TY - JOUR
T1 - Onset Classification in Hemodynamic Signals Measured during Three Working Memory Tasks Using Wireless Functional Near-Infrared Spectroscopy
AU - Dong, Sunghee
AU - Jeong, Jichai
N1 - Funding Information:
Manuscript received March 27, 2018; revised August 28, 2018 and November 14, 2018; accepted November 14, 2018. Date of publication November 30, 2018; date of current version December 12, 2018. This work was supported in part by the Institute for Information Communications Technology Promotion (IITP) Grant funded by the Korea government (No. 2017-0-00451) and in part by the Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Education, Science and Technology under Grant NRF-2018R1D1A1B07042378. (Corresponding author: Jichai Jeong.) The authors are with the Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, South Korea (e-mail:,zpfzpf123@korea.ac.kr; jcj@korea.ac.kr).
Publisher Copyright:
© 1995-2012 IEEE.
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Wireless wearable functional near-infrared spectroscopy (fNIRS) has attracted growing attention as a candidate for real-life brain monitoring systems. It is important to determine the onsets at which neuronal activation is evoked by cognitive status in real-time analysis. We propose a machine learning approach for the classification of cognitive event onsets (CogEOs) in hemodynamic signals during three cognitive tasks. The approach does not require a threshold to be set or additional measurement for the rest state. A support vector machine is trained by labeled features obtained from the mean amplitude of hemodynamic changes and then predicts the type of onset points. The problems caused by the imbalance between CogEOs and non-event onsets (NonEO) are solved by oversampling the feature samples labeled by cognitive events. By oversampling, the classification accuracy from an average of five classification scores reaches 74%, 77%, and 75% for the simple arithmetic, 1-back, and 2-back tasks. We achieve the best onset classification performance when the NonEOs are randomly distributed and when the subject is performing the 1-back task. Our study extends fNIRS to real-life applications by detecting the time point when brain activation starts among random observations using machine learning without additional triggers or threshold.
AB - Wireless wearable functional near-infrared spectroscopy (fNIRS) has attracted growing attention as a candidate for real-life brain monitoring systems. It is important to determine the onsets at which neuronal activation is evoked by cognitive status in real-time analysis. We propose a machine learning approach for the classification of cognitive event onsets (CogEOs) in hemodynamic signals during three cognitive tasks. The approach does not require a threshold to be set or additional measurement for the rest state. A support vector machine is trained by labeled features obtained from the mean amplitude of hemodynamic changes and then predicts the type of onset points. The problems caused by the imbalance between CogEOs and non-event onsets (NonEO) are solved by oversampling the feature samples labeled by cognitive events. By oversampling, the classification accuracy from an average of five classification scores reaches 74%, 77%, and 75% for the simple arithmetic, 1-back, and 2-back tasks. We achieve the best onset classification performance when the NonEOs are randomly distributed and when the subject is performing the 1-back task. Our study extends fNIRS to real-life applications by detecting the time point when brain activation starts among random observations using machine learning without additional triggers or threshold.
KW - Classification accuracy
KW - functional near-infrared spectroscopy
KW - onset classification
KW - working memory
UR - http://www.scopus.com/inward/record.url?scp=85057793707&partnerID=8YFLogxK
U2 - 10.1109/JSTQE.2018.2883890
DO - 10.1109/JSTQE.2018.2883890
M3 - Article
AN - SCOPUS:85057793707
SN - 0792-1233
VL - 25
JO - IEEE Journal of Selected Topics in Quantum Electronics
JF - IEEE Journal of Selected Topics in Quantum Electronics
IS - 1
M1 - 8554084
ER -