An orthogonal least squares-based fuzzy filter for real-time analysis of lung sounds

Pathological discontinuous adventitious sounds (DAS) are strongly related w ith the pulmonary dysfunction, Its clinical use for the interpretation of r espiratory malfunction depends on their efficient and objective separation from vesicular sounds (VS), In this paper, an automated approach to the iso lation of DAS from VS, based on their nonstationarity, is presented, The pr oposed scheme uses two fuzzy inference systems (FISs), operating in paralle l, to perform the task of adaptive separation, resulting in the orthogonal least squares-based fuzzy filter (OLS-FF), By applying the OLS-FF to fine/c oarse crackles and squawks, selected from three lung sound databases, the c oherent structure of DBS is revealed and they are efficiently separated fro m VS. The important time domain DAS features, related to diagnostic informa tion, are preserved and their true location and structural morphology are a utomatically identified, When compared to previous works, the OLS-FF perfor ms quite similarly, but with significantly lower computational load, result ing in a faster real-time clinical screening of DAS.