Second generation wavelets: Advantages in cardiosignal processing

Gavrovska, Ana; Zajic, Goran; Reljin, Irini; Bogdanović, Vesna; Reljin, Branimir

doi:10.1109/telsks.2013.6704942

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where noise σ represents the estimated standard deviation of noise and d 1 are detail coefficients from the first level of decomposition. Wavelet sym4 is selected based on the results of extensive testing (Chouakri et al 2005, Gavrovska et al 2013b. After denoising, classification type 0 is performed.…”

Section: Heart Sound Signal Classification and Multifractal Spectrum ...mentioning

confidence: 99%

“…In the first stage it is possible to easily differentiate healthy sounds in the noisy circumstances, σ n ∈ [0.001, 0.01]. It can be considered that in the case of a rather high level of noise (σ n ∈ [0.001, 0.01]), clinically valuable high-frequency content is not affected to a great extent (Gavrovska et al 2013b. The calculated slope parameter values for A versus B class and A versus C class differentiation are presented in figures 4(a) and (b).…”

Section: Classification In Noisy Circumstancesmentioning

confidence: 99%

See 1 more Smart Citation

Paediatric heart sound signal analysis towards classification using multifractal spectra

et al. 2016

View full text Add to dashboard Cite

Healthy versus unhealthy heart sound computer-aided classification tools are very popular for supporting clinical decisions. In this paper a new method is proposed for the classification of heart sound recordings from a statistical standpoint without detection and localization of fundamental heart sounds (S1, S2). This study analyzes the possibility of detecting healthy heart sound signal from a large set of measurements, corresponding to different pathologies, such as aortic regurgitation, mitral regurgitation, aortic stenosis and ventricular septal defects. The proposed method employs singularity spectra analysis and long-term dependency of irregular structures. Healthy signals are firstly separated from the rest of the recordings. In the second step, the signals with a click syndrome, used here as a reference, are detected in the unhealthy group. Innocent murmurs have not been considered in this paper. Each auscultatory recording is classified into one of the following classes: healthy; click syndrome; and other heart dysfunctions. The results of the proposed method provided high recall and precision values for each of the three classes. Since the presence of additive noise may affect the classification, we also analyzed the possibility of classifying signals in such circumstances. The method was tested, verified and showed high accuracy.

show abstract

Section: Heart Sound Signal Classification and Multifractal Spectrum ...mentioning

confidence: 99%

Section: Classification In Noisy Circumstancesmentioning

confidence: 99%

Paediatric heart sound signal analysis towards classification using multifractal spectra

et al. 2016

View full text Add to dashboard Cite

show abstract

“…Unfortunately, in some cases, as for instance in PMV (Prolapsed Mitral Valve) syndrome, standard higher-order wavelet (e.g., symmlet 8) may smooth out not only the noise but also the subtle click and thus the wrong diagnosis may be derived. To overcome this problem, we suggested to perform initial analysis of the signal, and to apply lower prediction order using lifting structure in case of the existence of potential abnormality [5]. The concept of filtering in physical domain (by using second generation wavelets and/or empirical mode decomposition [6]) may additionally improve the quality of denoising.…”

Section: A Signal Preprocessingmentioning

confidence: 99%