arXivDaily arXiv每日学术速递 周一至周五更新

科学与医疗

脑机接口 / BCI

脑机接口、EEG、神经信号解码、神经假体和脑控交互。

共收录 7277 信号源:q-bio.NC, eess.SP, cs.LG, cs.HC, cs.RO

1. EEG解码 3876 篇

2608.13072 2026-08-14 cs.AI 新提交 92%

EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding

EEG-PRIME:面向脑电信号解码的多层级条件原型对齐表示学习

Shuailei Zhang, Muyun Jiang, Wei Zhang, Jinbo Chen, Zhiwei Guo, Yong Li, Yi Ding, Cuntai Guan

机构 * College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院) Centre for AI in Medicine, Nanyang Technological University(南洋理工大学医学人工智能中心) Southeast University(东南大学)

专题命中 EEG解码 :EEG(title,title_cn);BCI(abstract,abstract_cn);motor imagery(abstract)

AI总结 本文提出EEG-PRIME脑电基础模型,结合掩码预训练与原型对齐指令调优,在16个多类型数据集上实现跨被试解码性能提升,且具备零样本迁移能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.08594 2026-06-16 cs.LG eess.SP 新提交 92%

How Much Capacity Does EEG Denoising Need? Ultra-Compact Networks reveal Benchmark Saturation and Metric-Utility Gap

脑电图去噪需要多少容量?超紧凑网络揭示基准饱和与度量-效用差距

Jasmeet Singh Bindra, Siddharth Panwar

机构 * Indian Knowledge Systems and Mental Health Applications (IKSMHA) Center, Indian Institute of Technology Mandi(印度理工学院曼迪分校印度知识体系与心理健康应用中心) School of Computing and Electrical Engineering, Indian Institute of Technology Mandi(印度理工学院曼迪分校计算与电气工程学院)

专题命中 EEG解码 :EEG(title,summary_cn);BCI(summary_cn,abstract);分类 eess.SP、cs.LG

AI总结 通过固定架构仅改变通道宽度(1.05K-40.26K参数),发现EEG去噪重建性能在3-6.5K参数时饱和,且重建度量不预测下游BCI效用,超紧凑模型(33-46KB)适用于边缘部署。

Comments 17 pages, will be submitted to peer-reviewed journal

详情

展开后加载摘要…

URL PDF HTML 收藏
1702.02914 2020-03-31 cs.LG cs.HC 92%

Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI)

Dongrui Wu, Jung-Tai King, Chun-Hsiang Chuang, Chin-Teng Lin, Tzyy-Ping Jung

专题命中 EEG解码 :BCI(title,abstract);brain-computer interface(title,abstract);EEG(title,abstract);分类 cs.LG、cs.HC

Journal ref IEEE Trans. on Fuzzy Systems, 26(2), pp. 771-781, 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.15431 2024-03-26 eess.SP cs.HC cs.LG 92%

Transferring BCI models from calibration to control: Observing shifts in EEG features

Ivo Pascal de Jong, Lüke Luna van den Wittenboer, Matias Valdenegro-Toro, Andreea Ioana Sburlea

专题命中 EEG解码 :BCI(title,abstract);EEG(title,abstract);brain-computer interface(abstract);motor imagery(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03176 2026-08-05 cs.CV cs.HC 新提交 92%

Frequency-Decorrelated Temporal Ensembles for EEG--fNIRS Imagined-Handwriting Decoding

用于EEG-fNIRS想象手写解码的频率去相关时间集成

Xiao Fan, Hongbin Guo, Yubo Han, Yi Zhang

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);neural decoding(abstract);分类 cs.HC

AI总结 本研究针对EEG-fNIRS想象手写解码难题,提出FRED系统,采用频率去相关时间集成等方法,在多模态脑机接口挑战赛中取得较好成绩,揭示了关键性能来源。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17883 2026-08-04 cs.LG cs.CV 版本更新 92%

EEG-FM-Compass: Progress, Benchmarking, and Future Directions for EEG Foundation Models

EEG基础模型:进展、基准测试与开放问题

Dingkun Liu, Yuheng Chen, Zhu Chen, Zhenyao Cui, Yaozhi Wen, Jiayu An, Jingwei Luo, Dongrui Wu

