Signal Reconstruction in Sensor Arrays Using Temporal-Spatial Sparsity Regularization
We propose a technique of multisensor signal reconstruction based on the assumption, that source signals are spatially sparse, as well as have sparse [wavelet-type] representation in time domain. This leads to a large scale convex optimization problem, which involves l 1 norm minimization. The optimization is carried by the Truncated Newton method, using preconditioned Conjugate Gradients in inner iterations. The byproduct of reconstruction is the estimation of source locations.
KeywordsSensor Array Wavelet Packet Independent Component Analysis Blind Source Separation Precondition Conjugate Gradient
Unable to display preview. Download preview PDF.
- 2.Zibulevsky, M., Pearlmutter, B.A., Bofill, P., Kisilev, P.: Blind source separation by sparse decomposition. In: Roberts, S.J., Everson, R.M. (eds.) Independent Components Analysis: Princeiples and Practice, Cambridge University Press, Cambridge (2001)Google Scholar
- 3.Cȩtin, M., Malioutov, D.M., Willsky, A.S.: A variational technique for source localization based on a sparse signal reconstruction perspective. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2002, vol. 3, pp. 2965–2968 (2002)Google Scholar
- 4.Malioutov, D.M., Cȩtin, M., FisherIII, J.W., Willsky, A.S.: Superresolution source localization through data-adaptive regularization. In: IEEE Sensor Array and Multichannel Signal Processing Workshop, August 2002, pp. 194–198 (2002)Google Scholar
- 5.Model, D., Zibulevsky, M.: Sparse multisensor signal reconstruction. CCIT report #467, EE department, Technion - Israel Institute of Technology (February 2004)Google Scholar