By Topic

An approach to reconstruct lost cardiac signals using pattern matching and neural networks via related cardiac information

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Thomas Chee Tat Ho ; Signal Processing Department, Institute for Infocomm Research, Singapore, Singapore ; Xiang Chen

An approach to reconstruct the missing signals by pattern matching and neural networks is proposed in this paper for The Physionet Challenge 2010, “Mind the Gap”. The hypothesis used in this approach in the reconstruction of the missing signals is that the different cardiac signals originating from the same heart should exhibit the same signs of stress acting upon it. The level of stress in the different cardiac signals can and may vary. The neural network is built via pattern matching and cross-reference scoring of data set A. Reconstruction of the missing signal in data set B and C is based on its own prior signal data and using the trained neural network to determine the most likely segment for the filling the missing “gap”.

Published in:

2010 Computing in Cardiology

Date of Conference:

26-29 Sept. 2010