专题命中 EEG解码 :EEG(title,title_cn);BCI(abstract_cn);brain-computer interface(abstract);分类 cs.LG

AI总结 本文研究了EEG基础模型的进展、基准测试与开放问题,通过评估12个开源模型和专用基线,发现线性探测不足,专用模型仍具竞争力,且大模型不必然提升泛化性能。

Journal ref National Science Review, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.20182 2026-05-20 cs.LG cs.AI 92%

Atoms of Thought: Universal EEG Representation Learning with Microstates

思想的原子:基于微状态的通用EEG表示学习

Xinyang Tian, Ruitao Liu, Ziyi Ye, Siyang Xue, Xin Wang, Xuesong Chen

机构 * Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院) Institute of Trustworthy Embodied AI, Fudan University(复旦大学可信具身人工智能研究院) School of Clinical Medicine, Tsinghua University(清华大学临床医学院) Beijing Five Seasons Medical Technology Co., Ltd.(北京五 Seasons 医疗科技有限公司)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);motor imagery(abstract);分类 cs.LG

AI总结 本文提出了一种基于微状态的通用EEG表示学习方法,通过将连续EEG信号聚类为离散的微状态序列,构建了一个通用的微状态分词器,并在睡眠分期、情绪识别和运动想象分类等下游任务中展示了其优越性,同时提高了可解释性和扩展性。

Comments Accepted by the 3rd International Workshop on Multimodal and Responsible Affective Computing (MRAC 2025). 8 pages of main text, 23 pages total, 5 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11885 2026-05-18 cs.AI q-bio.NC 92%

From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP

从聪明汉到科学发现:通过LRP解释EEG基础Transformer

Justus Meyer zu Bexten, Nico Scherf, Bogdan Franczyk, Simon M. Hofmann

机构 * Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)(可扩展数据分析与人工智能中心(ScaDS.AI)) Leipzig University(莱比锡大学) Neural Data Science and Statistical Computing, Max Planck Institute for Human Cognitive and Brain Sciences(神经数据科学与统计计算,人类认知与脑科学马克斯·普朗克研究所) Faculty of Economics, Leipzig University(经济学院,莱比锡大学) Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences(神经病学系,人类认知与脑科学马克斯·普朗克研究所)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);motor imagery(abstract);分类 q-bio.NC

AI总结 本文研究了EEG基础模型中注意力感知的LRP方法,用于验证模型决策并提出生物合理假设,揭示了模型在运动想象和情绪预测中的潜在问题。

Comments 18 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.10881 2026-05-18 cs.LG 92%

LAtte: Hyperbolic Lorentz Attention for Cross-Subject EEG Classification

LAtte:用于跨受试者EEG分类的双曲洛伦兹注意力

Ahmad Bdeir, Johannes Burchert, Tom Hanika, Lars Schmidt-Thieme, Niels Landwehr

机构 * Data Science Group(数据科学组) ISMLL Universität Hildesheim(希尔德斯海姆大学)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);neural signal(abstract);分类 cs.LG

AI总结 本文提出LAtte框架,结合双曲InceptionTime编码器与洛伦兹注意力,提升跨受试者EEG分类性能,通过分解EEG信号并引入低秩适应模块增强鲁棒性与泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
1808.04443 2018-08-15 q-bio.QM eess.SP 92%

Spatial and Spectral Features Fusion for EEG Classification during Motor Imagery in BCI

Chuanqi Tan, Fuchun Sun, Wenchang Zhang, Shaobo Liu, Chunfang Liu

专题命中 EEG解码 :BCI(title,abstract);EEG(title,abstract);motor imagery(title);brain computer interface(abstract)

Comments International Conference on Biomedical and Health Informatics (BHI 2017)

详情

展开后加载摘要…

URL PDF HTML 收藏
1805.01044 2018-05-04 cs.LG stat.ML 92%

Covariate Shift Estimation based Adaptive Ensemble Learning for Handling Non-Stationarity in Motor Imagery related EEG-based Brain-Computer Interface

Haider Raza, Dheeraj Rathee, ShangMing Zhou, Hubert Cecotti, Girijesh Prasad

专题命中 EEG解码 :brain-computer interface(title,abstract);EEG(title,abstract);motor imagery(title);BCI(abstract)

Comments 28 Pages, 3 figures, Neurocomputing

Journal ref Neurocomputing 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
1711.07258 2018-03-28 q-bio.NC 92%

