用眼动数据算法提取人类空间导航能力的五个量化指标。
Algorithmic Derivation of Human Spatial Navigation Indices From Eye Movement Data
- 基于眼动信号设计特征工程，结合机器学习生成导航指标。
- 导航与定向指标准确率达R2=0.72，地标识别达R2=0.50。
- 适合认知评估、早期认知衰退筛查，尤其适用于高风险人群。
空间导航是整合视觉、听觉和本体感觉等多源信息以理解并移动于空间的复杂认知功能，涉及构建心理地图、环境导航与方向线索处理。本研究提出一种算法框架，利用眼动数据（通过视网膜电图记录）提取与空间导航相关的五个子指标：导航与定向、空间焦虑、地标识别、路径概览与路径路线。通过统计特征分析与特征工程，结合信号处理与机器学习方法，实现了对眼动行为（包括眨眼、扫视、注视等）的定量建模。结果表明，导航与定向子指标达到R2=0.72，地标识别子指标为R2=0.50，具有显著预测能力。研究发现多项眼动特征与导航性能高度相关。该成果可推动认知评估工具发展，实现空间导航能力障碍的早期检测，尤其适用于认知衰退高风险个体。
原文摘要 · Abstract (English)
Spatial navigation is a complex cognitive function involving sensory inputs, such as visual, auditory, and proprioceptive information, to understand and move within space. This ability allows humans to create mental maps, navigate through environments, and process directional cues, crucial for exploring new places and finding one's way in unfamiliar surroundings. This study takes an algorithmic approach to extract indices relevant to human spatial navigation using eye movement data. Leveraging electrooculography signals, we analyzed statistical features and applied feature engineering techniques to study eye movements during navigation tasks. The proposed work combines signal processing and machine learning approaches to develop indices for navigation and orientation, spatial anxiety, landmark recognition, path survey, and path route. The analysis yielded five subscore indices with notable accuracy. Among these, the navigation and orientation subscore achieved an R2 score of 0.72, while the landmark recognition subscore attained an R2 score of 0.50. Additionally, statistical features highly correlated with eye movement metrics, including blinks, saccades, and fixations, were identified. The findings of this study can lead to more cognitive assessments and enable early detection of spatial navigation impairments, particularly among individuals at risk of cognitive decline.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。