Discrimination analysis of discontinuous breath sounds using higher-order crossings

Abstract

The paper evaluates the performance of an automatic discrimination analysis (DA) method used to discriminate efficiently the types of discontinuous breath sound (DBS), i.e. fine crackles (FCs), coarse crackles (CCs) and squawks (SQs); this may lead to more accurate characterisation of the pulmonary acoustical changes due to the related pathology. Based on higher-order crossings (HOCs), the proposed method, HOC-DA, captured the differences in the oscillatory patterns of FCs, CCs and SQs, which are only exposed when higher (> 1) crossings are employed. Prior to HOC-DA, wavelet-based de-noising of DBSs was employed to eliminate the effects of the vesicular sound (background noise) from their oscillatory pattern. The HOC-DA was applied to 157 discontinuous breath sounds corresponding to 16 cases included in three lung sound databases. Results showed that the HOC-DA efficiently separated FCs from CCs, SQs from CCs (both with an accuracy of 100%), and SQs from FCs (accuracy of 80%), with the optimum order ranging from 9 to 11. When compared with other classification tools, the HOC-DA resulted in high discrimination accuracy without involving high computational complexity. Owing to its simplicity, it could be implemented in a real-time context and be used in clinical medicine as a module of an integrated intelligent patient evaluation system.

Fast frequency estimation using spline wavelets

“…Formula (2) also offers a way to compute the auto-correlation, which is often used in signal spectrum analysis. [15][16][17] In the scale-space theory for computer vision, the zero-crossings in multi-scale or scale-space filtering are usually referred to as the fingerprints in the scale-space theory. 18,19 The famous scaling theorem states that the Gaussian kernel is the only filter with which the number of zero-crossings of a signal does not increase with the increase of smoothing scale.…”

Fast Frequency Estimation by Zero Crossings of Differential Spline Wavelet Transform

“…The relationship between the wavelet transform signatures of a signal and its frequency estimation based on Fourier transform is thus established. Formula (27) also offers a way to compute the autocorrelation, which is often used in signal spectrum analysis [2,3,21].…”

“…They have also found applications in many engineering fields. For example, the higher-order zero crossings were utilized for fast detection of contractions in uterine electromyography [2] and for discrimination of discontinuous breath sounds [3]. In computer vision, zero crossings were usually used for detection of edges in an image [4].…”

Lung Sounds: An Advanced Signal Processing Perspective

“…The  symbol denotes the center of each group (FC and CC), whereas the borderline is the estimated linear border that clearly discriminates the two groups. The solid and dash-dotted circles correspond to MN and [±(σ + s)] of the distance from cluster center, respectively, both for FC and CC [128].…”

“…HOC have been used to perform a discrimination analysis of DAS, especially FC, CC, and SQ [128]. In fact, HOC assesses the changes in oscillatory pattern of DAS according to their type, by estimating the relevant HOC sequence.…”