EUVIMEDEUVIMED entdecken
Crossref

REFS: robust EEG feature selection with incomplete labels for multi-dimensional emotion recognition

Xueyuan Xu iD, Wenjia Dong iD, Fulin Wei iD, Li Zhuo iD

Journal of Neural Engineering · 01.12.2026 · 23 (6) · 066006

DOI: 10.1088/1741-2552/aeb97e ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 06.11.2026. Verfasst von Xueyuan Xu und 3 weiteren Autor:innen. Beteiligte Einrichtung: The Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, People's Republic of Chin…. Hauptthemen laut MEDLINE: Electroencephalography, Emotions, Brain-Computer Interfaces, Pattern Recognition, Automated. Die Arbeit nennt 52 Literaturangaben. Gefördert von: National Natural Science Foundation of China, The Open Project of the Engineering Research Center of Autonomous Unmanned System Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . Compared to single-type features, multi-type electroencephalography (EEG) features provide a multi-level representation for analyzing multi-dimensional emotions. However, the high dimensionality of multi-type EEG features, combined with the relatively small number of high-quality EEG samples, poses challenges such as classifier overfitting and suboptimal real-time performance in the multi-dimensional emotion recognition task. As the number of EEG channels increases, the issue will become increasingly severe. Moreover, practical applications of affective brain–computer interface (a-BCI) frequently encounters partial absence of multi-dimensional emotional label data due to diverse emotional self-assessment models, and ambiguity and variability in individual emotion perception. Approach . To address these challenges, this study proposes a novel robust EEG feature selection method for incomplete multi-dimensional emotion recognition. The method leverages adaptive orthogonal latent semantic indexing to reconstruct the multi-dimensional emotional label space through second-order and higher-order relations, which could reduce the negative impact of missing values and outliers on label reconstruction. Simultaneously, it employs least squares regression with graph-based manifold learning regularization and global feature redundancy minimization regularization to enable EEG feature subset selection despite missing information, ultimately achieving robust and fast EEG-based multi-dimensional emotion recognition. Main results . The proposed method was validated on three multi-dimensional emotional datasets with varying channel configurations, namely DREAMER, DEAP and high-density EEG database, under different label missing ratios. Experimental results show that the proposed method consistently outperforms thirteen state-of-the-art feature selection methods in terms of robustness for EEG emotional feature selection across various missing ratios. Significance . The proposed method provides a robust and efficient solution for feature selection in multi-dimensional emotion recognition under incomplete EEG label scenarios, delivering reliable performance for practical a-BCI applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyEmotionsBrain-Computer InterfacesPattern Recognition, AutomatedHumansAlgorithms

Stichwörter der Autor:innen

EEGadaptive orthogonal latent semantic indexingembedded feature selectionincomplete emotional labelsmulti-dimensional affective computing

Autor:innen und Institutionen

  • The Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology, Beijing, People's Republic of China.
  • Engineering Research Center of Autonomous Unmanned System Technology, Ministry of Education, Hefei, People's Republic of China.
  • School of Artificial Intelligence, Anhui University, Hefei, People's Republic of China.

ORCID-Profile: Xueyuan Xu, Wenjia Dong, Fulin Wei, Li Zhuo

Förderung

  • National Natural Science Foundation of China
  • The Open Project of the Engineering Research Center of Autonomous Unmanned System Technology

Zitieren

APA

Xu, X., Dong, W., Wei, F., & Zhuo, L. (2026). REFS: robust EEG feature selection with incomplete labels for multi-dimensional emotion recognition. Journal of Neural Engineering, 23(6), 066006. https://doi.org/10.1088/1741-2552/aeb97e

Vancouver

Xu X, Dong W, Wei F, Zhuo L. REFS: robust EEG feature selection with incomplete labels for multi-dimensional emotion recognition. Journal of Neural Engineering. 2026;23(6):066006. doi:10.1088/1741-2552/aeb97e

BibTeX
@article{Xu2026,
  author = {Xu, Xueyuan and Dong, Wenjia and Wei, Fulin and Zhuo, Li},
  title = {REFS: robust EEG feature selection with incomplete labels for multi-dimensional emotion recognition},
  journal = {Journal of Neural Engineering},
  year = {2026},
  volume = {23},
  number = {6},
  pages = {066006},
  doi = {10.1088/1741-2552/aeb97e}
}
Kostenlos starten →