selected applications
11.3 Additional resources
11.4 Concluding remarks
References
Epilogue: looking toward the future | Sevgi Zubeyde Gurbuz
Index
