MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification

Automated sleep stage classification is essential for objective sleep evaluation and clinical diagnosis. While numerous algorithms have been developed, the predominant existing methods utilize single-channel electroencephalogram (EEG) signals, neglecting the complementary physiological information a...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuegang Xu, Quan Wang, Changyuan Wang, Yaxin Zhang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/14/4251
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849733143003660288
author Xuegang Xu
Quan Wang
Changyuan Wang
Yaxin Zhang
author_facet Xuegang Xu
Quan Wang
Changyuan Wang
Yaxin Zhang
author_sort Xuegang Xu
collection DOAJ
description Automated sleep stage classification is essential for objective sleep evaluation and clinical diagnosis. While numerous algorithms have been developed, the predominant existing methods utilize single-channel electroencephalogram (EEG) signals, neglecting the complementary physiological information available from other channels. Standard polysomnography (PSG) recordings capture multiple concurrent biosignals, where sophisticated integration of these multi-channel data represents a critical factor for enhanced classification accuracy. Conventional multi-channel fusion techniques typically employ elementary concatenation approaches that insufficiently model the intricate cross-channel correlations, consequently limiting classification performance. To overcome these shortcomings, we present MCAF-Net, a novel network architecture that employs temporal convolution modules to extract channel-specific features from each input signal and introduces a dynamic gated multi-head cross-channel attention mechanism (MCAF) to effectively model the interdependencies between different physiological channels. Experimental results show that our proposed method successfully integrates information from multiple channels, achieving significant improvements in sleep stage classification compared to the vast majority of existing methods.
format Article
id doaj-art-e3933ecd5cab460087f7dba7052ba8f4
institution DOAJ
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e3933ecd5cab460087f7dba7052ba8f42025-08-20T03:08:06ZengMDPI AGSensors1424-82202025-07-012514425110.3390/s25144251MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage ClassificationXuegang Xu0Quan Wang1Changyuan Wang2Yaxin Zhang3School of Computer Science and Engineering, Xi’an Technological University, Xi’an 710021, ChinaSchool of Computer Science and Engineering, Xi’an Technological University, Xi’an 710021, ChinaSchool of Computer Science and Engineering, Xi’an Technological University, Xi’an 710021, ChinaSchool of Computer Science and Engineering, Xi’an Technological University, Xi’an 710021, ChinaAutomated sleep stage classification is essential for objective sleep evaluation and clinical diagnosis. While numerous algorithms have been developed, the predominant existing methods utilize single-channel electroencephalogram (EEG) signals, neglecting the complementary physiological information available from other channels. Standard polysomnography (PSG) recordings capture multiple concurrent biosignals, where sophisticated integration of these multi-channel data represents a critical factor for enhanced classification accuracy. Conventional multi-channel fusion techniques typically employ elementary concatenation approaches that insufficiently model the intricate cross-channel correlations, consequently limiting classification performance. To overcome these shortcomings, we present MCAF-Net, a novel network architecture that employs temporal convolution modules to extract channel-specific features from each input signal and introduces a dynamic gated multi-head cross-channel attention mechanism (MCAF) to effectively model the interdependencies between different physiological channels. Experimental results show that our proposed method successfully integrates information from multiple channels, achieving significant improvements in sleep stage classification compared to the vast majority of existing methods.https://www.mdpi.com/1424-8220/25/14/4251automatic sleep stage classificationmulti-channel signal fusiontemporal convolutiondynamic gatedmulti-head cross-channel attention mechanism
spellingShingle Xuegang Xu
Quan Wang
Changyuan Wang
Yaxin Zhang
MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification
Sensors
automatic sleep stage classification
multi-channel signal fusion
temporal convolution
dynamic gated
multi-head cross-channel attention mechanism
title MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification
title_full MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification
title_fullStr MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification
title_full_unstemmed MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification
title_short MCAF-Net: Multi-Channel Temporal Cross-Attention Network with Dynamic Gating for Sleep Stage Classification
title_sort mcaf net multi channel temporal cross attention network with dynamic gating for sleep stage classification
topic automatic sleep stage classification
multi-channel signal fusion
temporal convolution
dynamic gated
multi-head cross-channel attention mechanism
url https://www.mdpi.com/1424-8220/25/14/4251
work_keys_str_mv AT xuegangxu mcafnetmultichanneltemporalcrossattentionnetworkwithdynamicgatingforsleepstageclassification
AT quanwang mcafnetmultichanneltemporalcrossattentionnetworkwithdynamicgatingforsleepstageclassification
AT changyuanwang mcafnetmultichanneltemporalcrossattentionnetworkwithdynamicgatingforsleepstageclassification
AT yaxinzhang mcafnetmultichanneltemporalcrossattentionnetworkwithdynamicgatingforsleepstageclassification