Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach

Song Nien Tang; Yuan Ho Chen; Yu Wei Chang; Yu Ting Chen; Shuo Hung Chou

doi:10.1109/ISOCC59558.2023.10396448

Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach

Song Nien Tang^*, Yuan Ho Chen, Yu Wei Chang, Yu Ting Chen, Shuo Hung Chou

^*此作品的通信作者

電子工程學系(含學碩博士班)

Chung Yuan Christian University

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同行評審

2 引文斯高帕斯（Scopus）

摘要

The hybrid architecture of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) model has been progressively applied to the time-series data application. This paper developed a hybrid CNN-LSTM network to classify electrocardiography signals. Moreover, we proposed a software (SW)-hardware (HW) co-design approach using a system-on-chip (SoC) field-programmable gate array (FPGA) platform to implement the hybrid CNN-LSTM inference. In our SoC-FPGA design, the CNN model was completed using the SW program while the LSTM model that employs the block circulant weight matrix was realized using the FPGA HW. An experiment was made to achieve 98.63 % ECG detection accuracy within 208.2 ms using the proposed SW-HW co-design SoC-FPGA approach.

原文	英語
主出版物標題	Proceedings - International SoC Design Conference 2023, ISOCC 2023
發行者	Institute of Electrical and Electronics Engineers Inc.
頁面	173-174
頁數	2
ISBN（電子）	9798350327038
DOIs	https://doi.org/10.1109/ISOCC59558.2023.10396448
出版狀態	已出版 - 2023
事件	20th International SoC Design Conference, ISOCC 2023 - Jeju, 韓國持續時間: 25 10 2023 → 28 10 2023

出版系列

名字	Proceedings - International SoC Design Conference 2023, ISOCC 2023

Conference

Conference	20th International SoC Design Conference, ISOCC 2023
國家/地區	韓國
城市	Jeju
期間	25/10/23 → 28/10/23

文獻附註

Publisher Copyright:
© 2023 IEEE.

存取文件

10.1109/ISOCC59558.2023.10396448

其它文件與鏈接

Link to publication in Scopus

引用此

Tang, S. N., Chen, Y. H., Chang, Y. W., Chen, Y. T., & Chou, S. H. (2023). Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach. 於 Proceedings - International SoC Design Conference 2023, ISOCC 2023 (頁 173-174). (Proceedings - International SoC Design Conference 2023, ISOCC 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISOCC59558.2023.10396448

@inproceedings{15ddbf863c59460e8aa5482b720af5ef,

title = "Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach",

abstract = "The hybrid architecture of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) model has been progressively applied to the time-series data application. This paper developed a hybrid CNN-LSTM network to classify electrocardiography signals. Moreover, we proposed a software (SW)-hardware (HW) co-design approach using a system-on-chip (SoC) field-programmable gate array (FPGA) platform to implement the hybrid CNN-LSTM inference. In our SoC-FPGA design, the CNN model was completed using the SW program while the LSTM model that employs the block circulant weight matrix was realized using the FPGA HW. An experiment was made to achieve 98.63 % ECG detection accuracy within 208.2 ms using the proposed SW-HW co-design SoC-FPGA approach.",

keywords = "CNN, Convolution Neural Network, FPGA, hybrid, long short term memory, LSTM, software-hardware co-design",

author = "Tang, {Song Nien} and Chen, {Yuan Ho} and Chang, {Yu Wei} and Chen, {Yu Ting} and Chou, {Shuo Hung}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 20th International SoC Design Conference, ISOCC 2023 ; Conference date: 25-10-2023 Through 28-10-2023",

year = "2023",

doi = "10.1109/ISOCC59558.2023.10396448",

language = "英语",

series = "Proceedings - International SoC Design Conference 2023, ISOCC 2023",

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

pages = "173--174",

booktitle = "Proceedings - International SoC Design Conference 2023, ISOCC 2023",

address = "美国",

}

Tang, SN, Chen, YH, Chang, YW, Chen, YT & Chou, SH 2023, Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach. 於 Proceedings - International SoC Design Conference 2023, ISOCC 2023. Proceedings - International SoC Design Conference 2023, ISOCC 2023, Institute of Electrical and Electronics Engineers Inc., 頁 173-174, 20th International SoC Design Conference, ISOCC 2023, Jeju, 韓國, 25/10/23. https://doi.org/10.1109/ISOCC59558.2023.10396448

Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach. / Tang, Song Nien; Chen, Yuan Ho; Chang, Yu Wei 等.
Proceedings - International SoC Design Conference 2023, ISOCC 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 173-174 (Proceedings - International SoC Design Conference 2023, ISOCC 2023).

研究成果: 圖書/報告稿件的類型 › 會議稿件 › 同行評審

TY - GEN

T1 - Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach

AU - Tang, Song Nien

AU - Chen, Yuan Ho

AU - Chang, Yu Wei

AU - Chen, Yu Ting

AU - Chou, Shuo Hung

PY - 2023

Y1 - 2023

N2 - The hybrid architecture of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) model has been progressively applied to the time-series data application. This paper developed a hybrid CNN-LSTM network to classify electrocardiography signals. Moreover, we proposed a software (SW)-hardware (HW) co-design approach using a system-on-chip (SoC) field-programmable gate array (FPGA) platform to implement the hybrid CNN-LSTM inference. In our SoC-FPGA design, the CNN model was completed using the SW program while the LSTM model that employs the block circulant weight matrix was realized using the FPGA HW. An experiment was made to achieve 98.63 % ECG detection accuracy within 208.2 ms using the proposed SW-HW co-design SoC-FPGA approach.

AB - The hybrid architecture of a Convolutional Neural Network (CNN) and a Long Short-Term Memory (LSTM) model has been progressively applied to the time-series data application. This paper developed a hybrid CNN-LSTM network to classify electrocardiography signals. Moreover, we proposed a software (SW)-hardware (HW) co-design approach using a system-on-chip (SoC) field-programmable gate array (FPGA) platform to implement the hybrid CNN-LSTM inference. In our SoC-FPGA design, the CNN model was completed using the SW program while the LSTM model that employs the block circulant weight matrix was realized using the FPGA HW. An experiment was made to achieve 98.63 % ECG detection accuracy within 208.2 ms using the proposed SW-HW co-design SoC-FPGA approach.

KW - CNN

KW - Convolution Neural Network

KW - FPGA

KW - hybrid

KW - long short term memory

KW - LSTM

KW - software-hardware co-design

UR - http://www.scopus.com/inward/record.url?scp=85184805295&partnerID=8YFLogxK

U2 - 10.1109/ISOCC59558.2023.10396448

DO - 10.1109/ISOCC59558.2023.10396448

M3 - 会议稿件

AN - SCOPUS:85184805295

T3 - Proceedings - International SoC Design Conference 2023, ISOCC 2023

SP - 173

EP - 174

BT - Proceedings - International SoC Design Conference 2023, ISOCC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th International SoC Design Conference, ISOCC 2023

Y2 - 25 October 2023 through 28 October 2023

ER -

Tang SN, Chen YH, Chang YW, Chen YT, Chou SH. Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach. 於 Proceedings - International SoC Design Conference 2023, ISOCC 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 173-174. (Proceedings - International SoC Design Conference 2023, ISOCC 2023). doi: 10.1109/ISOCC59558.2023.10396448

Hybrid CNN-LSTM Network for ECG Classification and Its Software-Hardware Co-Design Approach

摘要

出版系列

Conference

文獻附註

存取文件

其它文件與鏈接

指紋

引用此