EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Emotion Recognition Based on Fusion of Topological Features and Trajectory Images Derived from EEG Phase Space Reconstruction

Tianyue Liang, Xuanpeng Zhu, Yu Song iD

Sensors · 14.05.2026 · 26 (10) · 3102

DOI: 10.3390/s26103102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.05.2026. Verfasst von Tianyue Liang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Beijing-Dublin International College, Beijing University of Technology, Beijing 100124, China. Hauptthemen laut MEDLINE: Emotions, Electroencephalography. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Technologies R&D Program of Tianjin.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electroencephalogram (EEG) signals, as a direct measure of the brain’s cortical electrophysiological activity, can objectively capture emotion-induced neural changes. Phase space reconstruction is an effective method for processing nonlinear time series. It maps time series to a high-dimensional phase space, thereby better preserving subtle dynamic information in the signal. This paper proposes a method for emotion recognition in EEG signals based on phase space reconstruction. First, the macro-topological features of the trajectories are constructed via phase space reconstruction. The time delay and embedding dimension are then optimized using the minimum cross-prediction error and the G-P method, followed by dimensionality reduction to a two-dimensional plane via local linear embedding. Building on this foundation, and in response to the limitations of manually designed features, we further propose a deep learning-based method for extracting multiscale dynamic features from trajectory images. The designed GN-MVXXS framework, which utilizes a granularity-adaptive module to adaptively switch the receptive field and a noise-filtering module to suppress isolated noise points, thereby effectively uncovers microscopic evolutionary features at the image level. Finally, to leverage the complementary strengths of macro- and micro-level information, we propose a fusion method based on dynamic attention. This approach aligns the dual representational dimensions through global average pooling and nonlinear dimension expansion, and utilizes a dynamic attention mechanism to adaptively assign feature weights, enabling the model to collaboratively enhance both overall dynamic patterns and local details based on sample characteristics. The experimental results show that the model achieved an accuracy of 96.11% in the three-class classification task on the SEED, 86.33% in the four-class classification task on the HIED, and 83.67% in classification across normal-hearing and hearing-impaired individuals, significantly outperforming single-feature models and traditional fusion methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

EmotionsElectroencephalographyDatasets as TopicHumansMaleFemaleSignal Processing, Computer-AssistedBrainDeep Learning

Stichwörter der Autor:innen

EEG emotion recognitionphase space reconstructiontopological featurestrajectory images

Autor:innen und Institutionen

  • Beijing-Dublin International College, Beijing University of Technology, Beijing 100124, China.
  • School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China.

ORCID-Profile: Yu Song

Förderung

  • the Key Technologies R&D Program of Tianjin

Zitieren

APA

Liang, T., Zhu, X., & Song, Y. (2026). Emotion Recognition Based on Fusion of Topological Features and Trajectory Images Derived from EEG Phase Space Reconstruction. Sensors, 26(10), 3102. https://doi.org/10.3390/s26103102

Vancouver

Liang T, Zhu X, Song Y. Emotion Recognition Based on Fusion of Topological Features and Trajectory Images Derived from EEG Phase Space Reconstruction. Sensors. 2026;26(10):3102. doi:10.3390/s26103102

BibTeX
@article{Liang2026,
  author = {Liang, Tianyue and Zhu, Xuanpeng and Song, Yu},
  title = {Emotion Recognition Based on Fusion of Topological Features and Trajectory Images Derived from EEG Phase Space Reconstruction},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3102},
  doi = {10.3390/s26103102}
}
Kostenlos starten →