Title :
ECG frequency domain features extraction: a new characteristic for arrhythmias classification
Author :
Romero, I. ; Serrano, L.
Author_Institution :
Dept. of Electr. & Electron. Eng., Public Univ. of Navarra, Pamplona, Spain
Abstract :
This article describes a new ECG spectrum feature that allows the classification of dangerous arrhythmia. In order to check the classification effectiveness of this variable, the statistical method known as ANOVA has been used. The results obtained show that this parameter could be an effective classification feature of dangerous arrhythmia with an approximated probability of error of 0.00%.
Keywords :
electrocardiography; error statistics; feature extraction; frequency-domain analysis; medical signal processing; probability; signal classification; ANOVA; ECG signal classification; ECG spectrum feature; arrhythmias classification; classification effectiveness; frequency domain features extraction; half point feature; probability of error; resultant probability value column; Analysis of variance; Application software; Databases; Electrocardiography; Feature extraction; Fibrillation; Frequency domain analysis; Rhythm; Signal processing algorithms; Statistical analysis;
Conference_Titel :
Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE
Print_ISBN :
0-7803-7211-5
DOI :
10.1109/IEMBS.2001.1020624
