|
|
|
| The Application of Frequency Slice Wavelet Transform in ECG Signal Feature Extraction |
|
|
|
|
Abstract According to the difference of time-frequency characteristics of ECG
(electrocardiogram) signal and jamming signal, FSWT (Frequency Slice
Wavelet Transform) is used to deal with the ECG signal denoising and
feature extraction. FSWT algorithm has a good time-frequency
aggregation and can freely choose the frequency range for signal
reconstruction to extract characteristic information flexibly and
accurately. Firstly, ECG signal is decomposed to get the whole
time-frequency distribution characteristic by using FSWT and carries
on the detailed analysis. Frequency section interval is determined
according to frequency distribution characteristics of the jamming
signal, disturbance signal is refactored and isolated through the
time-frequency filter and the inverse transformation of FSWT. So it
can realize the ECG signal denoising and feature extraction. The
proposed algorithm is compared with wavelet threshold denoising
method, Empirical Mode Decomposition (EMD) and average empirical
mode decomposition (AIMF). The simulation results show that, the
denoising effect of FSWT is superior to other methods for ECG
signal, and gives the time-frequency distribution characteristics of
ECG signal.
|
|
|
|
|
|
| Cite this article: |
|
Nan Li,Zhaochun Yang. The Application of Frequency Slice Wavelet Transform in ECG Signal Feature Extraction[J]. Journal of Fiber Bioengineering and Informatics, 2015, 8(3): 461-472.
|
|
|
|
|
2015, Vol. 8 
