Information Filtering using Bayesian Networks: Effective User Interfaces for Aviation Weather Data

摘要

Weather is a complex, dynamic process with tremendous impact on aviation. While pilots often have access to large amounts of aviation weather data, they find it difficult and time-consuming to identify weather hazards, due to the sheer amount and cryptic formatting of the data. To address this challenge, we have developed information filtering concepts based on a unified Bayesian network model, integrating text and graphical weather data in the context of specific mission, equipment and personal profiles. Based on these concepts, we have implemented three applications, all of which were to existing technology. Using one of the applications, the AWARE Preflight system, pilots found significantly more hazards in about half the time compared to using the current technology.