Bone-Conduction-Based Brain Computer Interface Paradigm -- EEG Signal Processing, Feature Extraction and Classification

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.