Deep Neural Network Design for Radar Applications

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