Robust respiration rate estimation using adaptive Kalman filtering with textile ECG sensor and accelerometer.
Annu Int Conf IEEE Eng Med Biol Soc
; 2016: 3797-3800, 2016 Aug.
Article
en En
| MEDLINE
| ID: mdl-28269113
An adaptive Kalman filter-based fusion algorithm capable of estimating respiration rate for unobtrusive respiratory monitoring is proposed. Using both signal characteristics and a priori information, the Kalman filter is adaptively optimized to improve accuracy. Furthermore, the system is able to combine the respiration-related signals extracted from a textile ECG sensor and an accelerometer to create a single robust measurement. We measured derived respiratory rates and, when compared to a reference, found root-mean-square error of 2.11 breaths-per-minute (BrPM) while lying down, 2.30 BrPM while sitting, 5.97 BrPM while walking, and 5.98 BrPM while running. These results demonstrate that the proposed system is applicable to unobtrusive monitoring for various applications.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Procesamiento de Señales Asistido por Computador
/
Electrocardiografía
/
Frecuencia Respiratoria
Límite:
Humans
/
Male
/
Middle aged
Idioma:
En
Revista:
Annu Int Conf IEEE Eng Med Biol Soc
Año:
2016
Tipo del documento:
Article