Very-large-scale integration implementation of a convolutional neural network accelerator for abnormal heartbeat detection

Y. H. Chen*, Y. Juan

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

8 Scopus citations

Abstract

In this study, a very-large-scale integration implementation of a convolutional neural network (CNN) inference for abnormal heartbeat detection was proposed. Four-lead electrocardiogram signals were used to detect abnormal heartbeat conditions, such as premature ventricular complex. 1D CNNs and fully connected layers were utilised in the proposed chip to achieve high-speed, small-area, and high-accuracy arrhythmia detection. The proposed chip was implemented using a 90-nm complementary metal-oxide-semiconductor process and operated at 125 MHz with a 0.67mm2 core area. The power consumption was 4.18mW at high-speed operation frequency (125 MHz) and 3.79μW at 10 kHz for low-power applications. The detection accuracy was 95.14% based on the MIT-BIH arrhythmia database. Consequently, the properties of high speed, low power, small area, and high accuracy were established in the proposed accelerator chip.

Original languageEnglish
Pages (from-to)330-331
Number of pages2
JournalElectronics Letters
Volume56
Issue number7
DOIs
StatePublished - 30 03 2020

Bibliographical note

Publisher Copyright:
© 2020 The Institution of Engineering and Technology.

Fingerprint

Dive into the research topics of 'Very-large-scale integration implementation of a convolutional neural network accelerator for abnormal heartbeat detection'. Together they form a unique fingerprint.

Cite this