Please use this identifier to cite or link to this item:
http://repositorio.ufc.br/handle/riufc/70735| Type: | Artigo de Evento |
| Title: | Efficient ECG multi-level wavelet classification through neural network dimensionality reduction |
| Authors: | Andreão, Rodrigo Varejão Dorizzi, Bernadette Cortez, Paulo César Mota, João César Moura |
| Issue Date: | 2002 |
| Publisher: | Workshop on Neural Networks for Signal Processing |
| Citation: | MOTA, J. C. M. et al. Efficient ECG multi-level wavelet classification through neural network dimensionality reduction. In: WORKSHOP ON NEURAL NETWORKS FOR SIGNAL PROCESSING, 12., 2002, Martigny. Anais... Martigny: IEEE, 2002. p. 395-404. |
| 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. |
| URI: | http://www.repositorio.ufc.br/handle/riufc/70735 |
| Appears in Collections: | DETE - Trabalhos apresentados em eventos |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2002_eve_jcmmota.pdf | 358,34 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.