Detection of Abnormalities in ECG

The neural networks have many applications in technical fields. They have been applied successfully to speech recognition, image analysis and adaptive control, in order to construct software agents or autonomous robots. The electrocardiography (ECG) signal is periodical and therefore is quite predictable. In this paper we describe use of neural network for ECG signal prediction. Successful prediction of ECG should be used for the detection of abnormalities - artifacts, extrasystoles, apnea, etc. An automatic abnormalities detection system was created for offline and online purposes and functionality of this system is described in this paper.