Efficient ECG multi-level wavelet classification through neural network dimensionality reduction

Author

Andreão, Rodrigo Varejão ; Dorizzi, Bernadette ; Cortez, Paulo César ; Mota, João César Mom

Author_Institution

Inst. Nat. des Telecommun., Evry, France

fYear

2002

fDate

2002

Firstpage

395

Lastpage

404

Abstract

In this article, we explore the use of a unique type of wavelets for ECG beat detection and classification. Once the different beats are segmented, classification is performed using at the input of a neural network different wavelet scales. This improves the noise resistance and allows a better representation of the different morphologies. The results, evaluated on the MIT/BIH database, are excellent (97.69% on the normal and PVC classes) thanks to the use of a regularization technique.

Keywords

electrocardiography; medical signal detection; medical signal processing; neural nets; pattern classification; signal representation; signal resolution; wavelet transforms; ECG; MIT/BIH database; beat classification; beat detection; beat segmentation; dimensionality reduction; morphology representation; multi-level wavelet classification; neural network; noise resistance; regularization technique; wavelet scales; Artificial neural networks; Diseases; Electrocardiography; Heart; Morphology; Neural networks; Pathology; Signal processing; Spatial databases; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks for Signal Processing, 2002. Proceedings of the 2002 12th IEEE Workshop on

Print_ISBN

0-7803-7616-1

Type

conf

DOI

10.1109/NNSP.2002.1030051

Filename

1030051