An Arrhythmia Classification Method in Utilizing the Weighted KNN and the Fitness Rule

- The present study combines features extracted through principal component analysis and linear discriminant analysis, and it proposes a method of classifying arrhythmia using the fitness rules and weighted K-nearest neighbor based on the combined features.
- The proposed method showed slightly better results when the data were classified using the combination of features extracted through PCA and LDA than when the data were classified using features extracted through either PCA or LDA.
- The efficiency of the algorithm was shown by improving the accuracy using the WKNN and fitness rules.