A novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system

BACKGROUND: Monitoring respiration is important in several medical applications. One such application is respiratory rate monitoring in patients with sleep apnoea. The respiratory rate in patients with sleep apnoea disorder is irregular compared with the controls. Respiratory phase detection is required for a proper monitoring of respiration in patients with sleep apnoea.

AIMS: To develop a model to detect the respiratory phases present in the pulmonary acoustic signals and to evaluate the performance of the model in detecting the respiratory phases.

METHODS: Normalised averaged power spectral density for each frame and change in normalised averaged power spectral density between the adjacent frames were fuzzified and fuzzy rules were formulated. The fuzzy inference system (FIS) was developed with both Mamdani and Sugeno methods. To evaluate the performance of both Mamdani and Sugeno methods, correlation coefficient and root mean square error (RMSE) were calculated.

RESULTS: In the correlation coefficient analysis in evaluating the fuzzy model using Mamdani and Sugeno method, the strength of the correlation was found to be r = 0.9892 and r = 0.9964, respectively. The RMSE for Mamdani and Sugeno methods are RMSE = 0.0853 and RMSE = 0.0817, respectively.

CONCLUSION: The correlation coefficient and the RMSE of the proposed fuzzy models in detecting the respiratory phases reveals that Sugeno method performs better compared with the Mamdani method.