发表机构
College of Advanced Interdisciplinary Studies, Central South University of Forestry and Technology; Chow Yei Ching School of Graduate Studies, City University of Hong Kong; College of Computer and Mathematics, Central South University of Forestry and Technology; College of Computer Science and Electronic Engineering, Hunan University（中南林业科技大学先进交叉学科学院; 香港城市大学曹光彪研究生院; 中南林业科技大学计算机与数学学院; 湖南大学计算机科学与电子工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出结合智能眼镜与智能手机的智能决策支持系统，利用注视微运动实现非侵入式情感监测，通过混合AI流水线与少样本个性化机制，在60名志愿者测试中取得83.6%的个性化F1值，建立了可部署的实时情感监测范式。
AI 中文摘要
心理障碍的日益流行催生了对有效情感监测的需求，但当前依赖面部或生理信号的方法往往存在侵入性和隐私问题。本文提出一种智能决策支持系统及普及型边缘计算框架，利用智能眼镜和配套智能手机从微观视觉注视模式推断情感状态。该系统超越传统宏观注视指标，提取并分解三种不同的神经生理微运动：微眼跳、眼漂移和眼微震颤。我们引入可解释的混合人工智能流水线，结合多头注意力机制、极端梯度提升和支持向量机，以提取深度时间特征、量化其生理重要性并执行高效的设备端分类。通过包含60名志愿者的广泛评估，我们在严格的留一受试者交叉验证协议下，于受控和自然移动场景中对该框架进行了严格验证。消融研究明确表明，这些注视微运动相比传统宏观特征对情感推断具有更强的区分性。此外，结合当代情感科学，该系统引入少样本个性化机制，以弥合通用生理基线与个体情感异质性之间的差距，实现了83.6%的高鲁棒个性化F1值。本研究建立了一种可生理解释、非侵入性且可部署的连续实时情感监测范式。
英文摘要
The rising prevalence of psychological disorders necessitates effective emotion monitoring, yet current methods relying on facial or physiological signals often suffer from intrusiveness and privacy issues. This paper proposes an intelligent decision support system and pervasive edge-computing framework that leverages smart glasses and a companion smartphone to infer emotional states from microscopic visual fixation patterns. Moving beyond traditional macroscopic gaze metrics, the proposed system extracts and decomposes three distinct neurophysiological micro-movements: microsaccades, ocular drifts, and ocular microtremors. We introduce an interpretable hybrid artificial intelligence pipeline combining a multi-head attention mechanism, extreme gradient boosting, and a support vector machine to extract deep temporal features, quantify their physiological importance, and perform efficient on-device classification. Through an extensive evaluation involving 60 volunteers, we rigorously validate the framework under a strict leave-one-subject-out cross-validation protocol across both controlled and naturalistic mobile scenarios. Ablation studies unequivocally demonstrate that these fixational micro-movements are substantially more discriminative for emotion inference than traditional macroscopic features. Furthermore, aligned with contemporary affective science, the system incorporates a few-shot personalization mechanism to bridge universal physiological baselines with individual emotional heterogeneity, achieving a highly robust personalized F1-score of 83.6%. This work establishes a physiologically interpretable, unobtrusive, and deployable paradigm for continuous real-time emotion monitoring.
Comments22 pages, 15 Figures
