S-Space College of Medicine/School of Medicine (의과대학/대학원) Psychiatry (정신과학전공) Journal Papers (저널논문_정신과학전공)
Automatic ballistocardiogram (BCG) beat detection using a template matching approach
- Shin, J H; Choi, B H; Lim, Y G; Jeong, D U; Park, K S
- Issue Date
- Conf Proc IEEE Eng Med Biol Soc. 2008;1144-1146
- *Algorithms; *Artificial Intelligence; Ballistocardiography/*methods; Diagnosis, Computer-Assisted/*methods; Heart Rate/*physiology; Pattern Recognition, Automated/*methods; Reproducibility of Results; Sensitivity and Specificity
- This paper suggests a beat detection method for ballistocardiogram (BCG) from an unconstrained cardiac signal monitoring devices. A fiducial peak point of BCG is an I-J-K complex which corresponds with ventricle contraction and Electrocardiogram (ECG) QRS complex. The goal of the method is extraction of J peak without ECG synchronization. The detection method is based on a "template matching" rule evaluated using a correlation function in a local moving-window procedure. The total beat detection algorithm operates in two stages, template definition stage and beat detection stage with defined template in previous stage. In the first stage, the BCG template is constructed by the expert with an empirical analysis of BCG signal and measurement device. In the second stage, the correlation function calculates an accuracy of template with BCG signal using a local moving-window. The data analysis has been performed on the subjects tested at Seoul National University Hospital Sleep Medicine Center and presents 95.16% of sensitivity and 94.76% of positive predictivity value for the J peak detection.
- 1557-170X (Print)
- Files in This Item: There are no files associated with this item.