The application discloses a kind of heart sound
abnormality detection method and
system based on earphone, belong to
signal processing technical field.The method includes: obtaining the earphone
microphone collected ear sound
signal;Based on the
physical information neural network constructed in advance, the ear sound
signal is calculated inversely;Based on the constructed neural network, the mapping of inverse signal and real heart sound
label is completed, and the reconstructed heart sound chart is obtained;Based on the reconstructed heart sound chart,
abnormality detection identification is carried out;
Physical information neural network includes source
pulse wave inversion network HemoNet and source heart sound inversion network CardiNet;HemoNet is obtained in ear drum at
arterial pulse pressure wave by ear sound signal inversion, and source
pulse wave is obtained at heart;CardiNet is inverted into source heart sound signal at heart by heart sound collected in
thoracic cavity;MappingNet generates heart sound signal by source
pulse wave signal mapping, and obtains reconstructed heart sound chart.Improve the physical consistency and accuracy of reconstructed signal, realize accurate inversion source pulse wave signal and heart sound reconstruction, improve the convenience and accuracy of
heart rate monitoring.