# A Neuro-Symbolic System for Interpretable Multimodal Physiological Signals Integration in Human Fatigue Detection

Source: [A Neuro-Symbolic System for Interpretable Multimodal Physiological Signals Integration in Human Fatigue Detection](<https://www.sota2.com/research/paper/69c4bd8f0636e5bf4afc75ad>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T05:00:12.960Z

Authors: Mohammadreza Jamalifard, Yaxiong Lei, Parasto Azizinezhad, Javier Fumanal-Idocin, Javier Andreu-Perez

Published: 2026-03-25T14:41:02.000Z

## Abstract

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).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Classification on Fatigue Detection Dataset (LOSO-CV)](<https://www.sota2.com/research/sota/classification-on-fatigue-detection-dataset-loso-cv.md>): Classification; Fatigue Detection Dataset (LOSO-CV); Accuracy: 72.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.24358>)

[PDF](<https://arxiv.org/pdf/2603.24358.pdf>)
