Tutorials

Complex-Valued Neural Networks in Remote Sensing and Imaging (Half day)

Akira Hirose

ahirose@ee.t.u-tokyo.ac.jp

Duration: Half-Day

Description of Tutorial:

This tutorial presents and discusses the fundamentals of complex-valued neural networks (CVNNs) and their applications in the remote sensing and imaging field. The CVNN is a type of neural networks suitable for adaptive processing of complex-amplitude information. Since active remote sensing deals with coherent electromagnetic wave, we can expect the CVNN to work more appropriately than conventional neural networks or other adaptive methods in real-number space.

The beginning half of the tutorial is devoted to presentation of the basic idea, framework, and treatment in the CVNNs. We discuss the processing dynamics of Hebbian rule, back-propagation learning, and self-organizing map in the complex domain. The latter half shows some examples of CVNN processing in the geoscience and remote sensing (GRSS) fields. Namely, we present distortion reduction in generation of digital elevation model (DEM) from the data obtained by interferometric synthetic aperture radar (InSAR). Another example is ground penetrating radar (GPR) to visualize underground objects to distinguish specific targets in high-clutter situation. Finally we discuss the prospect of the CVNNs in the GRSS fields.

Material to be Distributed:

PowerPoint Handout,
Discounted book under negotiation with Springer

Biography of Presenter:

Dr. Hirose received his Ph.D. degree in electronic engineering from the University of Tokyo in 1991. Presently he is a Professor of The University of Tokyo, Tokyo, Japan. He has been publishing many articles on remote sensing, wireless electronics and complex-valued neural networks in leading journals as well as books such as Complex-Valued Neural Networks, Springer, 2006. Concerning this topic, he received awards such as the 1998 Outstanding Research Award of the Research Foundation for Opto-Science and Technology, the 2004 ICONIP Best Paper Award for Theoretical Development, and the 2006 IEEE/INNS WCCI-IJCNN Best Session Presentation Award. He is a Senior Member of the IEEE and the IEICE, and a Member of JNNS. He was the Chair of the IEICE Neurocomputing (NC) Technical Group (2009-2010), and presently serves as a Member of the Steering Committees of the IEICE Space, Aeronautical and Navigational Electronics (SANE) Technical Group, IEICE Electromagnetic Theory (EMT) Technical Group, IEEE Computational Intelligence Society (CIS) Japan Chapter (2005-). He is an IEEE CIS Neural Network Technical Committee (NNTC) Member, a Governing Board Member of Japanese Neural Network Society (JNNS) (2005-) and Asia-Pacific Neural Network Assembly (APNNA) (2007-). He also serves as the Editor-in-Chief Elect of the IEICE Transactions on Electronics (2009-) and an Associate Editor of journals such as the IEEE Transactions on Neural Networks (2009-) and the IEEE Geoscience and Remote Sensing Society (GRSS) Newsletter.

Selected Publications:

Journal Papers:

1 R.Natsuaki A.Hirose, "SPEC method - A fine co-registration method for SAR interferogram," IEEE Transactions on Geoscience and Remote Sensing, to appear

2 R.Yamaki A.Hirose, "Singular unit restoration in interferograms based on complex-valued Markov random field model for phase unwrapping," IEEE Geoscience and Remote Sensing Letters 6, 1 (2009) 18-22

3 S.Masuyama K.Yasuda A.Hirose, "Multiple mode selection of walled-LTSA array elements for high resolution imaging to visualize antipersonnel plastic landmines," IEEE Geoscience and Remote Sensing Letters, 5, 4 (2008) 745-749

4 R.Yamaki A.Hirose, "Singularity-spreading phase unwrapping," IEEE Transactions on Geoscience and Remote Sensing, 45, 10 (2007) 3240-3251

5 S.Masuyama A.Hirose, "Walled LTSA array for rapid, high spatial resolution, and phase sensitive imaging to visualize plastic landmines," IEEE Transactions on Geoscience and Remote Sensing, 45, 8 (2007) 2536-2543

Books:

1 A.Hirose, Complex-Valued Neural Networks, Springer (August 2006) ISBN 3-540-33456-4

2 A.Hirose (ed.), Complex-Valued Neural Networks: Theories and Applications, Series on Innovative Intelligence World Scientific Publishing Co. Singapore (Nov. 2003) ISBN 981-238-464-2