Paper Info
Title
One Lead ECG Based Personal Identification with Feature Subspace Ensembles
Abstract
In this paper we present results on real data, focusing on personal identification based on one lead ECG, using a reduced number of heartbeat waveforms. A wide range of features can be used to characterize the ECG signal trace with application to personal identification. We apply feature selection (FS) to the problem with the dual purpose of improving the recognition rate and reducing data dimensionality. A feature subspace ensemble method (FSE) is described which uses an association between FS and parallel classifier combination techniques to overcome some FS difficulties. With this approach, the discriminative information provided by multiple feature subspaces, determined by means of FS, contributes to the global classification system decision leading to improved classification performance. Furthermore, by considering more than one heartbeat waveform in the decision process through sequential classifier combination, higher recognition rates were obtained.
Year
DOI
Venue
2007
10.1007/978-3-540-73499-4_58
MLDM
Keywords
Field
DocType
feature selection,multiple feature subspaces,feature subspace ensemble method,lead ecg,fs difficulty,personal identification,data dimensionality,decision process,feature subspace ensembles,ecg signal trace,global classification system decision,heartbeat waveform,classification system
Heartbeat,Signal trace,Subspace topology,Pattern recognition,Feature selection,Computer science,Linear subspace,Curse of dimensionality,Artificial intelligence,Classifier (linguistics),Discriminative model,Machine learning
Conference
Volume
ISSN
Citations 
4571
0302-9743
26
PageRank 
References 
Authors
1.82
20
3
Name
Order
Citations
PageRank
Hugo Silva122730.18
Hugo Gamboa2409100.80
Ana Fred321617.07