Key result
SVM-based classification using chaotic and statistical features achieves ~99% accuracy in classifying arrhythmias.
Why the study?
Does combined chaotic and statistical feature extraction with SVM improve arrhythmia classification accuracy in ECG data?
Does combined chaotic and statistical feature extraction with SVM improve arrhythmia classification accuracy in ECG data?
A novel feature extraction method combining chaotic and statistical features with SVM achieved 98.95% accuracy in classifying 16 types of arrhythmias from ECG data.
No takes yet. Share an insight, caveat, or question.
May support automated ECG arrhythmia detection; leaves open clinical utility pending prospective validation.
Jayagopi et al. (2018) studied Arrhythmia. Combined Chaotic and Statistical Feature Extraction with Support Vector Machines was evaluated on Classification accuracy of 16 classes of Arrhythmia. A Support Vector Machine-based classification using combined chaotic and statistical features achieved an accuracy of 98.95% for classifying 16 classes of arrhythmia.