Integrating EEG and MEG signals to improve motor imagery classification in brain-computer interfaces

Marie-Constance Corsi, Mario Chavez, Denis Schwartz, Laurent Hugueville, Ankit N. Khambhati, Danielle S. Bassett, Fabrizio De Vico Fallani

专题命中 EEG解码 :brain-computer interface(title,abstract);EEG(title,abstract);motor imagery(title,abstract);分类 q-bio.NC

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01867 2025-06-03 q-bio.NC eess.SP 91%

EEG Foundation Models for BCI Learn Diverse Features of Electrophysiology

Mattson Ogg, Rahul Hingorani, Diego Luna, Griffin W. Milsap, William G. Coon, Clara A. Scholl

专题命中 EEG解码 :BCI(title,abstract);EEG(title,abstract);brain computer interface(abstract);neural decoding(abstract)

Comments Two figures, one table, six pages

详情

展开后加载摘要…

URL PDF HTML 收藏
1611.08024 2018-06-28 cs.LG q-bio.NC stat.ML 91%

EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces

Vernon J. Lawhern, Amelia J. Solon, Nicholas R. Waytowich, Stephen M. Gordon, Chou P. Hung, Brent J. Lance

专题命中 EEG解码 :EEG(title,abstract);brain-computer interface(title);BCI(abstract);brain computer interface(abstract)

Comments 30 pages, 10 figures. Added additional feature relevance analyses. Minor change to EEGNet architecture. Source code can be found at https://github.com/vlawhern/arl-eegmodels

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.10552 2026-07-22 cs.NE 版本更新 91%

MindPilot: Closed-loop Visual Stimulation Optimization for Brain Modulation with EEG-guided Diffusion

MindPilot: 闭环视觉刺激优化用于EEG引导的脑调控

Dongyang Li, Kunpeng Xie, Mingyang Wu, Yiwei Kong, Jiahua Tang, Haoyang Qin, Chen Wei, Quanying Liu

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);neural signal(abstract)

AI总结 MindPilot通过EEG反馈实现闭环视觉刺激优化,推动非侵入性脑调控和双向脑机接口的发展。

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.09315 2026-06-09 cs.CR cs.AI 新提交 91%

Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents

脑提示注入:BCI-LLM代理的路径安全审计

Jianwei Tai

机构 * University of California, Berkeley(加州大学伯克利分校)

专题命中 EEG解码 :BCI(title,title_cn);EEG(abstract,abstract_cn)

AI总结 提出路径安全审计契约,通过分离定理和共形校准量化BCI-LLM代理中脑信号注入攻击的风险,实验证明确认通道可降低路由风险。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.07212 2026-05-11 cs.LG cs.AI cs.HC cs.NE eess.SP 91%

Same Brain, Different Prediction: How Preprocessing Choices Undermine EEG Decoding Reliability

同一体脑,不同预测:预处理选择如何削弱EEG解码可靠性

Dengzhe Hou, Zihao Wu, Lingyu Jiang, Zirui Li, Fangzhou Lin, Kazunori D. Yamada

机构 * Tohoku University(东洋大学) University of Georgia(佐治亚大学) Texas A&M University(德克萨斯农工大学) Worcester Polytechnic Institute(沃斯特理工学院)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);分类 eess.SP、cs.LG、cs.HC

AI总结 本文研究了EEG解码中预处理选择对可靠性的影响,提出三种工具以量化、分解和减少预处理带来的不稳定性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.00857 2026-05-05 eess.SP cs.AI cs.LG q-bio.NC 91%

Foundation Model Guided Dual-Branch Co-Adaptation for Source-Free EEG Decoding

基于基础模型的双分支共适应源无关EEG解码

Peiliang Gong, Han Zhang, Zhen Jiang, Chenyu Liu, Ziyu Jia, Xinliang Zhou, Daoqiang Zhang, Xiaoli Li

机构 * College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院) College of Artifical Intelligence and Automation, Hohai University(河海大学人工智能与自动化学院) College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(南京航空航天大学人工智能学院) Brainnetcome Center, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所脑网络中心) Information Systems Technology and Design, Singapore University of Technology and Design(新加坡科技设计大学信息系统技术与设计)

