Rapid or slow heartbeats cause irregular rhythms resulting in Cardiac Arrhythmia, which is assessed by electrocardiogram (ECG). There are various types of arrhythmia and its detection is relevant to heart disease diagnosis. Automatic arrhythmia ECG assessment is a wellresearched area. This paper investigates ECG classification using soft computing techniques to classify arrhythmia type through the use of RR interval. Discrete Cosine Transform (DCT) is used to extract features from the time series ECG data using the distance between RR waves. The extracted beat RR interval is used as a feature extracted in the frequency domain and classified using Multi-Layer Perceptron Neural Network (MLP –NN), and proposed Feed Forward Neural Network (FNN) experiments were conducted through the MIT-BIH arrhythmia database.

Electrocardiogram (ECG) refers to the bioelectrical signals of the heart muscles activity; it is recorded in a graph called the electrocardiograph, which measures the heart’s electrical voltage. This plays an important role in diagnosing cardiovascular diseases. An ECG represents the heart beat’s arterial depolarization/ventricular repolarization, and is obtained through many electrodes. P, Q, R, S, and T (McSharry et al., 2003) revealed in Figure 1 are peaks and ECG waveforms. Varied characteristics like PR, QRS, and ST intervals also diagnose cardiac arrhythmia (Singh and Tiwari, 2006). The standard guidelines are shortlisted in John Camm (1996) for heart rate variability measure categorization. A summary of the measure and models are presented in Teich et al. (2001), and the examined physiological origins and heart rate mechanism are seen in Berntson et al. (1997).

Cardiac Arrhythmia is due to irregular rhythms caused by irregular heartbeats (Sandoe and Sigurd, 1991). A slow or fast heartbeat causes irregular rhythm. Arrhythmia is indicative of serious heart problems, but visual checks for arrhythmia are tedious and time-consuming. This is the reason why automatic heart beat classification, which expedites diagnosis, benefits medical experts. Real-time automatic arrhythmia detection/ classification is critical in clinical cardiology. ECG arrhythmia diagnoses are improved through pattern classifier techniques. Every person has different ECG recordings due to noise and amplitude and therefore signals are pre-processed to ensure beat detection and feature extraction.

Computer Sciences Journal, ECG, Arrhythmia classification, MIT-BIH ECG data, RR interval, Feed Forward Neural Network, Multilayer Perceptron.