Classification of SAECG by autoregressive modelling and neural networks

Author

Nyongesa, H.O. ; Alexakis, C. ; Saatchi, R. ; Rodrigues, M. ; Harris, N D ; Heller, S.R. ; Davies, C. ; Emery, C. ; Ireland, R.H.

Author_Institution

Univ. of Botswana, Gaborone, Botswana

Volume

2

fYear

2004

fDate

15-17 Sept. 2004

Firstpage

841

Abstract

The paper describes investigations into the classification of signal-averaged electrocardiogram (SAECG) signals, with regard to detection of the onset of hypoglycaemia in diabetic patients. Firstly, feature extraction is carried out to obtain time-domain features, which are classified by neural networks. Secondly, the SAECG signals are modelled by autoregressive modelling (AR), and the parameters classified using linear discriminant analysis. The classification performances using both approaches are compared. ECG datasets were obtained from ongoing related research, and consist of paired ECG-glucose readings from type-1 diabetic patients. Data was recorded overnight in the patient´s own homes.

Keywords

autoregressive processes; electrocardiography; feature extraction; medical signal processing; neural nets; signal classification; sugar; time-domain analysis; ECG datasets; ECG-glucose readings; autoregressive modelling; diabetic patients; hypoglycaemia; linear discriminant analysis; neural networks; signal-averaged electrocardiogram signals; time-domain features; Artificial neural networks; Biological neural networks; Diabetes; Electrocardiography; Feature extraction; Linear discriminant analysis; Neural networks; Personal digital assistants; Shape; Sugar;

fLanguage

English

Publisher

ieee

Conference_Titel

AFRICON, 2004. 7th AFRICON Conference in Africa

Print_ISBN

0-7803-8605-1

Type

conf

DOI

10.1109/AFRICON.2004.1406804

Filename

1406804