Počet záznamů: 1
Classification of ECG using ensemble of residual CNNs with or without attention mechanism
- 1.
SYSNO ASEP 0557480 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Classification of ECG using ensemble of residual CNNs with or without attention mechanism Tvůrce(i) Nejedlý, Petr (UPT-D) RID, SAI
Ivora, Adam (UPT-D)
Viščor, Ivo (UPT-D) RID, ORCID, SAI
Koščová, Zuzana (UPT-D)
Smíšek, Radovan (UPT-D) RID, ORCID, SAI
Jurák, Pavel (UPT-D) RID, ORCID, SAI
Plešinger, Filip (UPT-D) RID, ORCID, SAICelkový počet autorů 7 Číslo článku 044001 Zdroj.dok. Physiological Measurement. - : Institute of Physics Publishing - ISSN 0967-3334
Roč. 43, č. 4 (2022)Poč.str. 12 s. Forma vydání Tištěná - P Jazyk dok. eng - angličtina Země vyd. GB - Velká Británie Klíč. slova ECG ; classification ; deep learning ; PhysioNet challenge 2021 ; attention mechanism Vědní obor RIV FS - Lékařská zařízení, přístroje a vybavení Obor OECD Medical engineering CEP FW01010305 GA TA ČR - Technologická agentura ČR Způsob publikování Omezený přístup Institucionální podpora UPT-D - RVO:68081731 UT WOS 000790542900001 EID SCOPUS 85129997154 DOI 10.1088/1361-6579/ac647c Anotace Objective. This paper introduces a winning solution (team ISIBrno-AIMT) to the official round of PhysioNet Challenge 2021. The main goal of the challenge was a classification of ECG recordings into 26 multi-label pathological classes with a variable number of leads (e.g. 12, 6, 4, 3, 2). The main objective of this study is to verify whether the multi-head-attention mechanism influences the model performance. Approach. We introduced an ECG classification method based on the ResNet architecture with a multi-head attention mechanism for the official round of the challenge. However, empirical findings collected during model development suggested that the multi-head attention layer might not significantly impact the final classification performance. For this reason, during the follow-up round, we removed a multi-head attention layer to test the influence on model performance. Like the official round, the model is optimized using a mixture of loss functions, i.e. binary cross-entropy, custom challenge score loss function, and custom sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final architecture consists of three submodels forming a majority voting classification ensemble. Main results. The modified model without the multi-head attention layer increased the overall challenge score to 0.59 compared to the 0.58 from the official round. Significance. Our findings from the follow-up submission support the fact that the multi-head attention layer in the proposed architecture does not significantly affect the classification performance. Pracoviště Ústav přístrojové techniky Kontakt Martina Šillerová, sillerova@ISIBrno.Cz, Tel.: 541 514 178 Rok sběru 2023 Elektronická adresa https://iopscience.iop.org/article/10.1088/1361-6579/ac647c
Počet záznamů: 1