Feature selection algorithm for ECG signals using Range-Overlaps Method

This study proposes a simple and reliable feature selection algorithm for ECG signals, termed the Range-Overlaps Method. The proposed method has the advantages of good detection results, no complex mathematic computations, fast and low memory space and low time complexity. Both cluster analysis and fuzzy logic methods are applied to evaluate the performance of the proposed method. Experimental results show that the total classification accuracy is above 93%. Thus, the proposed algorithm provides an efficient, simple and fast method for feature selection on ECG signals.