专题命中 EEG解码 :EEG(title,title_cn);motor imagery(abstract);分类 q-bio.NC、eess.SP、cs.LG

AI总结 本文提出FUSED框架,通过双分支共适应机制整合大规模基础模型与紧凑专家模型,提升源无关EEG解码的泛化能力和稳定性,实验验证其在多任务中的优越性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.07655 2022-06-16 eess.SP cs.AI cs.LG q-bio.NC 91%

Classification of EEG Motor Imagery Using Deep Learning for Brain-Computer Interface Systems

Alessandro Gallo, Manh Duong Phung

专题命中 EEG解码 :EEG(title,abstract);motor imagery(title,abstract);brain-computer interface(title);分类 q-bio.NC、eess.SP、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.03115 2024-06-11 q-bio.NC 91%

GET: A Generative EEG Transformer for Continuous Context-Based Neural Signals

Omair Ali, Muhammad Saif-ur-Rehman, Marita Metzler, Tobias Glasmachers, Ioannis Iossifidis, Christian Klaes

专题命中 EEG解码 :EEG(title,abstract);neural signal(title,abstract);BCI(abstract);brain-computer interface(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2212.05289 2022-12-13 cs.LG 91%

A Hybrid Brain-Computer Interface Using Motor Imagery and SSVEP Based on Convolutional Neural Network

Wenwei Luo, Wanguang Yin, Quanying Liu, Youzhi Qu

专题命中 EEG解码 :brain-computer interface(title,abstract);motor imagery(title,abstract);BCI(abstract);EEG(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26910 2026-05-28 cs.LG cs.AI q-bio.NC 91%

EEG-FM-Audit: A Systematic Evaluation and Analysis Pipeline for EEG Foundation Models

EEG-FM-Audit:脑电图基础模型的系统评估与分析流程

Xianheng Wang, Yige Yang, Damien Coyle

机构 * Bath Institute for the Augmented Human(巴思增强人类研究所) University of Bath(巴斯大学)

专题命中 EEG解码 :EEG(title,title_cn);neural decoding(abstract);分类 q-bio.NC、cs.LG

AI总结 提出EEG-FM-Audit流程,通过ASHA驱动的基准测试、范式级消融研究和神经生理探测,系统评估脑电图基础模型,发现调优的监督基线可媲美或超越先进基础模型。

Comments 26 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.18298 2026-05-19 cs.AI cs.HC cs.LG 91%

DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

DARE-EEG: 一种用于挖掘双对齐表示的EEG基础模型

Yang Shao, Peiliang Gong, Qun Dai, Daoqiang Zhang

机构 * College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(航空宇航学院人工智能学院)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);分类 cs.LG、cs.HC

AI总结 本文提出DARE-EEG,一种通过双对齐表示学习预训练的自监督基础模型,旨在解决EEG编码器在不完整观测下学习不变表示的问题,通过对比学习和动量更新实现语义稳定性,并通过卷积-线性探针策略适应异构电极配置和采样率,实验表明其在EEG基准测试中表现优异。

Comments 22 pages, 10 pages of main text + 12 pages of appendices

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16326 2026-05-19 q-bio.QM cs.AI cs.LG eess.SP 91%

A Machine Learning Framework for EEG-Based Prediction of Treatment Efficacy in Chronic Neck Pain

一种基于EEG的慢性颈部疼痛治疗效果预测机器学习框架

Xiru Wang, Aiden Li, Hongzhao Tan, Stevie Foglia, Aimee Nelson, Zhen Gao

机构 * Department of Kinesiology, Faculty of Science, McMaster University(麦吉尔大学运动科学系) W Booth School of Engineering Practice and Technology, Faculty of Engineering, McMaster University(麦吉尔大学工程学院W Booth工程实践与技术学院)

专题命中 EEG解码 :EEG(title,title_cn);motor imagery(abstract);分类 eess.SP、cs.LG

AI总结 本文提出利用EEG数据预测慢性颈部疼痛治疗效果的机器学习框架,通过严格的数据预处理和文献综述,旨在开发支持个性化医疗的鲁棒预测模型。

Comments 15 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.16281 2026-05-08 cs.LG q-bio.NC 91%

Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction

Laya: 一种基于联合嵌入预测架构的EEG方法

Saarang Panchavati, Uddhav Panchavati, Hiroki Nariai, Corey Arnold, William Speier

