This paper presents a new algorithm for segmentation and classification of S1 and S2 heart sounds without ECG reference. The proposed approach is composed of three main stages. In the first stage the fundamental heart sound lobes are identified using a fast wavelet transform and the Shannon energy. Next, these lobes are validated and classified into S1 and S2 classes based on Mel-frequency coefficients and on a non supervised neural network. Finally, regular heart cycles are identified in a post-processing stage by a heart rhythm criterion. This approach was tested using sound samples collected from prosthetic valve implanted patients. Results are comparable with ECG based approaches.
机构:
Univ Estadual Campinas, Inst Math Stat & Sci Computat, Dept Math, Sao Paulo, BrazilUniv Estadual Campinas, Inst Math Stat & Sci Computat, Dept Math, Sao Paulo, Brazil
de Rezende, Ketty A.
Ledesma, Guido G. E.
论文数: 0引用数: 0
h-index: 0
机构:
Univ Estadual Campinas, Inst Math Stat & Sci Computat, Dept Math, Sao Paulo, BrazilUniv Estadual Campinas, Inst Math Stat & Sci Computat, Dept Math, Sao Paulo, Brazil
Ledesma, Guido G. E.
Manzoli Neto, Oziride
论文数: 0引用数: 0
h-index: 0
机构:
Univ Sao Paulo, Inst Math Sci & Computat, Sao Paulo, BrazilUniv Estadual Campinas, Inst Math Stat & Sci Computat, Dept Math, Sao Paulo, Brazil