Abstract:
Pulmonary disease is a major cause of ill-health throughout the world. The diagnosis of these common chest diseases is facilitated by pulmonary auscultation using a stethoscope. Auscultation with a stethoscope has many limitations. It is a subjective process that depends on the individual's own hearing, experience and ability to differentiate between different sound patterns. It is not easy to produce quantitative measurements or make a permanent record of an examination in documentary form. Here in this work we developed instrumentation for recording lung sounds, it consists of hardware - for acquiring the. signal, amplification and filtering. This filtered signal is digitized and recorded.
Respiratory sounds contain significant information on physiology and pathology of the lungs and the airways. The frequency spectrum and the amplitude of sounds, without adventitious sound components (crackles or wheezes), may reflect airway dimension and their pathologic changes (airway obstruction) or pathologic changes in the
pulmonary tissue. These crackles sounds are of non stationary in nature so here we implemented Stationary-Non stationary separating filter whose coefficients are solved by
LMS (least mean square) algorithm. Wheezes are musical sounds which are sinusoidal in nature are separated by using Discrete Wavelet Transform. Interference of heart sounds in lung sounds are reduced by spectrogram method with help of RLS (recursive least square) filter
