<![CDATA[Ventricular Fibrillation (VF) is a life-threatening heart rhythm disorder characterised by irregular and uncoordinated electrical activity of the heart that causes the heart to stop suddenly. An Electrocardiogram (ECG) is a medical test that detects heart abnormalities by measuring the electrical activity of the heart during contraction. The ECG in the VF shows very different characteristics from the normal heart rhythm, with loss of P waves and a regular QRS complex, replaced by rapid, irregular, and variable fibrillation waves of variable amplitude. A Support Vector Machine (SVM) is a type of Machine Learning that seeks the best hyperplane to separate classes. The kernel used in this study is best obtained by using the Quadratic Kernel. This study aims to detect Ventricular Fibrillation (VF) or Non-VF from ECG signals using Support Vector Machine (SVM). Preprocessing in this study: window size of ECG signals (5 seconds and 10 seconds), followed by a High Pass Filter, a Second Order Butterworth Low Pass Filter, and a Notch Filter. The characteristics used for extraction are Area Calculation (in this study, proposes using Ratio Area) and Spectral Analysis (FSMN, A1, A2, A3). Combinations of one to five of these trait extracts were trained and tested using SVM. The results obtained showed a combination of three characteristic extractions: FSMN-A1-A2 achieved the highest performance with 97% accuracy, 100% sensitivity, 94% specificity and the FSMN-A2-R characteristic extraction combination. The Area achieves 97% accuracy, 98% sensitivity, and 96% specificity. Adding trait extraction from three to four did not significantly improve performance.]]>
