Automated Detection of Sudden Cardiac Death by Discrete Wavelet Transform of Electrocardiogram Signal

Sudden cardiac death (SCD) results in millions of deaths annually; as it is a fatal heart abnormality, early prediction SCD could save peoples’ lives to the greatest extent. Symmetry and asymmetry play an important role many fields. Electrocardiograms (ECG) noninvasive process for acquiring electrical activity heart, has both asymmetric non-stationary characteristics; frequently employed diagnose evaluate heart’s condition. In this work, we have detected 14 min (separately each one-minute interval) prior its occurrence by analyzing ECG signals using discrete wavelet transform (DWT) locality preserving projection (LPP). experiment, performed DWT on obtain coefficients, then LPP reduction methodology was used cut down these obtained coefficients. Then, acquired features were ranked various methods, including T-test, Bhattacharyya, Wilcoxon, entropy. At last, highly subjected decision tree, k-nearest neighbor (KNN), support vector machine classifiers distinguishing normal from signals. Our proposed technique achieved highest accuracy 97.6% detection KNN classifier, compared existing works. method capable predicting people at risk developing before onset, and, hence, clinicians would enough time provide treatment intensive care units (ICU) subject SCD. Thus, useful tool can increase survival rate patients.