Translator Disclaimer
6 November 2008 Feature selection of signal-averaged electrocardiograms by orthogonal least squares method
Author Affiliations +
Proceedings Volume 7124, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2008; 71240P (2008) https://doi.org/10.1117/12.817954
Event: Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2008, 2008, Wilga, Poland
Abstract
A crucial problem in machine learning is finding the representative set of data for building a model for both classification and approximation task. In this paper we present the orthogonal least squares method for feature selection. The presented method was used for finding the most important features for selecting patients with sustained ventricular tachycardia after myocardial infarction (SVT+). We show that with the reduced set of descriptors used in the classification process we obtain the results that are better than those obtained with the full set.
© (2008) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Michal Raczyk, Stanislaw Jankowski, and Ewa Piatkowska-Janko "Feature selection of signal-averaged electrocardiograms by orthogonal least squares method", Proc. SPIE 7124, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2008, 71240P (6 November 2008); https://doi.org/10.1117/12.817954
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Using machine learning techniques to classify cricket sound
Proceedings of SPIE (December 31 2019)
A portable ECG monitor using Bluetooth
Proceedings of SPIE (June 29 2005)
Adaptive linear combination of weighted medians
Proceedings of SPIE (May 22 2002)
Frequency selective weighted median filters
Proceedings of SPIE (March 05 1999)

Back to Top