Electrocardiogram feature extraction based on Gaussian model(PDF)
《中国医学物理学杂志》[ISSN:1005-202X/CN:44-1351/R]
- Issue:
- 2020年第11期
- Page:
- 1441-1447
- Research Field:
- 医学信号处理与医学仪器
- Publishing date:
Info
- Title:
- Electrocardiogram feature extraction based on Gaussian model
- Author(s):
- SUN Shuping; YANG Wenbo; DONG Zengqi; ZHANG Biqiang; HUANG Tingting
- Nanyang Institute of Technology, Nanyang 473000, China
- Keywords:
- electrocardiogram signal QRS Gaussian mixture model feature extraction R-peak detection
- PACS:
- R318
- DOI:
- DOI:10.3969/j.issn.1005-202X.2020.11.018
- Abstract:
- A Gaussian mixture model-based electrocardiogram (ECG) feature extraction method is proposed to accurately locate the R-peak and extract ECG features. Firstly, short time modified Hilbert transform (STMHT) algorithm is adopted to locate the R-peak. Secondly, based on the located R-peak, 6 Gaussian functions are built to fit each ECG beat. Finally, ECG features are extracted based on the Gaussian models. The performance of the proposed algorithm is validated using the ECG records of MIT-BIH arrhythmia database, and the results show that the proposed method can achieve an average detection accuracy of 99.80%.
Last Update: 2020-12-02