DocumentCode
3064888
Title
Automatic ballistocardiogram (BCG) beat detection using a template matching approach
Author
Shin, J.H. ; Choi, B.H. ; Lim, Y.G. ; Jeong, D.U. ; Park, K.S.
Author_Institution
Biomedical Engineering Department of Seoul National University, South Korea
fYear
2008
fDate
20-25 Aug. 2008
Firstpage
1144
Lastpage
1146
Abstract
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.
Keywords
Accuracy; Data analysis; Detection algorithms; Electrocardiography; Hospitals; Medical tests; Monitoring; Performance evaluation; Signal analysis; Sleep; Ballistocardiogram; beat detection; template matching; ubiquitous healthcare; unconstrained monitoring system; Algorithms; Artificial Intelligence; Ballistocardiography; Diagnosis, Computer-Assisted; Heart Rate; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;
fLanguage
English
Publisher
ieee
Conference_Titel
Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE
Conference_Location
Vancouver, BC
ISSN
1557-170X
Print_ISBN
978-1-4244-1814-5
Electronic_ISBN
1557-170X
Type
conf
DOI
10.1109/IEMBS.2008.4649363
Filename
4649363
Link To Document