Search

In this paper, we propose a fuzzy rulebased boundary extraction method for a plaque in an intravascular ultrasound (IVUS) image. In the present method, a plaque boundary to be extracted is piecewise approximated by the polynomials inferred by fuzzy rules. The coefficients of the polynomials are determined by the weighted least square method using the separability measure obtained from the IVUS image. The proposed method achieves a precise and noise-robust extraction of the plaque with use of a small number of seed points and without any timeconsuming iterative processes. The validity and the effectiveness of the proposed method have been confirmed by applying it to the boundary extraction problem of the plaque in the IVUS image. [ABSTRACT FROM AUTHOR]

We discuss in this paper the feature extraction and signal reconstruction of air and bone conduction voices in the time domain by applying the independent component analysis (ICA). The basis functions of the air and bone conduction voices extracted by applying ICA are shown first, and then the quality of the signal reconstruction by using several of those basis functions is investigated from the signal compression viewpoint. [ABSTRACT FROM AUTHOR]