• Journal of Biomedical Engineering Research
• /
• v.16 no.4
• /
• pp.403-414
• /
• 1995

It is very difficult to quantize the ECG analysis because the decision criterion for ECG is different with each other depending on the medical specialists of the heart and there are measured detecting errors for each ECG measurement system. Therefore, we developed the real-time ECG identification system using digital fuzzy processor for STD-BUS, in order to reduce ambiguity generated in the process of ECG identification and to analyze the irregular ECG stastically to ECG's repetition interval. The variables such as AGE (months), width of QRS, average RRI, and RRI were used to classify the ECG, and were applied to ECG signal indentification system which is developed for the purpose of research. It was found that the automatic diagnosis of ECG signal was possible in the real time process which was impossible in general process of algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2391-2398
• /
• 2009

Premature ventricular contractions are the most common of all arrhythmias and may cause more serious situation in some patients. Therefore, the detection of this arrhythmia becomes crucial in the early diagnosis and prevention of possible life threatening cardiac diseases. Most of the algorithms detecting PVC reported in literature is not always feasible due to the presence of noise and P wave making the detection difficult, and the process being time consuming and ineffective for real time analysis. To solve this problem, a new approach for the detection of PVC is presented based rhythm analysis and beat matching in this paper. For this purpose, the ECG signals are first processed by the usual preprocessing method and R wave was detected. The algorithm that decides beat type using the rhythm analysis of RR interval and beat matching of QRS width is developed. The performance of R wave and PVC detection is evaluated by using MIT-BIH arrhythmia database. The achieved scores indicate sensitivity of 99.74%, positive predictivity of 99.81% and sensitivity of 93.91%, positive predictivity of 96.48% accuracy respectively for R wave and PVC detection.