Quantitative analysis signal-based approach using the dual tree complex wavelet transform for studying heart sound conditions

摘要

Heart sound signal is an important sign about the mechanical performance of the cardiac valves. Enhancement of heart sound signal is a crucial issue to identify cardiac disease relevant to valve disorder. This study, presents a new approach based on the use of Dual Tree Complex Wavelet transform (DTCWT). The current approach has been employed in order to identify the normal heart sound from the pathological disorder. Twenty analyzed signals obtained from the PhysioNet database. After the preprocessing procedure the DTCWT has been implemented and the reconstructed signal were employed to extract five statistical features for both sounds. The result of the implementation and box plot showing the robust of DTCWT with apparent significance amongst the traditional discreet wavelet transform (DWT).