Attention-Enhanced U-Net for Sensor-Efficient High-Density EEG Reconstruction in Wearable Brain Monitoring Systems.
High-channel-density (HCD) electroencephalography (EEG) enables fine-grained neural sensing but is constrained by high hardware costs, spatial complexity, and limited portability. This study developed a deep learning-based method to reconstruct high-density EEG signals from low-channel-density (LCD)...
| Publicado en: | Journal of Medical Systems Vol. 50; no. 1; pp. 1 - 15 |
|---|---|
| Autores principales: | , |
| Formato: | equations & formulas pictorial research tables/charts tracings Journal Article |
| Publicado: |
Springer Nature
4/5/2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=192768840&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 192768840 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01485598 4N0 jtl: Journal of Medical Systems issn: 01485598 maglogo: N pubinfo: dt: 4/5/2026 vid: 50 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 192768840 192768840 192768840 10.1007/s10916-026-02374-5 192768840 ppf: 1 ppct: 14 formats: tig: atl: Attention-Enhanced U-Net for Sensor-Efficient High-Density EEG Reconstruction in Wearable Brain Monitoring Systems. aug: au: Zhuang, Jyun-Rong Guo, Pin-Cheng affil: https://ror.org/05vn3ca78 Department of Mechanical Engineering, National Chung Hsing University, 145 Xingda Rd., South Dist, 402202, Taichung City, Taiwan, R.O.C. sug: subj: Virtual High-Throughput Screening Electroencephalography Wearable Sensors Deep Learning Neural Networks (Computer) Human Pearson's Correlation Coefficient Funding Source Brain-Computer Interfaces ab: High-channel-density (HCD) electroencephalography (EEG) enables fine-grained neural sensing but is constrained by high hardware costs, spatial complexity, and limited portability. This study developed a deep learning-based method to reconstruct high-density EEG signals from low-channel-density (LCD) inputs, enabling more practical and affordable brain-monitoring systems. This study introduces VEEG-A-U-Net, a lightweight U-Net architecture enhanced with attention gates and residual learning. The model combined spherical spline interpolation with a learnable correction signal to adaptively model spatial-temporal features. The framework was trained and evaluated on the SEED dataset, using normalized mean square error (NMSE), signal-to-noise ratio (SNR), and Pearson correlation coefficient (PCC) to assess reconstruction performance. Validation was conducted through leave-one-subject-out cross-validation (LOSO-CV) and cross-dataset experiments to examine generalizability. Under the same reconstruction setting (scale factor = 2), VEEG-A-U-Net achieved competitive reconstruction performance compared with state-of-the-art methods, while requiring substantially fewer parameters and computational operations. Cross-dataset evaluations confirmed stable performance across different EEG paradigms. Inference-time analysis showed low computational latency, indicating practical feasibility for deployment in resource-constrained and edge computing environments. A preliminary clinical EEG evaluation was also conducted to explore feasibility in clinical settings.The proposed framework offers an effective and lightweight solution for reconstructing high-density EEG from sparse measurements. These findings may support the development of sensor-efficient and portable EEG systems for practical neuroengineering and brain–computer interface applications. pubtype: Academic Journal doctype: equations & formulas pictorial research tables/charts tracings Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|