Unsupervised prototype reduction for data exploration and an application to air traffic management initiatives

• Published in: EURO Journal on Transportation and Logistics Vol. 8; no. 5; pp. 467 - 510
• Main Authors: Estes, Alexander, Lovell, David J., Ball, Michael O.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Elsevier B.V 01.12.2019; Springer Berlin Heidelberg; Elsevier Limited
• Subjects: 68U35; 90B80; Air traffic management; Airports; Business and Management; Decision support; Distance measurement; Exploration; Logistics; Management Science; Mathematics Subject Classification; Operations Research; Operations Research/Decision Theory; Optimization; Prototype generation; Prototypes; Reduction; Representative subset selection; Research Paper; Traffic management initiatives; Traffic planning; Unsupervised learning; Prototype generation; 68U35; Air traffic management; Representative subset selection; 90B80; Mathematics Subject Classification; Traffic management initiatives; Unsupervised learning; Decision support
• ISSN: 2192-4376; 2192-4384
• DOI: 10.1007/s13676-018-0132-0

We discuss a new approach to unsupervised learning and data exploration that involves summarizing a large data set using a small set of “representative” elements. These representatives may be presented to a user in order to provide intuition regarding the distribution of observations. Alternatively, these representatives can be used as cases for more detailed analysis. We call the problem of selecting the representatives the unsupervised prototype reduction problem. We discuss the KC-UPR method for this problem and compare it to other existing methods that may be applied to this problem. We propose a new type of distance measure that allows for more interpretable presentation of results from the KC-UPR method. We demonstrate how solutions from the unsupervised prototype reduction problem may be used to provide decision support for the planning of air traffic management initiatives, and we produce computational results that compare the effectiveness of several methods in this application. We also provide an example of how the KC-UPR method can be used for data exploration, using data from air traffic management initiatives at Newark Liberty International Airport.