ECG Arrhythmia Detection using PCA and Elman Neural Network

Cardiac arrhythmia refers to any abnormal electrical activity in the heart that causes irregular heartbeat. Under clinical settings, the arrhythmias can be monitored non-invasively using the electrocardiogram (ECG). Although reliable, the method is still prone to error due to its dependence on visual interpretation. Further, ECG data is enormous in dimension and increases as the data sampling rate increases. The increase in ECG sampling rate puts a limitation on processing of ECG data for analysis. However, high sampling rate gives an added advantage of ECG representation at high resolution at the same time, but analysis of ECG with this high dimensional data is time consuming. Therefore, in order to reduce the dimension of ECG data but at the maximum variance is required so that the reduced ECG data represents the full features of the ECG under scanner. In the presented work, the dimensionality of the high resolution ECG data is worked out with optimum speed of operation.