Effectiveness of an expert system for astronaut assistance on a sleep experiment.

BACKGROUND Principal Investigator-in-a-Box ([PI]) is an expert system designed to train and assist astronauts with the performance of an experiment outside their field of expertise, particularly when contact with the Principal Investigators on the ground is limited or impossible. In the current case, [PI] was designed to assist with the calibration and troubleshooting procedures of the Neurolab Sleep and Respiration Experiment. [PI] displays physiological signals in real time during the pre-sleep instrumentation period, alerts the astronauts when a poor signal quality is detected, and displays steps to improve quality. METHODS Two studies are presented in this paper. In the first study 12 subjects monitored a set of prerecorded physiological signals and attempted to identify any signal artifacts appearing on the computer screen. Every subject performed the experiment twice, once with the assistance of [PI] and once without. The second part of this study focuses on the postflight analysis of the data gathered from the Neurolab Mission. After replaying the physiological signals on the ground, the frequency of correct [PI] alerts and false alarms (i.e., incorrect diagnoses by the expert system) was determined in order to assess the robustness and accuracy of the rules. CONCLUSIONS Results of the ground study indicated a beneficial effect of [PI] and training in reducing anomaly detection time and the number of undetected anomalies. For the in-flight performance, excluding the saturated signals, the expert system had an 84% detection accuracy, and the questionnaires filled out by the astronauts showed positive crew reactions to the expert system.