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。

2026-04-28 至 2026-04-28 共收录 6 信号源:q-bio.NC, eess.SP, cs.LG, cs.HC, cs.RO

1. EEG解码 6 篇

2603.20738 2026-04-28 cs.CV 91%

SATTC: Structure-Aware Label-Free Test-Time Calibration for Cross-Subject EEG-to-Image Retrieval

SATTC: 结构感知的无标签测试时校准用于跨主体EEG到图像检索

Qunjie Huang, Weina Zhu

机构 * Yunnan University(云南大学)

专题命中 EEG解码 :EEG(title,title_cn);neural decoding(abstract)

AI总结 本文提出SATTC,一种无标签测试时校准方法,通过结合几何专家和结构专家,提升跨主体EEG到图像检索的准确性与稳定性。

Comments Accepted to CVPR 2026. Official code: https://github.com/QunjieHuang/SATTC-CVPR2026. This version corrects the dataset naming in the paper text and abstract: the experiments were conducted on THINGS-EEG2, whereas the previous version referred to it as THINGS-EEG in parts of the paper. Citations were already correct. Results are unchanged

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23933 2026-04-28 cs.LG eess.SP q-bio.NC 90%

Robust and Clinically Reliable EEG Biomarkers: A Cross Population Framework for Generalizable Parkinson's Disease Detection

鲁棒且临床可靠的EEG生物标志物:一种跨群体框架用于通用型帕金森病检测

Nicholas R. Rasmussen, Longwei Wang, Rodrigue Rizk, Md Rezwanul Akter Pallab, Samuel Stuwart, Martina Mancini, Arun Singh, KC Santosh

机构 * USD AI Research, Department of Computer Science, University of South Dakota(USD人工智能研究机构、计算机科学系、南达科他大学) Biomedical and Translational Sciences, Sanford School of Medicine, University of South Dakota(生物医学与转化科学、桑福德医学院、南达科他大学) Department of Sport, Exercise and Rehabilitation, Northumbria University(体育、运动与康复系、北umbria大学) Department of Neurology, Oregon Health & Science University(神经病学系、俄勒冈健康与科学大学)

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

AI总结 本文提出一种跨群体评估框架,用于评估EEG生物标志物的鲁棒性和临床可靠性,通过多队列实验发现训练群体多样性提高准确性和稳定性,达到94.1%的准确率。

Comments This is the non anonymized preprint corresponding to the version submitted to ACM Transactions on Computing for Healthcare. It is not the final typeset or accepted version

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23964 2026-04-28 cs.LG cs.AI 90%

Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction

基于扩散增强的任务引导时空网络用于基于EEG的痴呆症诊断和MMSE预测

Xiaoyu Zheng, Xu Tian, Bin Jiao, Kunbo Cui, Hanhe Lin, Lu Shen, Jin Liu

机构 * Hunan Provincial Key Lab on Bioinformatics, School of Computer Science and Engineering, Central South University(湖南生物信息省重点实验室,计算机科学与工程学院,中南大学) Xinjiang Engineering Research Center of Big Data and Intelligent Software, School of Software, Xinjiang University(新疆大数据与智能软件工程研究中心,软件学院,新疆大学) School of Science and Engineering, University of Dundee(科学与工程学院,邓迪大学) Department of Neurology, Xiangya Hospital, Central South University(神经内科,湘雅医院,中南大学)

专题命中 EEG解码 :EEG(title,title_cn);分类 cs.LG

AI总结 本文提出任务引导时空网络,通过多频段特征融合模块和扩散增强模块,提升EEG数据中痴呆症诊断和MMSE预测的准确性与鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23091 2026-04-28 cs.LG 90%

Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes

EEG基础模型的通道适应:跨架构、任务和训练模式的系统性基准测试

Kuntal Kokate, Bruno Aristimunha, Dung Truong, Arnaud Delorme

机构 * Swartz Center for Computational Neuroscience, Institute for Neural Computation, University of California San Diego(斯瓦茨计算神经科学中心,神经计算研究所,加州大学圣地亚哥分校) Yneuro Centre de Recherche Cerveau et Cognition, CNRS, Université Paul Sabatier(脑与认知研究中心,法国国家科学研究中心,保罗·萨巴蒂埃大学)

专题命中 EEG解码 :EEG(title,title_cn);分类 cs.LG

AI总结 本文系统比较了四种通道适应方法在不同EEG基础模型、任务和训练模式中的表现,发现灵活模型在微调时需外部方法辅助,且5M参数CBraMod在4/5数据集上超越更大模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23525 2026-04-28 q-bio.NC 81%

Triple Configuration of Brain Networks Based on Recurrent Neural Networks: The Synergistic Effects of Exogenous Stimuli, Task Demands, and Spontaneous Activity

基于循环神经网络的脑网络三重配置:外源性刺激、任务需求与自发活动的协同效应

Binghao Yang, Guangzong Chen

专题命中 EEG解码 :EEG(summary_cn,abstract);分类 q-bio.NC

AI总结 本文提出利用循环神经网络建模 resting-state EEG 数据,揭示由外源和内源因素驱动的脑网络三重配置,发现顶叶网络在支持多种配置模式中的关键作用,以及不同刺激模态下前顶叶和后顶叶区域的功能特化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.09862 2026-04-28 q-bio.NC 70%

Towards a Quantitative Theory of Digraph-Based Complexes and its Applications in Brain Network Analysis

走向基于有向图的复杂体的定量理论及其在脑网络分析中的应用

Heitor Baldo

专题命中 EEG解码 :EEG(abstract,abstract_cn);分类 q-bio.NC

AI总结 本文提出基于有向图构建的复杂体的定量方法,用于分析脑网络拓扑结构,探索更高阶结构在癫痫发作不同阶段的变化及生物标志物的潜在价值。

Comments Version 4: I corrected the text and added new notations to clarify the distinction between maximal and lower q-digraphs. Clarifications regarding density effects are added in Chapter 7

详情

展开后加载摘要…

URL PDF HTML 收藏