Use of wearable physiological sensors to predict cognitive workload in a visuospatial learning task.

BACKGROUND: Increased cognitive workload, sometimes known as mental strain or mental effort, has been associated with reduced performance. OBJECTIVE: The use of physiological monitoring was investigated to predict cognitive workload and performance. METHODS: Twenty-one participants completed a 10-minute seated rest, a visuospatial learning task modeled after crane operation, and the Stroop test, an assessment that measures cognitive interference. Heart rate, heart rate variability, electrodermal activity, skin temperature, and electromyographic activity were collected. RESULTS: It was found that participants' ability to learn the simulated crane operation task was inversely correlated with self-reported frustration. Significant changes were also found in physiological metrics in the simulation with respect to rest, including an increase in heart rate, electrodermal activity, and trapezius muscle activity; heart rate and muscle activity were also correlated with simulation performance. The relationship between physiological measures and self-reported workload was modeled and it was found that muscle activity and high frequency power, a measure of heart rate variability, were significantly associated with the workload reported. CONCLUSIONS: The findings support the use of physiological monitoring to inform real time decision making (e.g., identifying individuals at risk of injury) or training decisions (e.g., by identifying individuals that may benefit from additional training even when no errors are observed).

Gene name identification and normalization using a model organism database.

Biology has now become an information science, and researchers are increasingly dependent on expert-curated biological databases to organize the findings from the published literature. We report here on a series of experiments related to the application of natural language processing to aid in the curation process for FlyBase. We focused on listing the normalized form of genes and gene products discussed in an article. We broke this into two steps: gene mention tagging in text, followed by normalization of gene names. For gene mention tagging, we adopted a statistical approach. To provide training data, we were able to reverse engineer the gene lists from the associated articles and abstracts, to generate text labeled (imperfectly) with gene mentions. We then evaluated the quality of the noisy training data (precision of 78%, recall 88%) and the quality of the HMM tagger output trained on this noisy data (precision 78%, recall 71%). In order to generate normalized gene lists, we explored two approaches. First, we explored simple pattern matching based on synonym lists to obtain a high recall/low precision system (recall 95%, precision 2%). Using a series of filters, we were able to improve precision to 50% with a recall of 72% (balanced F-measure of 0.59). Our second approach combined the HMM gene mention tagger with various filters to remove ambiguous mentions; this approach achieved an F-measure of 0.72 (precision 88%, recall 61%). These experiments indicate that the lexical resources provided by FlyBase are complete enough to achieve high recall on the gene list task, and that normalization requires accurate disambiguation; different strategies for tagging and normalization trade off recall for precision.