Localizing Heart Sounds in Respiratory Signals Using Singular Spectrum Analysis

Abstract

Respiratory sounds are always contaminated by heart sound interference. An essential preprocessing step in some of the heart sound cancellation methods is localizing primary heart sound components. Singular spectrum analysis (SSA), a powerful time series analysis technique, is used in this paper. Despite the frequency overlap of the heart and lung sound components, two different trends in the eigenvalue spectra are recognizable, which leads to find a subspace that contains more information about the underlying heart sound. Artificially mixed and real respiratory signals are used for evaluating the performance of the method. Selecting the appropriate length for the SSA window results in good decomposition quality and low computational cost for the algorithm. The results of the proposed method are compared with those of well-established methods, which use the wavelet transform and entropy of the signal to detect the heart sound components. The proposed method outperforms the wavelet-based method in terms of false detection and also correlation with the underlying heart sounds. Performance of the proposed method is slightly better than that of the entropy-based method. Moreover, the execution time of the former is significantly lower than that of the latter.

A multiresolution approach to the extraction of the pyloric rhythm

“…sinusoidal or exponential), or other narrowband processes that are uncorrelated to white noise -except that the technique is much less effective at separating broadband processes from such noise as they are generally unstructured. Here, we adopt the widely used technique of singular spectrum analysis (SSA) that has found applications in a broad range of tasks in classic time-series analysis, multivariate statistics, dynamical systems, signal processing and, latterly, biomedical engineering [16]- [18].…”

Detection of periodic signals using a new adaptive line enhancer based on singular spectrum analysis

“…This is probably the main shortcoming of basic SSA. In some very recent applications such as [4], [5], [6], [7] or [8] selection of periodic components has been decided by clustering the eigentriples [5] or establishing some criteria [6], [7], [8]. Such criteria can be set only if the periodic signal is narrow band or well defined.…”

Detección Automática y Clasificación de Eventos en Sonidos Cardiopulmonares de Sujetos Saludables

“…A pesar de la superposición frecuencial de los componentes del corazón con los sonidos del pulmón, se pueden diferenciar dos tendencias en los espectros con valores propios, estos conducen a un sub-espacio que contiene más información sobre el sonido subyacente del corazón. En un experimento se mezclaron artificialmente señales respiratorias reales para evaluar la eficiencia del método [9] . Seleccionando la longitud adecuada para una ventana SSA que resulta en una descomposición de buena calidad y bajo costo computacional del algoritmo.…”

“…Seleccionando la longitud adecuada para una ventana SSA que resulta en una descomposición de buena calidad y bajo costo computacional del algoritmo. En lo general los algoritmos de detección de sonido del corazón existentes tienen menor desempeño en las señales anormales [9] . En [10] , se propone un algoritmo basado en un método de doble umbral para una detección robusta de los sonidos cardiacos S1 y S2.…”