EUVIMEDEUVIMED entdecken
Crossref

CSTO-Net: cross-view spectral-transport and topology-operator network for EEG emotion recognition

Zhaoyi Sun iD, Jian Liu, Zhaolong Liu, Guangxin Wu, Jianning Hua iD

Physiological Measurement · 30.11.2026 · 47 (11) · 115003

DOI: 10.1088/1361-6579/aeb59e ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physiological Measurement, online erschienen am 05.11.2026. Verfasst von Zhaoyi Sun und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Science and Engineering, Northeastern University, Shenyang 110819, People's Republic of China. Hauptthemen laut MEDLINE: Electroencephalography, Emotions, Signal Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit nennt 62 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective. Multi-view electroencephalography (EEG) emotion recognition must decide how the spectral graph sets of different connectivity views correspond and how their graph propagation operators interact. We present CSTO-Net, a cross-view spectral-transport and topology-operator network for EEG-based emotion recognition. Approach. CSTO-Net integrates three window-wise views: dynamic differential entropy as node attributes, amplitude-envelope Pearson correlation coefficient (PCC) graphs, and phase-locking value (PLV) graphs. Cross-view spectral transport routing (CSTR) formulates PCC–PLV spectral correspondence as an entropy-regularized optimal-transport problem with explicit marginal constraints, deliberately separating correspondence estimation from band-importance estimation. Directional cross-topology modulation (DCTM) performs ordered composition of the two routed propagation operators on shared node features and encodes order-dependent propagation discrepancy via a provably skew-symmetric graph-operator commutator with signed decomposition. Main results. On the database for emotion analysis using physiological signals dataset, CSTO-Net achieves 93.95 ± 2.50% valence and 94.97 ± 2.72% arousal accuracy under the subject-dependent (SD) setting, and 93.73% and 94.54% under participant-wise five-fold subject-independent cross-validation across 32 participants. On the SJTU Emotion EEG Dataset, it achieves 93.12% under the standard SD split, 91.36% under 15-fold leave-one-subject-out evaluation across 15 participants, and 98.05 ± 2.32% under SD five-fold cross-validation. Ablation studies confirm that both CSTR and DCTM contribute substantially to recognition accuracy. Significance. These results demonstrate that explicit cross-view spectral correspondence and topology-operator-level interaction provide complementary benefits for EEG emotion recognition, offering an interpretable route for modeling order-sensitive interactions between functional connectivity views.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEmotionsSignal Processing, Computer-AssistedNeural Networks, ComputerHumans

Stichwörter der Autor:innen

EEG emotion recognitionfunctional connectivitygraph neural networkgraph-operator commutatormulti-view fusionoptimal transport

Autor:innen und Institutionen

  • College of Information Science and Engineering, Northeastern University, Shenyang 110819, People's Republic of China.
  • School of Intelligent Sensing and Optoelectronic Engineering, Northeastern University at Qinhuangdao, Qinhuangdao 066004, People's Republic of China.
  • School of Control Engineering, Northeastern University at Qinhuangdao, Qinhuangdao 066004, People's Republic of China.

ORCID-Profile: Zhaoyi Sun, Jianning Hua

Zitieren

APA

Sun, Z., Liu, J., Liu, Z., Wu, G., & Hua, J. (2026). CSTO-Net: cross-view spectral-transport and topology-operator network for EEG emotion recognition. Physiological Measurement, 47(11), 115003. https://doi.org/10.1088/1361-6579/aeb59e

Vancouver

Sun Z, Liu J, Liu Z, Wu G, Hua J. CSTO-Net: cross-view spectral-transport and topology-operator network for EEG emotion recognition. Physiological Measurement. 2026;47(11):115003. doi:10.1088/1361-6579/aeb59e

BibTeX
@article{Sun2026,
  author = {Sun, Zhaoyi and Liu, Jian and Liu, Zhaolong and Wu, Guangxin and Hua, Jianning},
  title = {CSTO-Net: cross-view spectral-transport and topology-operator network for EEG emotion recognition},
  journal = {Physiological Measurement},
  year = {2026},
  volume = {47},
  number = {11},
  pages = {115003},
  doi = {10.1088/1361-6579/aeb59e}
}
Kostenlos starten →