Published Paper Details:

Traditional arrhythmia detection methods often focus solely on identifying irregular heart rhythms, frequently neglecting the quality of the input signal, which can lead to inaccuracies. This study proposes a novel approach that incorporates signal quality assessment as a preliminary step in arrhythmia detection, significantly enhancing reliability. By leveraging advanced deep learning models such as CNNs, RNNs, and FCNNs, combined with signal processing techniques, our method evaluates signal quality prior to detecting arrhythmic events, ensuring a more robust analysis. The proposed approach is tested on diverse datasets, demonstrating notable improvements in detection accuracy and signal quality evaluation. Comparative analyses, with and without signal quality assessment, further underscore the advantages of this technique over conventional methods. By integrating quality-aware detection into routine cardiac monitoring, this method holds the potential to reduce false alarms, improve detection precision, and advance arrhythmia management in clinical practice.