.png){kind=icon}
.png){kind=icon}
Return
A Detrended Residual EEG Imaging Framework for Multi-type Sleep Apnea Classification using a Hybrid Learning Approach
.png){kind=icon}
PRE
AI
S
M
DOI：10.1016/j.bspc.2026.111222.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Hybrid CNN+SVM enables stable multi-class sleep apnea classification. • Four-channel EEG fusion captures complementary time–frequency features. • Performance validated across C3A2 and C4A1 EEG derivations. • Ablation analysis evaluates contribution of DT-VMD preprocessing. • Multi-order IMF detrending improves EEG subtype representation.
Journal
IF:
4.9
Papers:
9.7K
Citations:
2.4W
Organization
No organization information available
Cited Papers