A Low Complexity ANFIS Approach for Premature Ventricular Contraction Detection Based on Backward Elimination

Premature ventricular contraction (PVC) is one of the common cardiacarrhythmias. The occurrence of PVC is dangerous in people who have recentlyundergone heart. A PVC beat can easily be diagnosed by a doctor based on theshape of the electrocardiogram signal. But in automatic detection, extractingseveral important features from each beat is required. In this paper, a method forautomatic detection of PVC using adaptive neuro-fuzzy inference systems (ANFIS) ispresented. In the proposed model first feature selection has been done usingbackward elimination algorithm, and then an ANFIS has been trained with selectedattributes. The performance of the proposed method has been compared with twoother methods. Simulation results show that the proposed algorithm, in addition tomaintaining the classification accuracy compared to existing methods uses fewerfeatures and requires less computing time, which is suitable for implementation on hardware with limited processing capability.

Keywords:

PVC , Neural Networks , Fuzzy Networks , ANFIS , Feature Selection