Key result
A multi-swarm optimization neural network combined with fuzzy FIR filtering achieved 87% accuracy in denoising ECG signals, outperforming existing approaches even with small datasets.
Why the study?
The presence of noise and artifacts complicates accurate detection of cardiovascular disease on ECG, necessitating reliable noise removal.
Does the use of RBF and MSONN with fuzzy FIR filtering improve noise reduction accuracy in ECG signals compared to existing approaches?
Does the use of RBF and MSONN with fuzzy FIR filtering improve noise reduction accuracy in ECG signals compared to existing approaches?
A novel approach using neural networks and fuzzy FIR filtering achieves 87% accuracy in denoising ECG signals, potentially improving the reliability of cardiovascular disease detection.
Cardiovascular disease (CVD) has been identified as a threat to human life for decades, with the majority of individuals dying as a result of delayed diagnosis and treatment. An electrocardiogram (ECG) plays a vital role in the prognosis of such an ailment. The presence of noise and artifacts complicates the accurate detection and identification of CVD. As a result, reliable signal recovery tasks necessitate noise removal, which is an inverse problem. The main noises present in electrocardiogram (ECG) signals are EMG noise, electrode motion artifact noise. In this paper, radial basis function (RBF) and multi swarm optimization neural network (MSONN) are used to denoise the ECG signal. The cut-off frequency is calculated using a low-pass filter. By using, fuzzy FIR filtering technique baseline wander noises can be removed. Results show that MOS based approach outperforms existing approaches in terms of accuracy and is observed to be 87% even when the dataset size is small. Further, noises if any exists are also removed by the use of cascaded multiplier less Fuzzy FIR filters
No takes yet. Share an insight, caveat, or question.
Tallapragada et al. (2022) studied Cardiovascular disease (ECG signal denoising). Radial basis function (RBF) and multi swarm optimization neural network (MSONN) with fuzzy FIR filtering vs. Existing approaches was evaluated on Accuracy of noise removal. A multi-swarm optimization neural network combined with fuzzy FIR filtering achieved 87% accuracy in denoising ECG signals, outperforming existing approaches even with small datasets.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: