Cardiac Arrhythmia Diagnosis Using a Neuro-Fuzzy Approach

Abstract

The ventricular premature contractions (VPC) are cardiac arrhythmias that are widely encountered in the cardiologic field. They can be detected using the electrocardiogram (ECG) signal parameters. A novel method for detecting VPC from the ECG signal is proposed using a new algorithm (Slope) combined with a fuzzy-neural network (FNN). To achieve this objective, an algorithm for QRS detection is first implemented, and then a neuro-fuzzy classifier is developed. Its performances are evaluated by computing the percentages of sensitivity (SE), specificity (SP), and correct classification (CC). This classifier allows extraction of rules (knowledge base) to clarify the obtained results. We use the medical database (MIT-BIH) to validate our results.

ECG Signal Classification for Remote Area Patients Using Artificial Neural Networks in Smartphone

“…Many study proposed various method of algorithm for classification and feature extractions of ECG signals [1]- [6]. One of those focused on the application of cutting-edge technology and computational algorithm for grouping of cardiac arrhythmia [7].…”

ECG Decision Support System based on feedforward Neural Networks

“…These ML approaches are recently executed to classify ECG abnormalities (Sonawane et al, 2013). So, among the most widely used ML classification approaches, we found the Fuzzy Logic (Ozbay et al, 2006), the Neuro-Fuzzy Networks (Benali et al, 2010;Haihua et al, 2015), the Support Vector Machine (Kohli et al, 2010), the Genetic Algorithms (Martis and Chakraborty, 2011), and the Artificial Neural Networks (ANN) (Che Soh et al, 2014). By the way, referring to literature, ANNs are among the most implemented on ECG arrhythmia classification (Kelwade and Salankar, 2015;Berkaya et al, 2018), since they are consistent in giving accurate results (Silipo and Marchesi, 1998).…”