High-Efficiency Algorithm for Cardiac Anomaly Detection and ECG Signal Denoising

The main objective of the study is to establish a new approach for the filtering of noise ECG signals that will in turn help in enhancing detection of CVDs. Their early diagnosis is important if the patient is to survive because they are among the main causes of death around the world. Electrical interference such as noise, baseline wander and mobility artefact are forms of noise that are frequently observed when interpreting ECG. These disturbances reduce the possibility of identifying causes of the illness. To minimize noise in the ECG data, this research employed the Fourier Decomposition Method (FDM). For dealing with complex, nonlinear and non-stationary nature of ECG data, FDM, a Fourier based adaptive decompression technique, has been used. To denoise the signal, the technique splits the noisy information on the group-limited Fourier intrinsic band functions (FIBFs) while preserving the signal essentials. For most comparisons with real-time ECG signals and other databases, FDM is superior to other denoising methods like EMD and WT based on the outcome’s signal to noise ration (SNR) and percentage root mean square difference (PRD). This paper further presents that by employing FDM as a preprocessing mechanism, CVD detection in ECG is enhanced.