Print Email Facebook Twitter Severity-based Hierarchical ECG Classification using Neural Networks Title Severity-based Hierarchical ECG Classification using Neural Networks Author Diware, S.S. (TU Delft Computer Engineering) Dash, Sudeshna (ASML) Gebregiorgis, A.B. (TU Delft Computer Engineering) Joshi, Rajiv V. (IBM Thomas J. Watson Research Centre) Strydis, C. (TU Delft Computer Engineering; Erasmus MC) Hamdioui, S. (TU Delft Quantum & Computer Engineering) Bishnoi, R.K. (TU Delft Computer Engineering) Department Quantum & Computer Engineering Date 2023 Abstract Timely detection of cardiac arrhythmia characterized by abnormal heartbeats can help in the early diagnosis and treatment of cardiovascular diseases. Wearable healthcare devices typically use neural networks to provide the most convenient way of continuously monitoring heart activity for arrhythmia detection. However, it is challenging to achieve high accuracy and energy efficiency in these smart wearable healthcare devices. In this work, we provide architecture-level solutions to deploy neural networks for cardiac arrhythmia classification. We have created a hierarchical structure after analyzing various neural network topologies where only required network components are activated to improve energy efficiency while maintaining high accuracy. In our proposed architecture, we introduce a severity-based classification approach to directly help the users of the wearable healthcare device as well as the medical professionals. Additionally, we have employed computation-in-memory based hardware to improve energy efficiency and area consumption by leveraging in-situ data processing and scalability of emerging memory technologies such as resistive random access memory (RRAM). Simulation experiments conducted using the MIT-BIH arrhythmia dataset show that the proposed architecture provides high accuracy while consuming average energy of 0.11 $\mu$J per heartbeat classification and 0.11 mm2 area, thereby achieving 25× improvement in average energy consumption and 12× improvement in area compared to the state-of-the-art. Subject ECGarrhythmiaseverity-based classificationneural networkscomputation-in-memoryresistive random access memory (RRAM) To reference this document use: http://resolver.tudelft.nl/uuid:84bd18e2-e9c1-4d83-8ba8-dfdf92ca6f3a DOI https://doi.org/10.1109/TBCAS.2023.3242683 Embargo date 2023-08-07 ISSN 1932-4545 Source IEEE Transactions on Biomedical Circuits and Systems, 17 (1), 77-91 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2023 S.S. Diware, Sudeshna Dash, A.B. Gebregiorgis, Rajiv V. Joshi, C. Strydis, S. Hamdioui, R.K. Bishnoi Files PDF Severity_Based_Hierarchic ... tworks.pdf 5.21 MB Close viewer /islandora/object/uuid:84bd18e2-e9c1-4d83-8ba8-dfdf92ca6f3a/datastream/OBJ/view