We propose a neuro-symbolic architecture that learns four interpretable physiological concepts, oculomotor dynamics, gaze stability, prefrontal hemodynamics, and multimodal, from eye-tracking and neural hemodynamics, functional near-infrared spectroscopy, (fNIRS) windows using attention-based encoders, and combines them with differentiable approximate reasoning rules using learned weights and soft thresholds, to address both rigid hand-crafted rules and the lack of subject-level alignment diagnostics. We apply this system to fatigue classification from multimodal physiological signals, a domain that requires models that are accurate and interpretable, with internal reasoning that can be inspected for safety-critical use. In leave-one-subject-out evaluation on 18 participants (560 samples), the method achieves 72.1% +/- 12.3% accuracy, comparable to tuned baselines while exposing concept activations and rule firing strengths. Ablations indicate gains from participant-specific calibration (+5.2 pp), a modest drop without the fNIRS concept (-1.2 pp), and slightly better performance with Lukasiewicz operators than product (+0.9 pp). We also introduce concept fidelity, an offline per-subject audit metric from held-out labels, which correlates strongly with per-subject accuracy (r=0.843, p < 0.0001).

翻译：我们提出了一种神经符号架构，该架构从眼动追踪和神经血液动力学（功能性近红外光谱，fNIRS）数据中，利用基于注意力的编码器学习四个可解释的生理概念——眼动动力学、注视稳定性、前额血液动力学以及多模态特征，并通过可微分近似推理规则（使用学习到的权重和软阈值）将这些概念组合起来，以应对刚性手工规则和缺乏受试者级对齐诊断的问题。我们将该系统应用于基于多模态生理信号的疲劳分类，这一领域要求模型兼具准确性和可解释性，且内部推理过程可被审查以适用于安全关键场景。在18名受试者（共560个样本）的留一法评估中，该方法达到72.1%±12.3%的准确率，与调优后的基线模型性能相当，同时能够揭示概念激活和规则触发强度。消融实验表明，采用受试者特定校准可带来性能提升（+5.2个百分点），去除fNIRS概念会导致微弱下降（-1.2个百分点），而使用Lukasiewicz算子相比乘积算子性能略优（+0.9个百分点）。我们还引入了概念保真度——一种基于保留标签的离线受试者级审计指标，该指标与受试者级准确率高度相关（r=0.843，p<0.0001）。