Natural fluctuations in sustained attention can lead to attentional failures in everyday tasks and even dangerous incidences. These fluctuations depend on personal factors, as well as task characteristics. So far, our understanding of sustained attention is partly due to the common usage of laboratory setups and tasks, and the complex interplay between behavior and brain activity. The focus of the current study was thus to test the feasibility of applying a single-channel wireless EEG to monitor patterns of sustained attention during (...) a set of ecological tasks. An EEG marker of attention (BEI—Brain Engagement Index) was continuously recorded from 42 healthy volunteers during auditory and visual tasks from the Test of Everyday Attention (TEA) and Trail Making Test (TMT). We found a descending pattern of both performance and BEI in the auditory tasks as task complexity increases, while the increase in performance and decrease in BEI on the visual task. In addition, patterns of BEI in the complex tasks were used to detect outliers and the optimal range of attention through exploratory models. The current study supports the feasibility of combined electrophysiological and neurocognitive investigation of sustained attention in ecological tasks yielding unique insights on patterns of sustained attention as a function of task modality and task complexity. (shrink)

A passive brain–computer interface based upon functional near-infrared spectroscopy brain signals is used for earlier detection of human drowsiness during driving tasks. This BCI modality acquired hemodynamic signals of 13 healthy subjects from the right dorsolateral prefrontal cortex of the brain. Drowsiness activity is recorded using a continuous-wave fNIRS system and eight channels over the right DPFC. During the experiment, sleep-deprived subjects drove a vehicle in a driving simulator while their cerebral oxygen regulation state was continuously measured. Vector phase analysis (...) was used as a classifier to detect drowsiness state along with sleep stage-based threshold criteria. Extensive training and testing with various feature sets and classifiers are done to justify the adaptation of threshold criteria for any subject without requiring recalibration. Three statistical features along with six VPA features were used. The average accuracies for the five classifiers are 90.9% for discriminant analysis, 92.5% for support vector machines, 92.3% for nearest neighbors, 92.4% for both decision trees, and ensembles over all subjects’ data. Trajectory slopes of CORE vector magnitude and angle: m and m are the best-performing features, along with ensemble classifier with the highest accuracy of 95.3% and minimum computation time of 40 ms. The statistical significance of the results is validated with a p-value of less than 0.05. The proposed passive BCI scheme demonstrates a promising technique for online drowsiness detection using VPA along with sleep stage classification. (shrink)