arXiv cs.LG + cs.RO + cs.HC· Isabella Guan·· 16 小时前AI 评分38
EEGBiFormer 用混合 CNN-Transformer 实时分类 16 通道 EEG 注意力状态
EEGBiFormer: Real-Time EEG Attention Classification via Hybrid CNN-Transformer with EEG-Informed Auditory Protocol Validation
AI 导读
EEGBiFormer 是一款混合 CNN-Transformer 模型，可从 16 通道 EEG 信号实时二分类专注与非专注状态，窗口级验证准确率 91.3%、F1 94.5%，17 次独立记录级准确率 88.2%，端到端延迟低于 100 ms。
正文 · 原文
Abstract:Sustained attention is critical for academic performance, yet existing auditory support tools are static and not grounded in real-time neural evidence. This paper presents EEGBiFormer, a hybrid CNN-Transformer model for realtime binary classification of attention states, focus versus nonfocus, from 16-channel EEG signals. A custom analog front-end acquisition board was designed and built to collect a task-based EEG dataset. Before model training, spectral and connectivity analysis, using Power Spectral Density and Phase Locking Value, confirmed distinct neural signatures between attention states, providing physiological grounding for the classification approach. EEGBiFormer achieved 91.3 percent window-level validation accuracy with an F1 score of 94.5 percent, and 88.2 percent recording-level accuracy across 17 independent sessions. End-to-end system latency was measured below 100 ms, supporting real-time responsiveness. The trained model was further used to objectively rank auditory stimuli by focus-state confidence, yielding EEG-informed audio protocols. In a paired within-subject behavioral study with 37 participants, these protocols produced a statistically significant 20 percent improvement in composite attention scores over silent controls, with a medium-to-large effect size. This work demonstrates a complete pipeline from custom EEG hardware through neural signal analysis, deep learning classification, and evidence-based auditory protocol design.
| Comments: | Accepted by IEEE MIT URTC 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.33832 [cs.LG] |
| (or arXiv:2610.33832v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33832 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Isabella Guan [view email]
[v1]
Sat, 24 Oct 2026 18:10:46 UTC (2,556 KB)
来源：arXiv cs.LG + cs.RO + cs.HC · arxiv.org