Document Type : Primary Research paper
Authors
1
Research Scholar, Sathyabama Institute of Science and Technology (Deemed to be University), Jeppiaar Nagar, Rajiv Gandhi Salai, Chennai - 600 119. Tamil Nadu, India. Asst. Professor, Department of E&TC Engineering & Associate Dean – IR, Trinity College of Engineering and Research, Pisoli, Pune-411048, MH, India.
2
Director (Research) and Professor, Sathyabama Institute of Science and Technology (Deemed to be University), Jeppiaar Nagar, Rajiv Gandhi Salai, Chennai - 600 119.Tamil Nadu, India.
3
Vice-Principal and Professor of ECE Department, SRM Valliammai Engineering College, Kattankulathur - 603203, Chengalpet (Dist.) Tamil Nadu, India.
4
PG student of Digital Electronics Engineering, Trinity College of Engineering and Research, Pisoli, Pune-411048, MH, India.
Abstract
CVD (Cardiovascular) Diseases is leading cause of human deaths globally. The increasing threats of CVD can be early detected with various medical tests, including electrocardiogram (ECG), and also 2D Echo, Stress Test. As ECG is non-invasive, clinical therapeutic agent, so with the help of an ECG signal, early detection of CVD is possible and proper medication can be provided for human life. All these signals from different equipment can, however, be non-stationary and repetitive, which takes more time to process and exhausting for physical examination. Moreover, Heart Signal from ECG machine is not a stationary indicator, the discrepancies might not be repeated and may demonstrate up at various periods, hence there is a need to adopt a computer aided model for fast and accurate prognosis of CVD’s. Similarly, the pre-processing of ECG signals is crucial as ECG signals are generally consists of various types of drift called as noise as well as various types of artifacts. During the preprocessing step, our main objective is to reduce or overcome on this noise so that we can able to get the proper de-noised signal which will help to decide the fiduciary points (P, Q, R, S, T), its event, non-event phenomenon such as P-wave, QRS-complex, T-wave, PQ-segment, ST- segment. Typical types of noise may have categories such as a power line intrusion, baseline wander, and noisy contact data of electrode, electrode motion artifacts, muscle contraction, and instrumentation noise. In this paper, we are focusing the preprocessing of the ECG signals through various filters accessible, so we can eliminate the undesirable noise through the original ECG data signal that will help us evaluate the clean signal which will contribute to predict the accurate result in classification.
Keywords
)