Abstract
Worldwide, health care segment is under a severe challenge to achieve more accurate and intelligent biomedical systems in order to assist healthcare professionals with more accurate and consistent data as well as reliability. The role of ECG in healthcare is one of the paramount importances and it has got a multitude of abnormal relations and anomalies which characterizes intricate cardiovascular performance image. Until the recent past, ECG instruments and analysis played the role of providing the PQRST signal as raw observational output either on paper or on a console or in a file having many diagnostic clues embedded in the signal left to the expert cardiologist to look out for characteristic intervals and to detect the cardiovascular abnormality. Methods and practises are required more and more, to automate this process of cardiac expertise using knowledge engineering and an intelligent systems approach. This paper presents one of the challenging R-peak detections to classify diagnosis and estimate cardio disorders in a fully automated signal processing sequence. This study used an adaptive wavelet approach to generate an appropriate wavelet for R-signal identification under noise, baseband wandering and temporal variations of R-positions. This study designed an adaptive wavelet and successfully detected R- peak variations under various ECG signal conditions. The result and analysis of this method and the ways to use it for further purposes are presented here.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call