Clustering analysis strategy of online Ambulatory Electrocardiogram waveforms

Two challenges make it difficult to cluster on-line AECG (Ambulatory Electrocardiogram) data. They are huge amount ECG (Electrocardiogram) waveforms and high dimension vector to describe individual ECG waveforms. A new strategy is proposed in the paper, it does not lose the clustering accuracy with reduced the ECG vector dimension data. In reducing ECG vector dimension, Sanger neural network was introduced, its time-consuming is the least among others methods. In clustering analysis, Simulated Annealing algorithm was introduced to improve the effect of clustering result. Through experiments and comparison with other strategy, the proposed strategy reach 94.40% average accuracy rate and nearly 1/4 time consuming.