The Application of Machine Learning Tools to the Validation of an Air Traffic Control Domain Theory

Abstract

In this paper we describe a project (IMPRESS) in which machine learning (ML) tools were created and utilised for the validation of an Air Traffic Control domain theory written in first order logic. During the project, novel techniques were devised for the automated revision of general clause form theories using training examples. These techniques were combined in an algorithm which focused in on the parts of a theory which involve ordinal sorts, and applied geometrical revision operators to repair faulty component parts. While we illustrate the feasibility of applying ML to this area, we conclude that to be effective it must be focused to the application at hand, and used in mixed-initiative mode within a tools environment. The method is illustrated with experimental results obtained during the project.

Conducting Verification and Validation of Multi- Agent Systems

“…-IMPRESS [12] that shows how to integrate different techniques into a common formal base. it originates in solving several problems that affects the validation tests of specifications…”

“…Formal Represent information with Form formalisms, Non-ambiguous language that Are based on mathematic Principles, like Z model, B method. [10][11] -IMPRESS [12] that shows how to integrate different techniques into a common formal base. it originates in solving several problems that affects the validation tests of specifications…”

On automatic knowledge validation for Bayesian knowledge bases

“…Several recent approaches in knowledge validation, e.g. [17,40,20,30], concentrate on correcting the knowledge base, which is a considerably difficult task, e.g. theory revision [13,21].…”

Piecewise Linear Representation Segmentation in Noisy Domains With a Large Number of Measurements: The Air Traffic Control Domain

“…Artificial intelligence techniques have been applied for different purposes, such as establishing a formalization of the domain theory and its associated validation process. 19 Considering it from the segmentation point of view, opportunity traffic provides very interesting time series due to the difficulties which segmentation processes have to face in them. These difficulties, along with the characteristics of data measurements, may include reconsiderations of the quality functions used to measure the accuracy of a segmentation result (due to the high noise in the measurement values and the knowledge of the motion models which the aircraft may perform).…”