Key result
FFT-improved AlexNet classifier detects cardiac arrhythmias with ~100% accuracy, outperforming traditional systems.
Why the study?
ECG signal processing for arrhythmia detection requires effective feature extraction and classification methods to improve diagnostic accuracy.
Does an FFT-based improved AlexNet classifier improve the detection of arrhythmias from ECG records compared to traditional systems?
Population
ECG records containing four types of arrhythmia conditions
Comparison
FFT-based improved AlexNet classifier vs other algorithms/traditional systems
Design
Simulation study using machine learning classification algorithms
Authors
Loading...
May aid automated ECG screening if validated; leaves open prospective clinical trials before practice change.
Does an FFT-based improved AlexNet classifier improve the detection of arrhythmias from ECG records compared to traditional systems?
An FFT-based improved AlexNet classifier improves the detection of arrhythmias from ECG records by 20% compared to traditional systems.
Arvind Chakrapani (2022) studied Cardiac arrhythmias (n=47). FFT-based improved AlexNet classifier vs. Traditional ECG classification systems was evaluated on Classification accuracy. The proposed FFT-based improved AlexNet classifier achieved a 99.7% detection accuracy in classifying ECG signals for cardiac arrhythmias, improving deviation detection by 20% over traditional systems.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: