A 0.04 μJ/ Classification High-Accuracy Energy-Efficient ECG Processor with SNN On-Chip Backpropagation and Adaptive Threshold Encoding

It is of great significance to conduct real-time Electrocardiography (ECG) monitoring with wearable devices. For wearable edge devices, the two most important factors are power consumption and inference accuracy [1]. For power consumption, many previous works have adopted spiking neural networks (SNN) to improve energy efficiency. For accuracy, a major problem with ECG classification is patient-topatient variation. Previous works have also done many efforts to solve the above issues. Thus, as shown in Fig.1, there are still the following unsolved challenges to be addressed:

Authors

Institutions

Publication Details

Published
2024-11-18
DOI
https://doi.org/10.1109/a-sscc60305.2024.10848982
Citations
2
Primary Topic
Analog and Mixed-Signal Circuit Design
Type
article
Field-Weighted Citation Impact
0.37

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

A 0.04 μJ/ Classification High-Accuracy Energy-Efficient ECG Processor with SNN On-Chip Backpropagation and Adaptive Threshold Encoding

Wei Gao, Zhiming Hu, Liang Chang, Zhiyuan Chang et al.
2 citations
Analog and Mixed-Signal Circuit Design
0.37
article

A 0.04 μJ/ Classification High-Accuracy Energy-Efficient ECG Processor with SNN On-Chip Backpropagation and Adaptive Threshold Encoding

Wei Gao, Zhiming Hu, Liang Chang, Zhiyuan Chang, Haodong Fan, Qihong Wu, Xi Yang, Jun Su, Li Zhang, Junlu Zhou, Jinxi Huang, Liang Zhou, Jiahao Zeng, Shuisheng Lin, Zhiwen Guo, Jun Zhou
article en
2 citations

Abstract

It is of great significance to conduct real-time Electrocardiography (ECG) monitoring with wearable devices. For wearable edge devices, the two most important factors are power consumption and inference accuracy [1]. For power consumption, many previous works have adopted spiking neural networks (SNN) to improve energy efficiency. For accuracy, a major problem with ECG classification is patient-topatient variation. Previous works have also done many efforts to solve the above issues. Thus, as shown in Fig.1, there are still the following unsolved challenges to be addressed:

University of Electronic Science and Technology of China (CN), Da Tang Xi Shi Group (China) (CN)
National Science Foundation
Affordable and clean energy
Openalex Percentile: Top 41%
Analog and Mixed-Signal Circuit Design
0.37
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

A 0.04 μJ/ Classification High-Accuracy Energy-Efficient ECG Processor with SNN On-Chip Backpropagation and Adaptive Threshold Encoding — Wei Gao, Zhiming Hu, et al. · (2024) | TGRS Research Map | TGRS