Least Squares Twin-Support Vector Machine was more accurate and faster for diagnosing arrhythmia compared to previous methods.
Does the Least Squares Twin-Support Vector Machine algorithm improve the accuracy and speed of ECG arrhythmia classification compared to previous methods?
The Least Squares Twin-Support Vector Machine algorithm offers a faster and more accurate automated method for ECG arrhythmia classification compared to traditional support vector machines.
Heart disease is one of the most common causes of death. Rapid diagnosis of patients with these diseases can greatly prevent them from sudden death. Today, the diagnosis of heart diseases is done by cardiologist, while achieving an automatic and accurate method for diagnosing has become a challenging issue in this area. Because small changes in the electrocardiogram signals are not recognizable with eyes, and visual disorders may be affected, artificial intelligence and machine learning algorithms can be the solution. In this paper, we use the Least Squares Twin-Support Vector Machine, which unlike ordinary support vector machine, is based on a Non-parallel margin. The results show that the method of this article is better than previous methods, and more accurate and faster for diagnosing arrhythmia.
Refahi et al. (Tue,) conducted a other in Arrhythmia. Least Squares Twin-Support Vector Machine vs. Ordinary support vector machine and previous methods was evaluated on Accuracy and speed of diagnosing arrhythmia. Least Squares Twin-Support Vector Machine was more accurate and faster for diagnosing arrhythmia compared to previous methods.