Learn More
—This paper is concerned with a fixed-point implementation of the extended Kalman filter (EKF) for applications in sensorless control of ac motor drives. The sensitivity of the EKF to round-off errors is well known, and numerically advantageous implementations based on the square-root decomposition of covariance matrices have been developed to address this(More)
– The particle filter provides a general solution to the nonlinear filtering problem with arbitrarily accuracy. However, the curse of dimensionality prevents its application in cases where the state dimension-ality is high. Further, estimation of stationary parameters is a known challenge in a particle filter framework. We suggest a marginalization approach(More)
Factor Analysis (FA) is a well established method for factors separation in analysis of dynamic medical imaging. However , its assumptions are valid only in limited regions of interest (ROI) in the images which must be selected manually or using heuristics. The resulting quality of separation is sensitive to the choice of these ROI. We propose a new(More)
Blind source separation algorithms are based on various separation criteria. Differences in convolution kernels of the sources are common assumptions in audio and image processing. Since it is still an ill posed problem, any additional information is beneficial. In this contribution , we investigate the use of sparsity criteria for both the source signal(More)
A common problem of imaging 3-D objects into image plane is superposition of the projected structures. In dynamic imaging, projection overlaps of organs and tissues complicate extraction of signals specific to individual structures with different dynamics. The problem manifests itself also in dynamic tomography as tissue mixtures are present in voxels.(More)
— An extension of the AutoRegressive (AR) model is studied, which allows transformations and distortions on the regressor to be handled. Many important signal processing problems are amenable to this Extended AR (i.e. EAR) model. It is shown that Bayesian identification and prediction of the EAR model can be performed recursively, in common with the AR(More)