Evaluation of a decision support system using Bayesian network modeling in an applied Multi-INT surveillance environment.

Sensemaking and decision-making are fundamental components of applied Intelligence, Surveillance, and Reconnaissance (ISR). Analysts acquire information from multiple sources over a period of hours, days, or even over the scale of months or years, that must be interpreted and integrated to predict future adversarial events. Sensemaking is essential for developing an appropriate mental model that will lead to accurate predictions sooner. Decision Support Systems (DSS) are one proposed solution to improve analyst decision-making outcomes by leveraging computers to conduct calculations that may be difficult for human operators and provide recommendations. In this study, we tested two simulated DSS that were informed by a Bayesian Network Model as a potential prediction-assistive tool. Participants completed a simulated multi-day, multi-source intelligence task and were asked to make predictions regarding five potential outcomes on each day. Participants in both DSS conditions were able to converge on the correct solution significantly faster than the control group, and between 36-44% more of the sample was able to reach the correct conclusion. Furthermore, we found that a DSS representing projected outcome probabilities as numerical, rather than using verbal ordinal labels, were better able to differentiate which outcomes were extremely unlikely than the control group or verbal-probability DSS.

Evaluation of Simulated Recognition Aids for Human Sensemaking in Applied Surveillance Scenarios.

OBJECTIVE: We determined whether the human capability for sensemaking, or for identifying essential elements of information (EEIs), could be enhanced by a simulated recognition aid that directed attention to people and vehicles in scenes or by a simulated recognition aid that directed attention to EEIs. BACKGROUND: For intelligence analysts, sensemaking is challenging because it frequently involves making inferences about uncertain data. One way to enhance sensemaking may involve collaboration from a machine recognition aid such as Project Maven, an established algorithm that directs analysts' attention to people and vehicles in scenes. We simulated the directed attention of Project Maven as well as a machine recognition aid that directed attention to EEIs. METHOD: We created full-motion videos of simulated compounds viewed by an overhead camera. Sensemaking was assessed by measuring participants' ability to predict events and identify signs. Participants' attention was directed by placing small globe symbols above either all people and vehicles, or all EEIs. Novices and intelligence analysts participated. RESULTS: Simulated recognition aids directing participants' attention to EEIs improved EEI identification but directing attention to people and vehicles (emulating Project Maven) did not. Participants' sensemaking was not enhanced by either type of simulated recognition aid. CONCLUSION: Guiding attention to features in a scene improves their identification whereas indiscriminate steering of attention to entities in the scene does not improve understanding of the holistic meaning of events, unless attention is drawn to relevant signs of those events. APPLICATION: Results contribute to our goal of determining which human-machine systems improve the sensemaking capability of intelligence analysts in the field.

Scanpath comparisons for complex visual search in a naturalistic environment.

Naturalistic surveillance tasks provide a rich source of eye-tracking data. It can be challenging to make meaningful comparisons using standard eye-tracking analysis techniques such as saccade frequency or blink rate in surveillance studies due to the temporal irregularity of events of interest. Naturalistic research environments present unique challenges, such as requiring specialized or expert analysts, small sample size, and long data collection sessions. These constraints demand rich data and sophisticated analyses, particularly in prescriptive naturalistic environments where problems must be thoroughly understood to implement effective and practical solutions. Using a small sample of expert surveillance analysts and an equal-sized sample of novices, we computed scanpath similarity on a variety of surveillance data using the ScanMatch Matlab tool. ScanMatch implements an algorithm initially developed for DNA protein sequence comparisons and provides a similarity score for two scanpaths based on their morphology and, optionally, duration in an area of interest. Both experts and novices showed equal dwell time on targets regardless of identification accuracy and both samples showed higher scanpath consistency across participants as a function of target type rather than individual subjects showing a particular scanpath preference. Our results show that scanpath analysis can be leveraged as a highly effective computer-based methodology to characterize surveillance identification errors and guide the implementation of solutions. Similarity scores can also provide insight into processes guiding visual search.