Neuro-Geospatial Modelling of EEG Affective States Using Literature-Informed Environmental Context
作者: Utsav Poudel, Jagannath Aryal, Subramaniyaswamy Vairavasundaram
分类: cs.AI, cs.HC, cs.LG
发布日期: 2026-08-21
🔗 代码/项目: GITHUB
💡 一句话要点
提出基于文献信息的环境上下文的EEG情感状态建模方法
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: EEG情感分类 多模态学习 环境影响 文献信息 地理空间建模
📋 核心要点
- 现有方法中,EEG与环境数据集缺乏共同的地理参考,限制了情感状态的准确分类。
- 本文提出利用文献信息的环境先验作为辅助模态,与EEG数据结合进行情感状态分类。
- 实验结果表明,结合环境信息的多模态模型准确率达到76.2%,相比单一EEG提升了8.8%。
📝 摘要(中文)
环境暴露(如空气污染和绿化)与情感和认知结果相关,但EEG和环境数据集很少共同进行地理参考。本文研究文献信息的环境先验如何作为辅助地理空间模态,用于EEG基础的情感状态分类。通过结合30通道EEG数据与来自OpenAQ、Sentinel-2、Sentinel-5P和OpenStreetMap的环境表示,采用双塔架构将EEG-Conformer表示与基于图的环境编码器结合。多模态模型的准确率达到76.2%,而单独使用EEG的准确率为67.4%。这些发现展示了技术的可行性,但并未建立观察到的或因果的暴露-情感关联。
🔬 方法详解
问题定义:本文旨在解决EEG与环境数据缺乏共同地理参考的问题,现有方法无法有效利用环境因素进行情感状态分类。
核心思路:通过引入文献信息的环境先验,作为辅助信息与EEG数据结合,提升情感状态分类的准确性。
技术框架:整体架构采用双塔模型,分别处理EEG-Conformer表示和环境编码器。EEG数据来自EAV基准,环境数据则来源于多个开放数据源。
关键创新:最重要的创新在于将文献信息的环境先验作为辅助模态,克服了数据集不共同注册的限制,提升了模型的分类性能。
关键设计:模型使用了30通道EEG数据,采用了图形编码器处理环境信息,实验中进行了多种控制实验以验证模型的有效性。
🖼️ 关键图片
📊 实验亮点
实验结果显示,结合环境信息的多模态模型准确率为76.2%,相比单一EEG的67.4%提升了8.8%。即使在扰动环境标签结构的情况下,模型仍保持部分性能提升,表明环境信息的贡献不容忽视。
🎯 应用场景
该研究为未来的移动EEG与环境联合研究提供了框架,潜在应用于心理健康监测、环境影响评估等领域,能够帮助理解环境因素对情感状态的影响。
📄 摘要(原文)
Environmental exposures such as air pollution and greenness have been associated with affective and cognitive outcomes, but EEG and environmental datasets are rarely jointly georeferenced. We investigate whether literature-informed environmental priors can serve as an auxiliary geospatial modality for EEG-based affective-state classification when individual-level exposure data are unavailable. We combine 30-channel EEG from the EAV benchmark (42 participants, aged 20-30 years) with environmental representations derived from OpenAQ, Sentinel-2, Sentinel-5P, and OpenStreetMap data for Astana. A dual-tower architecture combines EEG-Conformer representations with a graph-based environmental encoder. Because the datasets are not co-registered, environmental context is treated as a literature-informed prior rather than measured exposure. Subject-level repeated splits, permutation and label-shuffling controls, dose-response reversal, and domain-shift experiments distinguish architecture-level gains from prior-dependent gains. The multimodal model achieves 76.2% accuracy versus 67.4% for EEG alone. Controls disrupting environmental-label structure retain part of this gain, indicating that the improvement is not attributable solely to environmental information. Replacing the Astana environmental distribution with an independently modeled Singapore distribution reduces accuracy to 72.8%. These findings demonstrate technical feasibility but do not establish an observed or causal exposure-affect association. The study provides a framework for future jointly collected mobile EEG-environment studies. Implementation: https://github.com/r11up/geo-cog