EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantum-Kernel Learning for Subject-Independent EEG Emotion Recognition with Spectral-Connectivity Features

Gaochao Cui, Yutaka Tokuda iD, Hideaki Touyama iD

Sensors · 29.10.2026 · 26 (21) · 6840

DOI: 10.3390/s26216840 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.10.2026. Verfasst von Gaochao Cui und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Systems Engineering, Faculty of Information Engineering, Toyama Prefectural University, Imizu 939-0398, Japan. Hauptthemen laut MEDLINE: Electroencephalography, Emotions, Machine Learning. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Toyama Dai-ichi Bank Scholarship Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electroencephalography (EEG)-based emotion recognition remains challenging under subject-independent evaluation because of substantial inter-subject variability. This study investigates the feasibility of state-fidelity-based quantum-kernel learning for subject-independent valence and arousal recognition using differential entropy (DE) and phase-locking value (PLV) features. Using the DEAP dataset, DE and PLV features were extracted and evaluated individually and in combination, with subject-wise normalization and F-score feature selection applied within the evaluation framework. Six features were retained for valence and eight for arousal. The selected features were encoded using a Qiskit ZFeatureMap, and the fidelity-based quantum kernel was evaluated through statevector simulation on a classical computer. Quantum-kernel, Linear, and RBF SVMs were compared using nested participant-grouped cross-validation across DE, PLV, and DE–PLV feature representations. For valence, the quantum-kernel SVM using DE features achieved the highest mean balanced accuracy of 59.18%. For arousal, the Linear SVM using DE features achieved the highest mean balanced accuracy of 54.16%. Overall, the three classifiers showed comparable performance across the evaluated feature representations. These results support the feasibility of state-fidelity-based quantum similarity for subject-independent EEG emotion recognition.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEmotionsMachine LearningHumansSupport Vector MachineEntropyAlgorithmsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

DEAPEEGdifferential entropyelectroencephalographyemotion recognitionphase-locking valuequantum kernelquantum machine learningsupport vector machine

Autor:innen und Institutionen

  • Department of Information Systems Engineering, Faculty of Information Engineering, Toyama Prefectural University, Imizu 939-0398, Japan.
  • Independent Researcher, Higashimatsuyama 355-0028, Japan.

ORCID-Profile: Yutaka Tokuda, Hideaki Touyama

Förderung

  • Toyama Dai-ichi Bank Scholarship Foundation

Zitieren

APA

Cui, G., Tokuda, Y., & Touyama, H. (2026). Quantum-Kernel Learning for Subject-Independent EEG Emotion Recognition with Spectral-Connectivity Features. Sensors, 26(21), 6840. https://doi.org/10.3390/s26216840

Vancouver

Cui G, Tokuda Y, Touyama H. Quantum-Kernel Learning for Subject-Independent EEG Emotion Recognition with Spectral-Connectivity Features. Sensors. 2026;26(21):6840. doi:10.3390/s26216840

BibTeX
@article{Cui2026,
  author = {Cui, Gaochao and Tokuda, Yutaka and Touyama, Hideaki},
  title = {Quantum-Kernel Learning for Subject-Independent EEG Emotion Recognition with Spectral-Connectivity Features},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {6840},
  doi = {10.3390/s26216840}
}
Kostenlos starten →