RESUMO
According to the characteristics of ECG analysis, large data quantum, high accuracy demand and real-time, a classified algorithm of arrhythmia based on clustering analysis is presented in this paper. According to "things-of-one-kind-come-together" principle, this algorithm uses the similarities of cases with same kind of heart disease at the same time, includes the factors of the individual difference to analyze arrhythmias by clustering QRS complex waveform and rhythm analysis as the subordinate method. Verified by eight records of MIT-BIR standard heart electricity database, the probability of correct clustering reaches above 90%, which shows that this algorithm can analyze arrhythmias effectively.
Assuntos
Arritmias Cardíacas/diagnóstico , Análise por Conglomerados , Eletrocardiografia/estatística & dados numéricos , Algoritmos , Bases de Dados Factuais , Humanos , Processamento de Sinais Assistido por ComputadorRESUMO
To satisfy the difficult requirements of ECG analysis such as large data volume, high accuracy and real-time, a classification algorithm for arrhythmia based on clustering analysis is developed. According to things-of-one-kind-come-together principle, this algorithm uses the similarity of heart cases of the same category and, at the same time, incorporates the factor of individual differences. It analyzes arrhythmia by clustering QRS complex waveforms and applies rhythm analysis as the subordinate method. Verified by eight records of MIT-BIH arrhythmia standard heart electricity database, the clustering correct rate reaches above 90%, which shows that this algorithm can analyze arrhythmia effectively.