Bone-conduction-based brain computer interface paradigm - EEG signal processing, feature extraction and classification

Daiki Aminaka, Koichi Mori, Toshie Matsui, Shoji Makino, Tomasz M. Rutkowski

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The paper presents a novel bone-conduction based brain-computer interface paradigm. Four sub-threshold acoustic frequency stimulus patterns are presented to the subjects in an oddball paradigm allowing for 'aha-responses' generation to the attended targets. This allows for successful implementation of the bone-conduction based brain-computer interface (BCI) paradigm. The concept is confirmed with seven subjects in online bone-conducted auditory Morse-code patterns spelling BCI paradigm. We report also brain electrophysiological signal processing and classification steps taken to achieve the successful BCI paradigm. We also present a finding of the response latency variability in a function of stimulus difficulty.

Original languageEnglish
Title of host publicationProceedings - 2013 International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2013
Pages818-824
Number of pages7
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 9th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2013 - Kyoto, Japan
Duration: 2013 Dec 22013 Dec 5

Publication series

NameProceedings - 2013 International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2013

Conference

Conference2013 9th International Conference on Signal-Image Technology and Internet-Based Systems, SITIS 2013
Country/TerritoryJapan
CityKyoto
Period13/12/213/12/5

Keywords

  • Auditory BCI
  • Brain signal processing
  • EEG
  • P300

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Fingerprint

Dive into the research topics of 'Bone-conduction-based brain computer interface paradigm - EEG signal processing, feature extraction and classification'. Together they form a unique fingerprint.

Cite this