TY  - JOUR
KW  - Brain; Hemodynamics; Infrared devices; Near infrared spectroscopy; Signal processing; Support vector machines
KW  -  Cerebral hemodynamics; Cognitive training; Contribution ratios; Functional near-infrared spectroscopy (fnirs); Linear Support Vector Machines; Logical operators; Mental workload assessments; Multiple features
KW  -  Brain computer interface
KW  -  accuracy; adult; Article; artificial neural network; brain region; cognition; controlled study; deoxygenation; diagnostic test accuracy study; electroencephalography; emotion; feasibility study; female; functional magnetic resonance imaging; functional near-infrared spectroscopy; gray matter; heart rate; hemodynamics; human; human experiment; imagery; infrared spectroscopy; learning algorithm; linear support vector machine; male; mental disease; mouse; nerve cell network; neurofeedback; nonhuman; nuclear magnetic resonance imaging; prefrontal cortex; psychophysiology; receiver operating characteristic; sensitivity and specificity; Short Form 36; signal noise ratio; skin conductance; support vector machine; task performance; trail making test; training; working memory; workload; near infrared spectroscopy; prefrontal cortex; support vector machine
KW  -  Hemodynamics; Humans; Prefrontal Cortex; Spectroscopy
KW  -  Near-Infrared; Support Vector Machine; Workload
ID  - scholars12555
IS  - 11
N2  - Knowing the actual level of mental workload is important to ensure the efficacy of brain-computer interface (BCI) based cognitive training. Extracting signals from limited area of a brain region might not reveal the actual information. In this study, a functional near-infrared spectroscopy (fNIRS) device equipped with multi-channel and multi-distance measurement capability was employed for the development of an analytical framework to assess mental workload in the prefrontal cortex (PFC). In addition to the conventional features, e.g. hemodynamic slope, we introduced a new feature - deep contribution ratio which is the proportion of cerebral hemodynamics to the fNIRS signals. Multiple sets of features were examined by a simple logical operator to suppress the false detection rate in identifying the activated channels. Using the number of activated channels as input to a linear support vector machine (SVM), the performance of the proposed analytical framework was assessed in classifying three levels of mental workload. The best set of features involves the combination of hemodynamic slope and deep contribution ratio, where the identified number of activated channels returned an average accuracy of 80.6 in predicting mental workload, compared to a single conventional feature (accuracy: 59.8). This suggests the feasibility of the proposed analytical framework with multiple features as a means towards a more accurate assessment of mental workload in fNIRS-based BCI applications. © 2001-2011 IEEE.
Y1  - 2020///
VL  - 28
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85095862002&doi=10.1109%2fTNSRE.2020.3026991&partnerID=40&md5=289a34852adab11d22f73f1c6e5247a7
JF  - IEEE Transactions on Neural Systems and Rehabilitation Engineering
A1  - Lim, L.G.
A1  - Ung, W.C.
A1  - Chan, Y.L.
A1  - Lu, C.-K.
A1  - Sutoko, S.
A1  - Funane, T.
A1  - Kiguchi, M.
A1  - Tang, T.B.
AV  - none
TI  - A unified analytical framework with multiple fNIRS features for mental workload assessment in the prefrontal cortex
SP  - 2367
N1  - cited By 15
SN  - 15344320
PB  - Institute of Electrical and Electronics Engineers Inc.
EP  - 2376
ER  -