A New Clustering Strategy in Ambulatory Electrocardiogram Waveform

Ambulatory electrocardiogram is used to record about 24 hours electrocardiogram waveform. The purpose is to find out the conspicuous variation in the recording data. A new strategy used to cluster the electrocardiogram waveform is presented in this paper. The aim of that is to obtain more accurate clustering results. After the controlled trial on MIT/BIH data, it can be safely concluded that the clustering result achieved by improved strategy can got more accurate than that by the traditional clustering algorithm. An average accuracy ratio is about 94.6%, 1.6% higher than k-means algorithm averagely and 1.3% higher than simulated annealing algorithm averagely.