Skip to Main content Skip to Navigation

Brain-Computer Interface with cortical electrical activity recording

Abstract : Brain Computer Interface (BCI) is a system for translation of brain neural activity into commands for external devices. This study was undertaken as a step toward the fully autonomous (self-paced) BCI functioning in natural environment which is of crucial importance for BCI clinical applications. To model the natural environment binary self-paced BCI experiments were carried out in freely moving animals. In comparison to the previous works, the long-term experimental sessions were carried out, which better comply with the real-life applications requirements. The main goal of the study was to discriminate the specific neuronal pattern related to the animal's control action against background brain activity of freely-moving animal. To achieve the necessary level of selectivity the Multi-Way Analysis was chosen since it provides a simultaneous signal processing in several domains, namely, temporal, frequency and spatial. To improve the capacity of the generic Multy-Way PLS approach for treatment of high-dimensional data, the Iterative NPLS algorithm is introduced in the current study. Having lower memory requirements it provides huge datasets treatment, allows high resolution, preserves the accuracy of the generic algorithm, and demonstrates better robustness. For adaptive calibration of BCI system the Recursive NPLS algorithm is proposed. Finally, the Penalized NPLS algorithm is developed for effective selection of feature subsets, namely, for subset of electrodes. The proposed algorithms were tested on artificial and real datasets. They demonstrated performance which either suppress or is comparable with one of the generic NPLS algorithm. Their computational efficiency is acceptable for the real-time applications. Developed algorithms were applied for calibration of the BCI system and were used in the real-time close-loop binary BCI experiments in animals. The proposed methods represent a prospective approach for further development of a human BCI system.
Document type :
Complete list of metadata

Cited literature [169 references]  Display  Hide  Download
Contributor : Abes Star :  Contact
Submitted on : Wednesday, October 31, 2012 - 12:02:13 PM
Last modification on : Sunday, October 25, 2020 - 7:08:06 AM
Long-term archiving on: : Friday, February 1, 2013 - 3:38:34 AM


Version validated by the jury (STAR)


  • HAL Id : tel-00747428, version 1



Andriy Yelisyeyev. Brain-Computer Interface with cortical electrical activity recording. Human health and pathology. Université de Grenoble, 2011. English. ⟨NNT : 2011GRENS038⟩. ⟨tel-00747428⟩



Record views


Files downloads