Abstract: This paper presents the design of an energy-efficient Electrocardiogram (ECG) processor for arrhythmia detection and classification of life-threatening arrhythmia plays an important part in dealing with various cardiac conditions. It provides better time and frequency resolution of the Electrocardiogram (ECG) signal, which helps in decoding important information of an ECG, which improves the arrhythmia classification. The decisions can be achieved by determining different intervals such as PR Interval, RR Interval, Heart Rate etc. and those intervals will be compared with the ideal intervals. During the whole process Modelsim was used & ECG signals were taken from PhysioBank ATM. The proposed QRS detection architecture deals with almost all the ECG signal artifacts, such as low-frequency noise, baseline drift, and high-frequency interference with minimum hardware resources. Few metrics needed to be concerned during the implementation of ECG processor are Accuracy (low detection error-rate), Area (hardware resource utilization), Power efficiency (low power consumption), Speed (delay), Sensitivity (real time monitoring) And Predictivity. Thereby, in this proposed project we are going to simulate the results and compare few performance metrics with the existing methodology.
Keywords: Electrocardiogram, QRS complex, hybrid classifier, multi-scaled product, soft-threshold algorithm, wavelet ECG detector.
| DOI: 10.17148/IJIREEICE.2020.8906