A Lightweight Hybrid-Attention Conformer for Affective State Recognition from Wearable EEG
Sensors · 03.11.2026 · 26 (21) · 6943
DOI: 10.3390/s26216943 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 03.11.2026. Verfasst von Mustafa Eriş und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Digital Forensics Engineering, Faculty of Technology, Fırat University, Elazığ 23119, Türkiye. Hauptthemen laut MEDLINE: Electroencephalography, Wearable Electronic Devices, Attention. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fırat University, Scientific Research Projects Coordination Unit of Fırat University.
Abstract (Originalsprache)
Recognizing affective states from electroencephalography (EEG) is a core task in affective computing, with applications in mental health monitoring and public safety. Most existing approaches rely on handcrafted features or image-based transformations of EEG, while transformer models capture global context at high computational cost. This study proposes KimiFormer, an end-to-end hybrid-attention Conformer that classifies raw EEG directly. A hierarchical Spatio-Temporal Stemming (STS) module tokenizes the multichannel signal and learns inter-electrode relationships. Stacked Conformer blocks combine linear and full attention in a 3:1 ratio, reducing computational cost while preserving long-range modeling. The model was evaluated on the public EEG Violence Dataset, recorded with a 14-channel wearable headset from 14 participants viewing violent and neutral videos. Under record-wise leave-one-record-out cross-validation with nested selection of the training hyperparameters, KimiFormer achieved 95.5% accuracy (97.0% under 10-fold cross-validation). On the external DREAMER dataset, its subject-independent performance remained close to chance (balanced accuracy 52.7% for valence and 50.2% for arousal), as did that of two established raw-EEG models. Ablation showed the STS module to be essential (65% accuracy without it). With 3.2 M parameters, 1.51 GFLOPs and an inference latency of 15.64 ms per sample, KimiFormer is suited to real-time, on-device processing of low-channel wearable EEG.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Digital Forensics Engineering, Faculty of Technology, Fırat University, Elazığ 23119, Türkiye.
ORCID-Profile: Mustafa Eriş, Fatma Güneş Eriş, Orhan Yaman
Förderung
- Fırat University
- Scientific Research Projects Coordination Unit of Fırat University
Zitieren
APA
Eriş, M., Eriş, F. G., & Yaman, O. (2026). A Lightweight Hybrid-Attention Conformer for Affective State Recognition from Wearable EEG. Sensors, 26(21), 6943. https://doi.org/10.3390/s26216943
Vancouver
Eriş M, Eriş FG, Yaman O. A Lightweight Hybrid-Attention Conformer for Affective State Recognition from Wearable EEG. Sensors. 2026;26(21):6943. doi:10.3390/s26216943
BibTeX
@article{Eri2026,
author = {Eriş, Mustafa and Eriş, Fatma Güneş and Yaman, Orhan},
title = {A Lightweight Hybrid-Attention Conformer for Affective State Recognition from Wearable EEG},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {6943},
doi = {10.3390/s26216943}
}
EUVIMED