| Summary: | 碩士 === 元智大學 === 工業工程與管理學系 === 94 === Doctors and medical personnel usually use electrocardiogram (ECG) signal to diagnose the abnormal information of the heart and to classify each kind of ECG. The diagnosis process needs a lot of human resources and time, and it often causes incorrect judgment because of fatigue or personal bias. For this reason, the purpose of this study is how to correctly judge the characteristic R wave of ECG. The methods based on slope concept presented good performances to regular and less noise of on ECG pattern. If there were significant noises on ECG data, it produced several turned points in the region between Q and R wave, and that couldn’t diagnose properly. The research revised So and Chan method and combined with the concept of continuous runs to improve the weakness on QRS complex. The diagnosis technique is trained by Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database and verified by real medical ECG data. The results showed that the revised So and Chan method could obtain better performances than the other traditional methods mentioned literature. The proposed method produces 98.35% accuracy to detect R wave locations on ECG data, and improves shortcoming of So and Chan method effectively.
|
|---|
