EUVIMEDEUVIMED entdecken
Crossref

CTSSP: A temporal–spectral-spatial joint optimization algorithm for motor imagery EEG decoding

Lincong Pan iD, Kun Wang iD, Weibo Yi, Yang Zhang iD, Minpeng Xu iD, Dong Ming

Journal of Neural Engineering · 01.02.2026 · 23 (1) · 016009

DOI: 10.1088/1741-2552/ae34ea ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 20.01.2026. Verfasst von Lincong Pan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, People's Republic of China. Hauptthemen laut MEDLINE: Electroencephalography, Algorithms, Brain-Computer Interfaces, Imagination. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Brain Science and Brain-like Intelligence Technology-National Science and Technology Major Project, Emerging Frontiers Cultivation Program of Tianjin University Interdisciplinary Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective. Motor imagery brain–computer interfaces hold significant promise for neurorehabilitation, yet their performance is often compromised by electroencephalography (EEG) non-stationarity, low signal-to-noise ratios, and severe cross-session variability. Current decoding methods typically suffer from fragmented optimization, treating temporal, spectral, and spatial features in isolation. Approach. We propose common temporal–spectral-spatial patterns (CTSSP), a unified framework that jointly optimizes filters across all three domains. The algorithm integrates: (1) multi-scale temporal segmentation to capture dynamic neural evolution, (2) channel-adaptive finite impulse response filters to enhance task-relevant rhythms, and (3) low-rank regularization to improve generalization. Main results. Evaluated across five public datasets, CTSSP achieves state-of-the-art performance. It yielded mean accuracies of 76.9% (within-subject), 68.8% (cross-session), and 69.8% (cross-subject). In within-subject and cross-session scenarios, CTSSP significantly outperformed competing baselines by margins of 2.6%–14.6% ( p < 0.001) and 2.3%–13.8% ( p < 0.05), respectively. In cross-subject tasks, it achieved the highest average accuracy, proving competitive against deep learning models. Neurophysiological visualization confirms that the learned filters align closely with motor cortex activation mechanisms. Significance. CTSSP effectively overcomes the limitations of decoupled feature extraction by extracting robust, interpretable, and coupled temporal–spectral-spatial patterns. It offers a powerful, data-efficient solution for decoding MI EEG in noisy, non-stationary environments. The code is available at https://github.com/PLC-TJU/CTSSP .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyAlgorithmsBrain-Computer InterfacesImaginationMotor CortexHumansMovement

Stichwörter der Autor:innen

brain–computer interface (BCI)cross-session decodingelectroencephalography (EEG)motor imagery (MI)temporal–spectral-spatial joint optimization

Autor:innen und Institutionen

  • Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, People's Republic of China.
  • School of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin 300072, People's Republic of China.
  • Haihe Laboratory of Brain-computer Interaction and Human-machine Integration, Tianjin 300392, People's Republic of China.
  • Beijing Machine and Equipment Institute, Beijing 100192, People's Republic of China.
  • Rehabilitation and Physical Therapy Department, Shandong University of Traditional Chinese Medicine Affiliated Hospital, Jinan 250011, People's Republic of China.

ORCID-Profile: Lincong Pan, Kun Wang, Yang Zhang, Minpeng Xu

Förderung

  • National Natural Science Foundation of China
  • Brain Science and Brain-like Intelligence Technology-National Science and Technology Major Project
  • Emerging Frontiers Cultivation Program of Tianjin University Interdisciplinary Center

Zitieren

APA

Pan, L., Wang, K., Yi, W., Zhang, Y., Xu, M., & Ming, D. (2026). CTSSP: A temporal–spectral-spatial joint optimization algorithm for motor imagery EEG decoding. Journal of Neural Engineering, 23(1), 016009. https://doi.org/10.1088/1741-2552/ae34ea

Vancouver

Pan L, Wang K, Yi W, Zhang Y, Xu M, Ming D. CTSSP: A temporal–spectral-spatial joint optimization algorithm for motor imagery EEG decoding. Journal of Neural Engineering. 2026;23(1):016009. doi:10.1088/1741-2552/ae34ea

BibTeX
@article{Pan2026,
  author = {Pan, Lincong and Wang, Kun and Yi, Weibo and Zhang, Yang and Xu, Minpeng and Ming, Dong},
  title = {CTSSP: A temporal–spectral-spatial joint optimization algorithm for motor imagery EEG decoding},
  journal = {Journal of Neural Engineering},
  year = {2026},
  volume = {23},
  number = {1},
  pages = {016009},
  doi = {10.1088/1741-2552/ae34ea}
}
Kostenlos starten →