Key result
The proposed Wavelet Coherence technique optimized with Firefly Algorithm and classified using Levenberg Marquardt Neural Network achieved 99.1% accuracy in detecting atrial fibrillation.
Why the study?
Does a Wavelet Coherence and Firefly Algorithm-based neural network improve the detection accuracy of atrial fibrillation from ECG signals?
Does a Wavelet Coherence and Firefly Algorithm-based neural network improve the detection accuracy of atrial fibrillation from ECG signals?
Absolute Event Rate: 99.1% vs 90.1%
A novel machine learning approach using Wavelet Coherence and Firefly Algorithm demonstrated high accuracy (99.1%) in detecting atrial fibrillation from ECG signals.
Requires clinical validation before AF detection use; leaves open real-world performance of this ML approach.
Atrial Fibrillation (AF) is a common type of heart abnormality. During the AF electrical discharges in the atrium are rapid that results in irregular heart beat. The morphology of ECG changes due to the abnormalities in the heart. This paper consists of three major steps for the detection of heart diseases: signal pre-processing, feature extraction and classification. Feature extraction is the key process in detecting the heart abnormality. Most of the ECG detection systems depend on the time domain features for cardiac signal classification. In this paper we proposed a Wavelet Coherence (WTC) technique for ECG signal analysis. The WTC measures the similarity between two waveforms in frequency domain. Parameters extracted from WTC function is used as the features of the ECG signal. These features are optimized using Firefly algorithm (FFA). The optimized features from the FFA are given as the input to the Levenberg Marquardt Neural Network (LM NN) classifier. From the literature it is observed that the performance of the classifier is improved with the help of the optimized (reduced) features.
No takes yet. Share an insight, caveat, or question.
Kora et al. (2018) studied Atrial Fibrillation (n=44). Wavelet Coherence (WTC) with Firefly Algorithm (FFA) and Levenberg Marquardt Neural Network (LM NN) vs. Auto Regressive (AR) method and other traditional feature extraction techniques was evaluated on Classification accuracy for Atrial Fibrillation detection. The proposed Wavelet Coherence technique optimized with Firefly Algorithm and classified using Levenberg Marquardt Neural Network achieved 99.1% accuracy in detecting atrial fibrillation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: