Dipper Throated Algorithm for Feature Selection and Classification in Electrocardiogram

Arrhythmia has been classified using a variety of methods. Because the dynamic nature electrocardiogram (ECG) data, traditional handcrafted approaches are difficult to execute, making machine learning (ML) solutions more appealing. Patients with cardiac arrhythmias can benefit from competent monitoring save their lives. Cardiac arrhythmia classification and prediction have greatly improved in recent years. Arrhythmias category conditions which heart's electrical activity is abnormally rapid or sluggish. Every year, it one main reasons mortality for both men women, worldwide. For arrhythmias, this work proposes novel technique based on optimized feature selection K-nearest neighbors (KNN) classifier. The proposed method makes advantage UCI repository, 279-attribute high-dimensional dataset. approach dividing patients into 16 groups electrocardiography dataset’s features. purpose design an efficient intelligent system employing dipper throated optimization categorize patients. This comprehensive outperforms earlier methods presented literature. achieved accuracy 99.8%.