No abstract

In day to day life, continuous monitoring of medical data is essential for many individuals including patients with severe health risks and elderly people. In this paper, one such system is developed for continuous monitoring of Atrial Fibrillation abnormality. Electrocardiographic (ECG) signal monitoring plays a vital role in the management of patients with atrial fibrillation (AF). Atrial Fibrillation (AF) is a type of abnormality in heart, it causes during the AF electrical discharges in the atrium are rapid and results in an abnormal heartbeat. In this paper, ECG signals taken from the MIT-BIH arrhythmia database. After the signal is acquired, the hybrid filtering technique is used to remove the artifacts. Naturally, the ECG signal gets distorted by different types of artifacts which must be removed from the signal otherwise it will convey incorrect information regarding the patient's heart condition. Efficient LMS and Normalized LMS adaptive filters are computationally used for cancellation of noise. Analyzing functions of the filtered signal is Peak Signal to Noise Ratio (PSNR), Mean Square Normalized Error Performance (MSE), Maximum Square Error (MAXERR), the ratio of Squared Norms (L2RAT). The continuous health statistics will be given to individuals and caretaker in the remote location so that they can take necessary action to prevent from health issues. The paper will provide primitive solutions in the field of telemedicine using continuous health monitoring and medical data analysis of a particular individual.In future work, the ECG sensor will acquire the ECG signal and the acquired signal processed through the classification algorithm for classifying the signal into different categories. The biosensor is a combination of the biological element with the physiochemical transducer to produce an electronic signal which can be further converted, processed and transmitted for data analytics, processing, validation, visualization, interpretation, and data logging.