A document presents equations for scoring rules in a diagnostic and/or prognostic artificial-intelligence software system of the rule-based inference- engine type. The equations define a set of metrics that characterize the evaluation of a rule when data required for the antecedence clause(s) of the rule are missing. The metrics include a primary measure denoted the rule completeness metric (RCM) plus a number of subsidiary measures that contribute to the RCM. The RCM is derived from an analysis of a rule with respect to its truth and a measure of the completeness of its input data. The derivation is such that the truth value of an antecedent is independent of the measure of its completeness. The RCM can be used to compare the degree of completeness of two or more rules with respect to a given set of data. Hence, the RCM can be used as a guide to choosing among rules during the rule-selection phase of operation of the artificial-intelligence system.
This work was done by Mark James of Caltech for NASA's Jet Propulsion Laboratory.
The software used in this innovation is available for commercial licensing. Please contact Karina Edmonds of the California Institute of Technology at (818) 393-2827. Refer to NPO-42717.
This Brief includes a Technical Support Package (TSP).
Equations for Scoring Rules When Data Are Missing
(reference NPO-42717) is currently available for download from the TSP library.
Don't have an account?
Overview
The document titled "Numeric Techniques for Scoring Symbolic Rules in the Presence of Missing Data" (NASA Tech Brief NPO-42717) outlines a mathematical framework designed to evaluate rules in scenarios where data may be incomplete. This framework is particularly relevant for prognostic reasoning technologies, which are essential for extended-duration space missions that operate far from Earth.
The core concept introduced is the Rule Completeness Metric (RCM), a scoring system that assesses how complete the antecedents of a rule are concerning the available data. The RCM is derived from an analysis of the rule's truth and its completeness, allowing for a separation between the truth-value of the antecedent and its completeness measure. This independence enables the RCM to serve as a guiding heuristic during the rule selection process, facilitating better decision-making even when data is missing.
The document emphasizes the significance of prognostic reasoning in enhancing safety, affordability, and sustainability for future exploration systems. By providing timely and accurate health status information, these technologies can improve safety by extending the response window for critical decisions made by crew members and ground operators. Additionally, prognostic reasoning can lead to cost savings by predicting failures in advance, thereby reducing unplanned maintenance and streamlining troubleshooting processes.
The document also discusses the development of a hybrid-reasoning engine that incorporates two key features: prognostic forecasting and reasoning on incipient faults, as well as improved operation in degraded systems. This engine aims to anticipate future events logically, which is crucial for effective mission planning and execution.
Overall, the document serves as a technical support package that not only details the mathematical techniques for scoring rules in the presence of missing data but also highlights the broader implications of these technologies for aerospace applications. It underscores NASA's commitment to advancing research and technology that can be applied across various domains, ensuring that future exploration systems are safe, cost-effective, and sustainable. The information is part of NASA's Commercial Technology Program, aimed at disseminating aerospace-related developments with potential wider applications.
