High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network

Kai Fen Chang; Yuan Ho Chen

doi:10.1109/ISOCC56007.2022.10031526

High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network

Kai Fen Chang
, Yuan Ho Chen

Department of Electronic Engineering

Chang Gung University
Chang Gung Memorial Hospital

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Arrhythmias can be a sign of heart disease. If the heart is abnormal, using a wearable to monitor the heart rate can help us seek immediate medical attention. This work uses a deep learning network to build a simple architecture with only 3 layers that can achieve 98.5% high accuracy. Of the 3 layers, only 2 have computational power, Dense and Softmax. Therefore, the use of multipliers is reduced, and the area can be reduced in hardware implementation. This work implemented the proposed chip using TSMC 90nm CMOS technology, realizing a chip with an operating frequency of 50MHz, an area of 0.654 × 0.651mm2, and maximum power consumption of 0.64 mW.

Original language	English
Title of host publication	Proceedings - International SoC Design Conference 2022, ISOCC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	177-178
Number of pages	2
ISBN (Electronic)	9781665459716
DOIs	https://doi.org/10.1109/ISOCC56007.2022.10031526
State	Published - 2022
Event	19th International System-on-Chip Design Conference, ISOCC 2022 - Gangneung-si, Korea, Republic of Duration: 19 10 2022 → 22 10 2022

Publication series

Name	Proceedings - International SoC Design Conference 2022, ISOCC 2022

Conference

Conference	19th International System-on-Chip Design Conference, ISOCC 2022
Country/Territory	Korea, Republic of
City	Gangneung-si
Period	19/10/22 → 22/10/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Electrocar-diogram (ECG)
Very-large-scale integration (VLSI)
convolutional neural network (CNN)

Access to Document

10.1109/ISOCC56007.2022.10031526

Cite this

@inproceedings{afd3811a231f4fc59679fca586bb1427,

title = "High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network",

abstract = "Arrhythmias can be a sign of heart disease. If the heart is abnormal, using a wearable to monitor the heart rate can help us seek immediate medical attention. This work uses a deep learning network to build a simple architecture with only 3 layers that can achieve 98.5\% high accuracy. Of the 3 layers, only 2 have computational power, Dense and Softmax. Therefore, the use of multipliers is reduced, and the area can be reduced in hardware implementation. This work implemented the proposed chip using TSMC 90nm CMOS technology, realizing a chip with an operating frequency of 50MHz, an area of 0.654 {\texttimes} 0.651mm2, and maximum power consumption of 0.64 mW.",

keywords = "Electrocar-diogram (ECG), Very-large-scale integration (VLSI), convolutional neural network (CNN)",

author = "Chang, \{Kai Fen\} and Chen, \{Yuan Ho\}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th International System-on-Chip Design Conference, ISOCC 2022 ; Conference date: 19-10-2022 Through 22-10-2022",

year = "2022",

doi = "10.1109/ISOCC56007.2022.10031526",

language = "英语",

series = "Proceedings - International SoC Design Conference 2022, ISOCC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "177--178",

booktitle = "Proceedings - International SoC Design Conference 2022, ISOCC 2022",

address = "美国",

}

Chang, KF & Chen, YH 2022, High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network. in Proceedings - International SoC Design Conference 2022, ISOCC 2022. Proceedings - International SoC Design Conference 2022, ISOCC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 177-178, 19th International System-on-Chip Design Conference, ISOCC 2022, Gangneung-si, Korea, Republic of, 19/10/22. https://doi.org/10.1109/ISOCC56007.2022.10031526

High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network. / Chang, Kai Fen; Chen, Yuan Ho.
Proceedings - International SoC Design Conference 2022, ISOCC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 177-178 (Proceedings - International SoC Design Conference 2022, ISOCC 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network

AU - Chang, Kai Fen

AU - Chen, Yuan Ho

PY - 2022

Y1 - 2022

N2 - Arrhythmias can be a sign of heart disease. If the heart is abnormal, using a wearable to monitor the heart rate can help us seek immediate medical attention. This work uses a deep learning network to build a simple architecture with only 3 layers that can achieve 98.5% high accuracy. Of the 3 layers, only 2 have computational power, Dense and Softmax. Therefore, the use of multipliers is reduced, and the area can be reduced in hardware implementation. This work implemented the proposed chip using TSMC 90nm CMOS technology, realizing a chip with an operating frequency of 50MHz, an area of 0.654 × 0.651mm2, and maximum power consumption of 0.64 mW.

AB - Arrhythmias can be a sign of heart disease. If the heart is abnormal, using a wearable to monitor the heart rate can help us seek immediate medical attention. This work uses a deep learning network to build a simple architecture with only 3 layers that can achieve 98.5% high accuracy. Of the 3 layers, only 2 have computational power, Dense and Softmax. Therefore, the use of multipliers is reduced, and the area can be reduced in hardware implementation. This work implemented the proposed chip using TSMC 90nm CMOS technology, realizing a chip with an operating frequency of 50MHz, an area of 0.654 × 0.651mm2, and maximum power consumption of 0.64 mW.

KW - Electrocar-diogram (ECG)

KW - Very-large-scale integration (VLSI)

KW - convolutional neural network (CNN)

UR - https://www.scopus.com/pages/publications/85148451896

U2 - 10.1109/ISOCC56007.2022.10031526

DO - 10.1109/ISOCC56007.2022.10031526

M3 - 会议稿件

AN - SCOPUS:85148451896

T3 - Proceedings - International SoC Design Conference 2022, ISOCC 2022

SP - 177

EP - 178

BT - Proceedings - International SoC Design Conference 2022, ISOCC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 19th International System-on-Chip Design Conference, ISOCC 2022

Y2 - 19 October 2022 through 22 October 2022

ER -

High Accuracy Abnormal ECG Detection Chip Using a Simple Neural Network

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this