A novel multichannel sparse convolutional autoencoder for electrocardiogram signal compression

Basit Öğe Kaydı
dc.authorid0009-0009-5059-965X
dc.authorid0000-0001-9213-576X
dc.authorid0000-0002-0664-649X
dc.contributor.authorBekiryazici, Tahir
dc.contributor.authorDamkaci, Mehmet
dc.contributor.authorAydemir, Gurkan
dc.contributor.authorGurkan, Hakan
dc.date.accessioned2026-02-08T15:15:20Z
dc.date.available2026-02-08T15:15:20Z
dc.date.issued2025
dc.departmentBursa Teknik Üniversitesi
dc.description.abstractElectrocardiogram (ECG) signal compression is paramount in continuously monitoring cardiac patients, as it reduces data storage and transmission costs. Deep neural networks, particularly autoencoders, offer significant potential for compressing ECG signals by mapping them to lower-dimensional spaces. This paper presents a novel multichannel convolutional autoencoder model designed to compress ECG signals efficiently. The proposed approach encodes the ECG signal into a four-channel lower-dimensional space using a convolutional encoder, which is subsequently reconstructed by a deconvolutional decoder. Unlike traditional autoencoderbased methods, the first channel in the model remains unconstrained, while increasing levels of sparsity constraints are imposed on the remaining channels. Different quantization levels are applied to each channel to optimize compression further, reflecting the varying numerical ranges caused by the sparsity constraints. The quantized channels are then encoded using Huffman coding, resulting in a higher compression ratio. The model's effectiveness is evaluated on a popular benchmark dataset, using normalized percent root mean square difference (PRDN) error and compression ratio as performance metrics. The proposed method achieves an average compression ratio of 20.23:1, with an average PRDN error of 9.86%, demonstrating its capability to compress ECG signals efficiently while maintaining reconstruction accuracy.
dc.identifier.doi10.1016/j.jelectrocard.2025.154125
dc.identifier.issn0022-0736
dc.identifier.issn1532-8430
dc.identifier.pmid41092549
dc.identifier.scopus2-s2.0-105018630179
dc.identifier.scopusqualityQ3
dc.identifier.urihttps://doi.org/10.1016/j.jelectrocard.2025.154125
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5723
dc.identifier.volume93
dc.identifier.wosWOS:001598909800003
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherChurchill Livingstone Inc Medical Publishers
dc.relation.ispartofJournal of Electrocardiology
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzWOS_KA_20260207
dc.subjectECG
dc.subjectECG compression
dc.subjectSparse autoencoders
dc.subjectConvolutional autoencoders
dc.titleA novel multichannel sparse convolutional autoencoder for electrocardiogram signal compression
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu