DocumentCode
2319034
Title
Detection of ventricular fibrillation by sequential hypothesis testing of binary sequences
Author
Pardey, J.
Author_Institution
Cardiology Products Div., Huntleigh Healthcare
fYear
2007
fDate
Sept. 30 2007-Oct. 3 2007
Firstpage
573
Lastpage
576
Abstract
A method is presented for the detection of ventricular fibrillation using binary sequences derived from the surface electrocardiogram. The binary sequences are used to obtain threshold crossing interval and Lempel-Ziv complexity measurements which together form the inputs to a neural network classifier. It is shown that the method outperforms the sequential hypothesis testing of either measurement on the MIT, AHA and CU databases.
Keywords
binary sequences; electrocardiography; medical computing; neural nets; AHA database; CU database; Lempel-Ziv complexity measurements; MIT database; binary sequences; electrocardiogram; neural network classifier; sequential hypothesis testing; ventricular fibrillation; ANSI standards; Artificial neural networks; Binary sequences; Cardiology; Electrocardiography; Fibrillation; Medical services; Neural networks; Sequential analysis; Spatial databases;
fLanguage
English
Publisher
ieee
Conference_Titel
Computers in Cardiology, 2007
Conference_Location
Durham, NC
ISSN
0276-6547
Print_ISBN
978-1-4244-2533-4
Electronic_ISBN
0276-6547
Type
conf
DOI
10.1109/CIC.2007.4745550
Filename
4745550
Link To Document