A fuzzy sets method for classification of arrhythmias is developed in this work.At first R-R and QRS interval are transformed into fuzzy variables with S-style and Z-style membership functions.Then their grades of membership for normal and beats of PVC and APC are calculated to determine the classification.The method is verified with MIT-BIH database and the clinical data.The results show that this method is effective for the classification of arrhythmias accurately and rapidly.