Share Email Print
cover

Journal of Biomedical Optics

Multiclass classification of hemodynamic responses for performance improvement of functional near-infrared spectroscopy-based brain–computer interface
Author(s): Jaeyoung Shin; Jichai Jeong
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

We improved the performance of a functional near-infrared spectroscopy (fNIRS)-based brain–computer interface based on relatively short task duration and multiclass classification. A custom-built eight-channel fNIRS system was used over the motor cortex areas in both hemispheres to measure the hemodynamic responses evoked by four different motor tasks (overt execution of arm lifting and knee extension for both sides) instead of finger tapping. The hemodynamic responses were classified using the naive Bayes classifier. Among the mean, max, slope, variance, and median of the signal amplitude and the time lag of the signal, several signal features are chosen to obtain highest classification accuracy. Ten runs of threefold cross-validation were conducted, which yielded classification acWe improved the performance of a functional near-infrared spectroscopy (fNIRS)-based brain–computer interface based on relatively short task duration and multiclass classification. A custom-built eight-channel fNIRS system was used over the motor cortex areas in both hemispheres to measure the hemodynamic responses evoked by four different motor tasks (overt execution of arm lifting and knee extension for both sides) instead of finger tapping. The hemodynamic responses were classified using the naive Bayes classifier. Among the mean, max, slope, variance, and median of the signal amplitude and the time lag of the signal, several signal features are chosen to obtain highest classification accuracy. Ten runs of threefold cross-validation were conducted, which yielded classification accuracies of 87.1%±2.4% to 95.5%±2.4%, 77.5%±1.9% to 92.4%±3.2%, and 73.8%±3.5% to 91.5%±1.4% for the binary, ternary, and quaternary classifications, respectively. Eight seconds of task duration for obtaining sufficient quaternary classification accuracy was suggested. The bit transfer rate per minute (BPM) based on the quaternary classification accuracy was investigated. A BPM can be achieved from 2.81 to 5.40  bits/min.

Paper Details

Date Published: 26 June 2014
PDF: 9 pages
J. Biomed. Opt. 19(6) 067009 doi: 10.1117/1.JBO.19.6.067009
Published in: Journal of Biomedical Optics Volume 19, Issue 6
Show Author Affiliations
Jaeyoung Shin, Korea Univ. (Korea, Republic of)
Jichai Jeong, Korea Univ. (Republic of Korea)


© SPIE. Terms of Use
Back to Top