Behavioral and Neurophysiological Signatures of Benzodiazepine-Related Driving Impairments.

Impaired driving due to drug use is a growing problem worldwide; estimates show that 18-23.5% of fatal accidents, and up to 34% of injury accidents may be caused by drivers under the influence of drugs (Drummer et al., 2003; Walsh et al., 2004; NHTSA, 2010). Furthermore, at any given time, up to 16% of drivers may be using drugs that can impair one's driving abilities (NHTSA, 2009). Currently, drug recognition experts (DREs; law enforcement officers with specialized training to identify drugged driving), have the most difficult time with identifying drivers potentially impaired on central nervous system (CNS) depressants (Smith et al., 2002). The fact that the use of benzodiazepines, a type of CNS depressant, is also associated with the greatest likelihood of causing accidents (Dassanayake et al., 2011), further emphasizes the need to improve research tools in this area which can facilitate the refinement of, or additions to, current assessments of impaired driving. Our laboratories collaborated to evaluate both the behavioral and neurophysiological effects of a benzodiazepine, alprazolam, in a driving simulation (miniSim(TM)). This drive was combined with a neurocognitive assessment utilizing time synched neurophysiology (electroencephalography, ECG). While the behavioral effects of benzodiazepines are well characterized (Rapoport et al., 2009), we hypothesized that, with the addition of real-time neurophysiology and the utilization of simulation and neurocognitive assessment, we could find objective assessments of drug impairment that could improve the detection capabilities of DREs. Our analyses revealed that (1) specific driving conditions were significantly more difficult for benzodiazepine impaired drivers and (2) the neurocognitive tasks' metrics were able to classify "impaired" vs. "unimpaired" with up to 80% accuracy based on lane position deviation and lane departures. While this work requires replication in larger studies, our results not only identified criteria that could potentially improve the identification of benzodiazepine intoxication by DREs, but also demonstrated the promise for future studies using this approach to improve upon current, real-world assessments of impaired driving.

Characterizing donation behavior from psychophysiological indices of narrative experience.

Research on narrative persuasion has yet to investigate whether this process influences behavior. The current study explored whether: (1) a narrative could persuade participants to donate to a charity, a prosocial, behavioral decision; (2) psychophysiological metrics can delineate the differences between donation/non-donation behaviors; and (3) donation behavior can be correlated with measures of psychophysiology, self-reported reactions to the narrative, and intrinsic characteristics. Participants (n = 49) completed personality/disposition questionnaires, viewed one of two versions of a narrative while EEG and ECG were recorded, completed a questionnaire regarding their reactions to the narrative, and were given an opportunity to donate to a charity related to the themes of the narrative. Results showed that: (1) 34.7% of participants donated; (2) psychophysiological metrics successfully delineated between donation behaviors and the effects of narrative version; and (3) psychophysiology and reactions to the narrative were better able to explain the variance (88 and 65%, respectively) in the amount donated than all 3 metrics combined as well as any metric alone. These findings demonstrate the promise of narrative persuasion for influencing prosocial, behavioral decisions. Our results also illustrate the utility of the previously stated metrics for understanding and possibly even manipulating behaviors resulting from narrative persuasion.

Modeling temporal sequences of cognitive state changes based on a combination of EEG-engagement, EEG-workload, and heart rate metrics.

The objective of this study was to investigate the feasibility of physiological metrics such as ECG-derived heart rate and EEG-derived cognitive workload and engagement as potential predictors of performance on different training tasks. An unsupervised approach based on self-organizing neural network (NN) was utilized to model cognitive state changes over time. The feature vector comprised EEG-engagement, EEG-workload, and heart rate metrics, all self-normalized to account for individual differences. During the competitive training process, a linear topology was developed where the feature vectors similar to each other activated the same NN nodes. The NN model was trained and auto-validated on combat marksmanship training data from 51 participants that were required to make "deadly force decisions" in challenging combat scenarios. The trained NN model was cross validated using 10-fold cross-validation. It was also validated on a golf study in which additional 22 participants were asked to complete 10 sessions of 10 putts each. Temporal sequences of the activated nodes for both studies followed the same pattern of changes, demonstrating the generalization capabilities of the approach. Most node transition changes were local, but important events typically caused significant changes in the physiological metrics, as evidenced by larger state changes. This was investigated by calculating a transition score as the sum of subsequent state transitions between the activated NN nodes. Correlation analysis demonstrated statistically significant correlations between the transition scores and subjects' performances in both studies. This paper explored the hypothesis that temporal sequences of physiological changes comprise the discriminative patterns for performance prediction. These physiological markers could be utilized in future training improvement systems (e.g., through neurofeedback), and applied across a variety of training environments.

EEG-derived estimators of present and future cognitive performance.

Previous electroencephalography (EEG)-based fatigue-related research primarily focused on the association between concurrent cognitive performance and time-locked physiology. The goal of this study was to investigate the capability of EEG to assess the impact of fatigue on both present and future cognitive performance during a 20-min sustained attention task, the 3-choice active vigilance task (3CVT), that requires subjects to discriminate one primary target from two secondary non-target geometric shapes. The current study demonstrated the ability of EEG to estimate not only present, but also future cognitive performance, utilizing a single, combined reaction time (RT), and accuracy performance metric. The correlations between observed and estimated performance, for both present and future performance, were strong (up to 0.89 and 0.79, respectively). The models were able to consistently estimate "unacceptable" performance throughout the entire 3CVT, i.e., excessively missed responses and/or slow RTs, while acceptable performance was recognized less accurately later in the task. The developed models were trained on a relatively large dataset (n = 50 subjects) to increase stability. Cross-validation results suggested the models were not over-fitted. This study indicates that EEG can be used to predict gross-performance degradations 5-15 min in advance.

Drowsiness/alertness algorithm development and validation using synchronized EEG and cognitive performance to individualize a generalized model.

A great deal of research over the last century has focused on drowsiness/alertness detection, as fatigue-related physical and cognitive impairments pose a serious risk to public health and safety. Available drowsiness/alertness detection solutions are unsatisfactory for a number of reasons: (1) lack of generalizability, (2) failure to address individual variability in generalized models, and/or (3) lack of a portable, un-tethered application. The current study aimed to address these issues, and determine if an individualized electroencephalography (EEG) based algorithm could be defined to track performance decrements associated with sleep loss, as this is the first step in developing a field deployable drowsiness/alertness detection system. The results indicated that an EEG-based algorithm, individualized using a series of brief "identification" tasks, was able to effectively track performance decrements associated with sleep deprivation. Future development will address the need for the algorithm to predict performance decrements due to sleep loss, and provide field applicability.

Weakly Supervised Recognition of Daily Life Activities with Wearable Sensors.

This paper considers scalable and unobtrusive activity recognition using on-body sensing for context awareness in wearable computing. Common methods for activity recognition rely on supervised learning requiring substantial amounts of labeled training data. Obtaining accurate and detailed annotations of activities is challenging, preventing the applicability of these approaches in real-world settings. This paper proposes new annotation strategies that substantially reduce the required amount of annotation. We explore two learning schemes for activity recognition that effectively leverage such sparsely labeled data together with more easily obtainable unlabeled data. Experimental results on two public data sets indicate that both approaches obtain results close to fully supervised techniques. The proposed methods are robust to the presence of erroneous labels occurring in real-world annotation data.