A signal-noise separation algorithm for the estimation of respiratory rate from breath sound

Breathing is an involuntary action by the human body, and irregularities in breathing suggests possible respiratory disorders. Respiratory rate is an important parameter for breath sound analysis, and many papers have been published on how respiratory rate can be measured accurately and non-invasively. However, relatively fewer papers deal with breath sound based respiratory rate estimation. This paper proposes a signal-noise separation algorithm for estimating the respiratory rate from the breath sound. The estimation accuracy, in terms of mean square error, of the proposed algorithm has been evaluated using data collected from patients of the National University Hospital (NUH), for both low noise and high noise environments.