Data reconstruction for missing electrocardiogram using linear predictive coding
An electrocardiogram (ECG) reconstruction method based on a linear prediction technique is proposed in this paper. The method can reconstruct a rather long missing parts of ECG signals. Each missing data segment may cover 1 to 8 beats. The data used in the experiments are from the MIT-BIH normal sin...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=64949199551&origin=inward http://cmuir.cmu.ac.th/jspui/handle/6653943832/60354 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Chiang Mai University |
| Summary: | An electrocardiogram (ECG) reconstruction method based on a linear prediction technique is proposed in this paper. The method can reconstruct a rather long missing parts of ECG signals. Each missing data segment may cover 1 to 8 beats. The data used in the experiments are from the MIT-BIH normal sinus rhythm database. The experimental results show that our method can perform very well. The reconstructed signals are visually very close to the ground truths. The numerical evaluation also shows that the proposed method yields good results on the heart rate variability (HRV) measure derivation. It gives the time-domain HRV measures that are very close to the ground truths. Its performance is also better than the method commonly used by experts in which the abnormal beats are removed before calculating the HRV measures. © 2008 IEEE. |
|---|