Subspace estimation plays an important role in, for example, sensor array signal processing, Recursive methods for subspace tracking with application to nonstationary environments have also drawn considerable interest...
详细信息
Subspace estimation plays an important role in, for example, sensor array signal processing, Recursive methods for subspace tracking with application to nonstationary environments have also drawn considerable interest, In this paper, instrumental variable (IV) extensions of the recently developed projection approximation subspace tracking (PAST) algorithm are presented. The IV approach is motivated by the fact that PAST gives biased estimates when the noise is not spatially white, The proposed algorithms are based on a projection like unconstrained criterion, with a resulting computational complexity of 3ml + O(mn), where m dimension of the measurement vector;l dimension of the IV vector;n subspace dimension, In addition, an extension to a "second order" IV algorithm is proposed, which in certain scenarios is demonstrated to have better tracking properties than the basic IV-PAST algorithms, The performance of the algorithms is demonstrated with a simulation study of a time-varying arrayprocessing scenario.
A non-model-based image analysis technique for brain imaging is presented. In this approach, the brain tissue type and organ structure are represented by image regions. The technique formulates the region detection pr...
详细信息
ISBN:
(纸本)0780320506
A non-model-based image analysis technique for brain imaging is presented. In this approach, the brain tissue type and organ structure are represented by image regions. The technique formulates the region detection problem in a multidimensional signalprocessing framework. Following the region detection, the image analysis is performed by segmentation which is completed by region parameter estimation and pixel classification. The proposed technique has superior computation speed over existing model-based approaches. The most important feature is that it properly utilizes the spatial correlations among the pixels. The major applications of this technique in brain image analysis are tissue classification and quantification.
暂无评论