Rectified Adam Optimizer and LSTM with Attention Mechanism for ECG-Based Multi-class Classification of Cardiac Arrhythmia

Simple item page
dc.contributor.authorSivaranjani, T.
dc.contributor.authorSasikumar, B.
dc.contributor.authorSugitha, G.
dc.coverage.issue2cs
dc.coverage.volume34cs
dc.date.accessioned2025-05-12T08:56:24Z
dc.date.available2025-05-12T08:56:24Z
dc.date.issued2025-06cs
dc.description.abstractCardiac Arrhythmia (CA) is one of the most prevalent cardiac conditions and prime reasons for sudden death. The current CA detection methods face challenges in noise removal, R-peak detection, and low-level feature selection, which can impact diagnostic accuracy and signal stability. The research aims to develop an effective framework for detecting and classifying CA using advanced signal processing, feature extraction, feature selection, and classification for reliable medical diagnosis. The input electrocardiogram (ECG) signals are processed using hybrid noise reduction techniques such as cascaded variable step size normalized least mean square and sparse low-rank filter. The complex and high-level features are extracted using higher-order spectral energy distributed image, wavelet transform, and R-wave peak to R-wave peak interval to enhance the representation of cardiac data. Recursive feature elimination is applied to select the most relevant diagnostic features and the Rectified Adam optimizer is used to fine-tune parameters to achieve better training stability. The model integrates long-term memory with an attention mechanism to enhance the classification performance of arrhythmia detection. Simulation results demonstrate that the proposed model achieves 99.40% accuracy, outperforming existing models and showing its efficiency in classifying CA for better diagnosis and early treatments.en
dc.formattextcs
dc.format.extent195-205cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRadioengineering. 2025 vol. 34, č. 2, s. 195-205. ISSN 1210-2512cs
dc.identifier.doi10.13164/re.2025.0195en
dc.identifier.issn1210-2512
dc.identifier.urihttps://hdl.handle.net/11012/250914
dc.language.isoencs
dc.publisherRadioengineering Societycs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttps://www.radioeng.cz/fulltexts/2025/25_02_0195_0205.pdfcs
dc.rightsCreative Commons Attribution 4.0 International licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectCardiac arrhythmiaen
dc.subjectelectrocardiogramen
dc.subjectsparse low-rank filteren
dc.subjectrecursive feature eliminationen
dc.subjectlong short-term memoryen
dc.subjectrectified Adam optimizeren
dc.subjectattention mechanismen
dc.titleRectified Adam Optimizer and LSTM with Attention Mechanism for ECG-Based Multi-class Classification of Cardiac Arrhythmiaen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
25_02_0195_0205.pdf
Size:
1.4 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
2025/2