An improved ECG-derived respiration method using kernel principal component analysis
Recent studies show that principal component analysis (PCA) of heart beats generates well-performing ECG-derived respiratory signals (EDR). This study aims at improving the performance of EDR signals using kernel PCA (kPCA). Kernel PCA is a generalization of PCA where nonlinearities in the data are...
- Autores:
- Tipo de recurso:
- Fecha de publicación:
- 2011
- Institución:
- Universidad del Rosario
- Repositorio:
- Repositorio EdocUR - U. Rosario
- Idioma:
- eng
- OAI Identifier:
- oai:repository.urosario.edu.co:10336/28434
- Acceso en línea:
- https://repository.urosario.edu.co/handle/10336/28434
- Palabra clave:
- Principal component analysis
Kernel
Electrocardiography
Correlation
Coherence
Sensors
Optimization
- Rights
- License
- Restringido (Acceso a grupos específicos)
| Summary: | Recent studies show that principal component analysis (PCA) of heart beats generates well-performing ECG-derived respiratory signals (EDR). This study aims at improving the performance of EDR signals using kernel PCA (kPCA). Kernel PCA is a generalization of PCA where nonlinearities in the data are taken into account for the decomposition. The performance of PCA and kPCA is evaluated by comparing the EDR signals to the reference respiratory signal. Correlation coefficients of 0.630 ± 0.189 and 0.675 ± 0.163, and magnitude squared coherence coefficients at respiratory frequency of 0.819 ± 0.229 and 0.894 ± 0.139 were obtained for PCA and kPCA respectively. The Wilcoxon signed rank test showed statistically significantly higher coefficients for kPCA than for PCA for both the correlation (p = 0.0257) and coherence (p = 0.0030) coefficients. To conclude, kPCA proves to outperform PCA in the extraction of a respiratory signal from single lead ECGs. |
|---|