EUVIMEDEUVIMED entdecken
Crossref

Hands-free motor imagery EEG classification via LLM multi-agents

Ruiyu Zhao, Shurui Li, Xinjie He, Xingyu Wang, Andrzej Cichocki, Yunhe Lu, Jing Jin

Journal of Neuroscience Methods · 2026

DOI: 10.1016/j.jneumeth.2026.110871 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2026. Verfasst von Ruiyu Zhao und 6 weiteren Autor:innen. Beteiligte Einrichtung: The Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shangha…. Hauptthemen laut MEDLINE: Imagination, Electroencephalography, Brain-Computer Interfaces, Signal Processing, Computer-Assisted. Die Arbeit nennt 54 Literaturangaben. Gefördert von: Science and Technology Commission of Shanghai Municipality, East China University of Science and Technology, National Science and Technology Major Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Motor imagery (MI) brain-computer interfaces (BCI) rely on precise electroencephalogram (EEG) classification. However, issues such as the reliance on extensive manual experience for MI-EEG model design, parameter tuning, and optimization directions, along with the poor task flexibility of foundation models and state degradation during long-term multi-agent iterations, severely restrict the state-of-the-art (SOTA) efficiency of MI-EEG. NEW METHOD: To address these challenges, we propose AutoMI, a novel framework that uses multi-agent automated rapid iterations to construct SOTA MI-EEG models. AutoMI introduces a hybrid decision mechanism that tightly couples Q-learning strategies with deterministic rules. By integrating planning, execution, and output agents with predefined tools, AutoMI ensures broad general applicability across various hyperparameter optimizations and structural improvements. Furthermore, AutoMI integrates experience tracking and rollback mechanisms to prevent ambiguous optimization. RESULTS: In evaluations on the IV2a, OpenBMI, and ECUST-MI datasets, the SOTA models finally constructed through AutoMI iterations achieve accuracies of 77.62%, 78.08%, and 83.02%, with maximum improvement reaching 24.69%, 23.35%, and 23.28% respectively. Furthermore, the average time per iteration for a single subject on the OpenBMI dataset is approximately 500 s. COMPARISON WITH EXISTING METHODS: Compared with automated optimization algorithms, the accuracies increase by 18.42%, 9.27%, and 19.25% respectively, demonstrating the effectiveness of the proposed AutoMI framework and proving that its optimization capability reaches SOTA. CONCLUSION: Experimental results indicate that AutoMI provides a novel perspective and framework design reference for future BCI model optimization.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ImaginationElectroencephalographyBrain-Computer InterfacesSignal Processing, Computer-AssistedMachine LearningMotor ActivityHumansAlgorithms

Stichwörter der Autor:innen

Automatic model optimizationBrain–computer interfaceMI-EEG classificationMotor imageryMulti-agent system

Autor:innen und Institutionen

  • The Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China.
  • School of Math, East China University of Science and Technology, Shanghai, 200237, China.
  • Laboratory for Advanced Brain Signal Processing, RIKEN Brain Science Institute, Wako-shi, 351-0198, Japan; Systems Research Institute, Polish Academy of Sciences, Warsaw, 01-447, Poland; Department of Informatics, Nicol…
  • Shanghai Lansheng Brain Hospital Investment Co., Ltd., Shanghai, 200336, China.
  • The Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China; School of Math, East China University of Science and…

Förderung

  • Science and Technology Commission of Shanghai Municipality
  • East China University of Science and Technology
  • National Science and Technology Major Project

Zitieren

APA

Zhao, R., Li, S., He, X., Wang, X., Cichocki, A., Lu, Y., & Jin, J. (2026). Hands-free motor imagery EEG classification via LLM multi-agents. Journal of Neuroscience Methods. https://doi.org/10.1016/j.jneumeth.2026.110871

Vancouver

Zhao R, Li S, He X, Wang X, Cichocki A, Lu Y, et al. Hands-free motor imagery EEG classification via LLM multi-agents. Journal of Neuroscience Methods. 2026. doi:10.1016/j.jneumeth.2026.110871

BibTeX
@article{Zhao2026,
  author = {Zhao, Ruiyu and Li, Shurui and He, Xinjie and Wang, Xingyu and Cichocki, Andrzej and Lu, Yunhe and Jin, Jing},
  title = {Hands-free motor imagery EEG classification via LLM multi-agents},
  journal = {Journal of Neuroscience Methods},
  year = {2026},
  doi = {10.1016/j.jneumeth.2026.110871}
}
Kostenlos starten →