A real-time ECG classification algorithm using fractal and cross-correlation analyses achieved 100% classification accuracy for normal and premature ventricular contraction beats in some ECG records.
Does an algorithm based on fractal and cross correlation analyses accurately classify ECG beats in real-time?
An algorithm based on fractal and cross correlation analyses can achieve high accuracy for real-time ECG classification of normal and premature ventricular contraction beats.
The objective of this project is to develop algorithms for real-time electrocardiogram (ECG) classification. The program is made to be concise and accurate enough for use on an ambulatory monitor. A reliable QRS detection algorithm based on a one-pole filter has been developed. Automatic ECG classification using fractal and cross correlation analyses is investigated. The computation demand is not high and real-time analysis is possible. Testing is carried out using the American Heart Association (AHA) ventricular arrhythmia ECG data. The types of beat being selected in the study are: normal (N), premature ventricular contraction (V), and fusion of ventricular and normal beats (F). The classification accuracy of 100% for N and V beats can be achieved in some ECG records.
Lai et al. (Thu,) conducted a other in Ventricular arrhythmia. Real-time ECG classification algorithm based on fractal and cross correlation analyses was evaluated on Classification accuracy for normal (N) and premature ventricular contraction (V) beats. A real-time ECG classification algorithm using fractal and cross-correlation analyses achieved 100% classification accuracy for normal and premature ventricular contraction beats in some ECG records.