STF-KernelSHAP: A Model-Agnostic Space–Time–Frequency Shapley Framework for Physiologically Informed EEG Explainability
Computers · 03.07.2026 · 15 (7) · 428
DOI: 10.3390/computers15070428 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computers, online erschienen am 03.07.2026. Verfasst von Diego Armando Pérez-Rosero und 4 weiteren Autor:innen. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science, Technology and Innovation, Universidad Nacional de Colombia.
Abstract (Originalsprache)
Interpretability is essential for deploying deep learning (DL) models in electroencephalography (EEG)-based neurotechnology, particularly in brain–computer interfaces and clinical decision-support settings. Existing post hoc explainable artificial intelligence (XAI) methods often yield single-domain attribution maps, limiting their capacity to characterize the joint spatial, temporal, and spectral structure of EEG dynamics. In addition, perturbation-based strategies may disrupt physiological signal organization, whereas gradient-based methods require access to model internals and are therefore tied to specific classifier architectures. Here, we introduce space–time–frequency KernelSHAP (STF-KernelSHAP), a model-agnostic Shapley framework for physiologically coherent EEG explainability. The method comprises three stages. First, EEG trials are decomposed into structured channel–time–frequency cells using segment-wise spectral analysis. Second, coalitions are formed over complete channel–time–frequency cells and reconstructed in the signal domain to support physiologically informed perturbations. Third, class-conditional relevance is estimated with a KernelSHAP-based weighted surrogate model that uses only model outputs, enabling architecture-independent Shapley estimation. We evaluate STF-KernelSHAP on two prerecorded public datasets: the GIGA motor imagery/movement execution (MI-ME) dataset for motor imagery (MI) decoding and the IEEE DataPort EEG Data for Attention-Deficit/Hyperactivity Disorder (ADHD)/Control Children dataset for ADHD detection. For ADHD detection, the T-GARNet base classifier interpreted with STF-KernelSHAP achieved 73.33% accuracy and 79.86% area under the curve (AUC); these values characterize classifier performance rather than the explainer itself. We compare the framework against KernelSHAP, local interpretable model-agnostic explanations (LIME), Occlusion, Integrated Gradients, and gradient-weighted class activation mapping++ (Grad-CAM++). Fidelity is assessed with Deletion and remove and debias (ROAD), while qualitative analyses examine topographic and frequency-band attribution maps. Results show that STF-KernelSHAP remains functionally competitive with established XAI methods while providing window-dependent and frequency-specific explanations. Overall, STF-KernelSHAP offers a physiologically informed and model-agnostic alternative for multidomain EEG interpretability.
Förderung
- Ministry of Science, Technology and Innovation
- Universidad Nacional de Colombia
Zitieren
APA
Pérez-Rosero, D. A., Lopez-Boscan, A. C., Álvarez-Meza, A. M., Cárdenas-Peña, D. A., & Castellanos-Dominguez, G. (2026). STF-KernelSHAP: A Model-Agnostic Space–Time–Frequency Shapley Framework for Physiologically Informed EEG Explainability. Computers, 15(7), 428. https://doi.org/10.3390/computers15070428
Vancouver
Pérez-Rosero DA, Lopez-Boscan AC, Álvarez-Meza AM, Cárdenas-Peña DA, Castellanos-Dominguez G. STF-KernelSHAP: A Model-Agnostic Space–Time–Frequency Shapley Framework for Physiologically Informed EEG Explainability. Computers. 2026;15(7):428. doi:10.3390/computers15070428
BibTeX
@article{PrezRosero2026,
author = {Pérez-Rosero, Diego Armando and Lopez-Boscan, Andres Camilo and Álvarez-Meza, Andrés Marino and Cárdenas-Peña, David Augusto and Castellanos-Dominguez, German},
title = {STF-KernelSHAP: A Model-Agnostic Space–Time–Frequency Shapley Framework for Physiologically Informed EEG Explainability},
journal = {Computers},
year = {2026},
volume = {15},
number = {7},
pages = {428},
doi = {10.3390/computers15070428}
}
EUVIMED