Sustained attention is the ability to keep focused and vigilance for long time in external stimulation, which was crucial in safe-critical human-machine system. While the ability of sustained attention will decline because of mental fatigue, even lead to serious accidents in fatigue state. Therefore, it is of great significance to explore the impact of fatigue on sustained attention. Functional Near-Infrared Spectroscopy (fNIRS) can measure cerebral hemoglobin in order to reflect cognitive function indirectly. In previous related fatigue studies, monotonous and long-time CPT (continuous performance test task) was often used to explore the performance change and brain activity, but the effect of time on task (TOT) was always involved. In this study, in order to avoid the TOT effect, the sustained attention task and fatigue task were separated. It was adopted in the study that the modified continuous performance test (CPT) was chosen as the sustained attention task and verbal 2-back task as the fatigue induced task. The fNIRS signals were extracted from 10 channels in the prefrontal cortex (PFC) from 20 healthy subjects. Studies found that cerebral lateralization increased significantly from alert to fatigue state in sustained attention task. Besides, Average oxyhemoglobin (HBO) of PFC increased significantly from alert to fatigue task, and the spatial pattern of activity of oxyhemoglobin also changed, which c be sensitive features to fatigue detection.
Functional near-infrared spectroscopy (fNIRS), which can measure cortex hemoglobin activity, has been widely adopted in brain-computer interface (BCI). To explore the feasibility of recognizing motor imagery (MI) and motor execution (ME) in the same motion. We measured changes of oxygenated hemoglobin (HBO) and deoxygenated hemoglobin (HBR) on PFC and Motor Cortex (MC) when 15 subjects performing hand extension and finger tapping tasks. The mean, slope, quadratic coefficient and approximate entropy features were extracted from HBO as the input of support vector machine (SVM). For the four-class fNIRS-BCI classifiers, we realized 87.65% and 87.58% classification accuracy corresponding to hand extension and finger tapping tasks. In conclusion, it is effective for fNIRS-BCI to recognize MI and ME in the same motion.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.