Heart sound signal classification method based on convolutional recurrent neural network
A cyclic neural network and signal classification technology, applied in the field of heart sound signal classification based on convolutional cyclic neural network, can solve problems such as low accuracy and dependence on heart sound analysis, and achieve improved accuracy, robustness and generalization. Ability, the effect of good learning ability
- Application Information
AI Technical Summary
Problems solved by technology
 The specific embodiment of the present invention selects the PhysioNet / CinCChallenge heart sound database provided on the 2016 Physical Network Challenge.
 like figure 1 As shown, it is a flowchart of an embodiment of the present invention, including the following steps:
Noise processing of heart sound data: Since the heart sound signal is relatively weak and easily affected by the environment, it is inevitable to introduce noise during the acquisition process, which has a great impact on the correctness of the signal analysis results, so it is necessary to remove the noise first. Heart sound signal for further processing. Therefore, a 5th-order Butterworth band-pass filter is used to process the heart sound signal. According to the frequency distribution of the noise of the heart sound signal, the design cut-off frequencies are respectively wn 1 =20Hz,wn 2 =400Hz. figure 2 is the normal heart sound signal and the filtered waveform, image 3 Abnor...
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction