Electrocardiogram reconstruction using support vector regression
This paper presents a new method to apply support vector regression (SVR) to reconstruct chest lead electrocardiogram (ECG) signals. The reconstructed V2, V3, V4, and V5 signals are obtained from SVRs using Lead 1, Lead II, Vl, and V6 signals as the input features. Only QRS complex, T wave, and P wa...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2015
|
| Online Access: | http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=84889069230&origin=inward http://cmuir.cmu.ac.th/handle/6653943832/39025 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Chiang Mai University |
| Summary: | This paper presents a new method to apply support vector regression (SVR) to reconstruct chest lead electrocardiogram (ECG) signals. The reconstructed V2, V3, V4, and V5 signals are obtained from SVRs using Lead 1, Lead II, Vl, and V6 signals as the input features. Only QRS complex, T wave, and P wave of ECGs are selected to ensure the inclusion of useful information and to reduce the size of training set. We use the 4-fold cross validation to select the best SVR models based on their regression performances. The root mean square (RMS) error of less than 0.2 mV is achieved by the SVR-based models on the test sets. © 2012 IEEE. |
|---|