Open AccessA novel approach to detect respiratory phases from pulmonary acoustic signals using normalised power spectral density and fuzzy inference system
Author(s) -
Palaniappan Rajkumar,
Sundaraj Kenneth,
Sundaraj Sebastian,
Huliraj N.,
Revadi S.S.
Publication year - 2016
Publication title -
the clinical respiratory journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.789
H-Index - 33
eISSN - 1752-699X
pISSN - 1752-6981
DOI - 10.1111/crj.12250
Subject(s) - mean squared error , correlation coefficient , spectral density , fuzzy logic , pearson product moment correlation coefficient , medicine , correlation , mathematics , statistics , pattern recognition (psychology) , artificial intelligence , computer science , geometry
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 M amdani and S ugeno methods. To evaluate the performance of both M amdani and S ugeno methods, correlation coefficient and root mean square error ( RMSE ) were calculated. Results In the correlation coefficient analysis in evaluating the fuzzy model using M amdani and S ugeno method, the strength of the correlation was found to be r = 0.9892 and r = 0.9964, respectively. The RMSE for M amdani and S ugeno 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 S ugeno method performs better compared with the M amdani method.