Towards a Brain-Computer Interface Based on Unsupervised Methods to Command a Lower-Limb Robotic Exoskeleton

Denis Delisle-Rodriguez, Ana Cecilia Villa-Parra, Teodiano Bastos

Research output: Contribution to conferencePaper

Abstract

This work presents a brain-computer interface (BCI) based on unsupervised methods for conveying control commands to a robotic exoskeleton, in order to provide support to patients with severe motor disability during walking. For this purpose, an adaptive spatial filter based on similarity indices is proposed to preserve the useful information on electroencephalography (EEG) signals. Additionally, a method for feature selection based on the Maximal Information Compression Index (MICI), and the representation entropy (RE) is used, increasing its robustness for uncertain patterns, such as gait planning. Good values of accuracy (ACC > 75%) and false positive rate (FPR< 10%) were obtained for four subjects. Thus, this BCI based on unsupervised method may be suitable to recognize uncertainty pattern, such as gait planning.

Original languageEnglish (US)
Pages1099-1104
Number of pages6
DOIs
StatePublished - 16 Jan 2019
EventProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 -
Duration: 16 Jan 2019 → …

Conference

ConferenceProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
Period16/01/19 → …

Keywords

  • brain-computer interface
  • feature selection
  • gait intention
  • gait planning
  • spatial filter

Fingerprint

Dive into the research topics of 'Towards a Brain-Computer Interface Based on Unsupervised Methods to Command a Lower-Limb Robotic Exoskeleton'. Together they form a unique fingerprint.

Cite this