Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/175631
Title: Squeeze-excite fusion based multimodal neural network for sleep stage classification with flexible EEG/ECG signal acquisition circuit
Authors: Tao, Shuailin
Hu, Jinhai
Goh, Wang Ling
Gao, Yuan
Keywords: Computer and Information Science
Issue Date: 2024
Source: Tao, S., Hu, J., Goh, W. L. & Gao, Y. (2024). Squeeze-excite fusion based multimodal neural network for sleep stage classification with flexible EEG/ECG signal acquisition circuit. 2024 IEEE International Symposium on Circuits and Systems (ISCAS).
Project: A18A1b0055 
Conference: 2024 IEEE International Symposium on Circuits and Systems (ISCAS)
Abstract: This paper presents a multimodal fusion strategy for sleep stage classification using polysomnography (PSG) with elec troencephalogram (EEG) and Electrocardiogram (ECG) data. The Squeeze-Excite (SE) Fusion mechanism is implemented to enhance the collaborative impact of EEG and ECG signals on neural network classification. To address the challenges of imbalance in the dataset, a balanced sampler is used. Improved feature extraction is achieved through Linear-frequency cepstrum coefficients (LFCC) applied to the EEG signal. A recurrent convolutional neural network (RCNN) reduces model parameters and optimizes architecture, while quantizing the network weight down to INT4 ensures hardware compatibility, especially for edge devices. Applying these methodologies to signals, this optimized approach achieves a significant validation accuracy of 77.6% with a compact 23.5KB weight memory size on the MIT-BIH dataset, covering six distinct classification categories.
URI: https://hdl.handle.net/10356/175631
URL: https://2024.ieee-iscas.org/
Schools: Interdisciplinary Graduate School (IGS) 
School of Electrical and Electronic Engineering 
Organisations: Institute of Microelectronics, A*STAR 
Research Centres: Centre for Integrated Circuits and Systems
Rights: © 2024 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:IGS Conference Papers

Files in This Item:
File Description SizeFormat 
iscas2024_TaoShuailin_FV.pdf5.21 MBAdobe PDFThumbnail
View/Open

Page view(s)

34
Updated on Jun 23, 2024

Download(s)

29
Updated on Jun 23, 2024

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.