Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring
This paper presents an electrocardiogram (ECG) signal classification model based on dynamically-biased Long Short-Term Memory (DB-LSTM) network. Compared to conventional LSTM networks, DB-LSTM introduces a set of parameters C which save the previous time-step cell gate states of the unit cell. Hence...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/179112 https://ieeexplore.ieee.org/abstract/document/10181690 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-179112 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1791122024-07-19T15:39:06Z Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring Hu, Jinhai Goh, Wang Ling Gao, Yuan School of Electrical and Electronic Engineering 2023 IEEE International Symposium on Circuits and Systems (ISCAS) Institute of Microelectronics, A*STAR Centre for Integrated Circuits and Systems Engineering Long short-term memory ECG classification DB-LSTM This paper presents an electrocardiogram (ECG) signal classification model based on dynamically-biased Long Short-Term Memory (DB-LSTM) network. Compared to conventional LSTM networks, DB-LSTM introduces a set of parameters C which save the previous time-step cell gate states of the unit cell. Hence, more feature information is preserved and a smaller size network is required for the classification task. Comprehensive simulations using MIT-BIH ECG datasets show that this model can perform ECG feature classification with shorter time window, faster training convergence while achieving comparable training and classification accuracy with much lower weigh resolution. Compared to the other state-of- art ECG analysis algorithms, this model only requires 4 layers, and it achieved 96.74% accuracy when weights are truncated from FP32 to INT4 with only 2.4% accuracy degradation. Implemented on Xilinx Artix-7 FPGA, the proposed design is estimated to consume only 40μW dynamic power, which is a promising candidate for resource constrained edge devices. Agency for Science, Technology and Research (A*STAR) Submitted/Accepted version This work was supported by the Agency for Science, Technology and Research (A*STAR), Singapore under the Cyber-Physiochemical Interface programme, grant No. A18A1b0045. 2024-07-19T05:36:52Z 2024-07-19T05:36:52Z 2023 Conference Paper Hu, J., Goh, W. L. & Gao, Y. (2023). Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring. 2023 IEEE International Symposium on Circuits and Systems (ISCAS). https://dx.doi.org/10.1109/ISCAS46773.2023.10181690 978-1-6654-5109-3 https://hdl.handle.net/10356/179112 10.1109/ISCAS46773.2023.10181690 https://ieeexplore.ieee.org/abstract/document/10181690 en A18A1b0045 © 2023 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/ISCAS46773.2023.10181690. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Long short-term memory ECG classification DB-LSTM |
spellingShingle |
Engineering Long short-term memory ECG classification DB-LSTM Hu, Jinhai Goh, Wang Ling Gao, Yuan Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring |
description |
This paper presents an electrocardiogram (ECG) signal classification model based on dynamically-biased Long Short-Term Memory (DB-LSTM) network. Compared to conventional LSTM networks, DB-LSTM introduces a set of parameters C which save the previous time-step cell gate states of the unit cell. Hence, more feature information is preserved and a smaller size network is required for the classification task. Comprehensive simulations using MIT-BIH ECG datasets show that this model can perform ECG feature classification with shorter time window, faster training convergence while achieving comparable training and classification accuracy with much lower weigh resolution. Compared to the other state-of- art ECG analysis algorithms, this model only requires 4 layers, and it achieved 96.74% accuracy when weights are truncated from FP32 to INT4 with only 2.4% accuracy degradation. Implemented on Xilinx Artix-7 FPGA, the proposed design is estimated to consume only 40μW dynamic power, which is a promising candidate for resource constrained edge devices. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Hu, Jinhai Goh, Wang Ling Gao, Yuan |
format |
Conference or Workshop Item |
author |
Hu, Jinhai Goh, Wang Ling Gao, Yuan |
author_sort |
Hu, Jinhai |
title |
Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring |
title_short |
Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring |
title_full |
Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring |
title_fullStr |
Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring |
title_full_unstemmed |
Classification of ECG anomaly with dynamically-biased LSTM for continuous cardiac monitoring |
title_sort |
classification of ecg anomaly with dynamically-biased lstm for continuous cardiac monitoring |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/179112 https://ieeexplore.ieee.org/abstract/document/10181690 |
_version_ |
1806059911674593280 |