<![CDATA[One important step in the process of identifying EKG signals is feature extraction, where the obtained features characterize the condition of the heart. The condition of the heart can be observed based on the waves produced in the EKG signal, which are generated by the electrical activity of the heart. In this study, two types of mother wavelets will be compared to determine which type is most suitable for extracting features from EKG signals. The types of mother wavelets to be compared are Daubechies and Symlet with orders of 5, 6, and 7 for Daubechies, and 6, 7, and 8 for Symlet. EKG signals with MI and normal heart conditions that have been improved in quality and have undergone signal segmentation are extracted using Discrete Wavelet Transformation (DWT) with Daubechies and Symlet mother wavelets at the two-level decomposition, and statistical features such as mean, median, standard deviation, kurtosis, and skewness are taken. Features are extracted from the D2 and D1 sub-bands, resulting in a total of 10 features obtained. The EKG signals are then classified using the KNN method, and to obtain generalized results, K-fold cross-validation is also applied. Based on the experiments conducted, the highest accuracy obtained was 94% with sensitivity and specificity of 82% and 91% by applying the Daubechies mother wavelet of order 7.]]>
Copyrights © 2023