机构 * Department of Medical Informatics(医学信息学系) UCLA(美国加利福尼亚大学洛杉矶分校) Department of Cognitive Science(认知科学系) UCSD(美国圣地亚哥大学) David Geffen School of Medicine(大卫·盖弗医学院) Mattel Children’s Hospital(马特尔儿童医院)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);分类 q-bio.NC、cs.LG

AI总结 本文提出Laya,一种基于LeJEPA的EEG基础模型,通过预测潜在表示而非信号重建,提升EEG表示的语义结构和临床准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.17842 2026-04-21 eess.SP cs.LG 91%

Canine EEG Helps Human: Cross-Species and Cross-Modality Epileptic Seizure Detection via Multi-Space Alignment

犬类EEG帮助人类:通过多空间对齐实现跨物种和跨模态的癫痫发作检测

Z. Wang, S. Li, Dongrui Wu

机构 * Ministry of Education Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(教育部图像处理与智能控制重点实验室,人工智能与自动化学院,华中科技大学) Hubei Key Laboratory of Brain-inspired Intelligent Systems, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(湖北省脑启发智能系统重点实验室,人工智能与自动化学院,华中科技大学)

专题命中 EEG解码 :EEG(title,title_cn);brain-computer interface(abstract);分类 eess.SP、cs.LG

AI总结 本文提出基于跨物种和跨模态EEG数据的多空间对齐方法,利用深度学习技术提升癫痫发作检测能力,实验显示在有限标注数据下,检测准确率超过90%。

Journal ref National Science Review, 12(6):nwaf086, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.30775 2026-07-31 stat.AP stat.ML 版本更新 91%

Bayesian Classification with Probit-link Split-and-merge Gaussian Process Prior in EEG-based Brain-Computer Interfaces

基于脑电图脑机接口中Probit-link分裂合并高斯过程先验的贝叶斯分类

Yunong Wu, Jane E. Huggins, Jian Kang, Tianwen Ma

专题命中 EEG解码 :EEG(title,abstract);brain-computer interface(title,abstract);BCI(abstract,abstract_cn)

AI总结 提出一种基于Probit-link分裂合并高斯过程先验的贝叶斯生成模型,用于脑电图响应二元分类,实现时空特征选择并降低计算复杂度,同时保持预测精度。

Comments 32 pages, 7 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.09654 2026-04-14 cs.HC cs.AI cs.LG eess.SP 91%

NeuroPath: Practically Adopting Motor Imagery Decoding through EEG Signals

NeuroPath: 通过EEG信号实际采用运动想象解码

Jiani Cao, Kun Wang, Yang Liu, Zhenjiang Li

机构 * City University of Hong Kong(香港城市大学) Florida State University(佛罗里达州立大学)

专题命中 EEG解码 :EEG(title,abstract);motor imagery(title,abstract);BCI(abstract);brain-computer interface(abstract)

AI总结 NeuroPath提出一种神经架构,通过EEG信号统一解码运动想象任务,解决现有方法模型孤立、电极配置固定和低信噪比下性能下降的问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.03224 2024-12-05 cs.HC cs.LG eess.SP 91%

Channel Reflection: Knowledge-Driven Data Augmentation for EEG-Based Brain-Computer Interfaces

Ziwei Wang, Siyang Li, Jingwei Luo, Jiajing Liu, Dongrui Wu

专题命中 EEG解码 :brain-computer interface(title,abstract);EEG(title,abstract);BCI(abstract);motor imagery(abstract)

Journal ref Neural Networks, 176:106351, 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.04104 2024-09-09 cs.LG cs.AI cs.CV cs.HC eess.SP 91%

MixNet: Joining Force of Classical and Modern Approaches Toward the Comprehensive Pipeline in Motor Imagery EEG Classification

Phairot Autthasan, Rattanaphon Chaisaen, Huy Phan, Maarten De Vos, Theerawit Wilaiprasitporn

专题命中 EEG解码 :EEG(title,abstract);motor imagery(title,abstract);BCI(abstract);brain-computer interface(abstract)

Comments Supplementary materials and source codes are available on-line at https://github.com/Max-Phairot-A/MixNet

Journal ref IEEE Internet of Things Journal 2024

详情

展开后加载摘要…

URL PDF HTML 收藏