Change search
ReferencesLink to record
Permanent link

Direct link
Identifying Radio Communication Inefficiency to Improve Air Combat Training Debriefings
Swedish Defence Research Agency.
KTH, School of Computer Science and Communication (CSC), Theoretical Computer Science, TCS.ORCID iD: 0000-0002-2677-9759
Swedish Defence Research Agency.
2016 (English)In: Proceedings of the 2016 Interservice/Industry Training, Simulation, and Education Conference (I/ITSEC 2016), Arlington, Virginia: National Training and Simulation Association (NTSA) , 2016, 1-12 p., 16287Conference paper (Refereed)
Abstract [en]

In flight simulator training, the retrospective debriefing activity is the essential tool for reflecting upon the conducted exercise. The debriefing typically serves to highlight carefully chosen exercise moments that can help the trainees to gain further insight. These moments are revisited from a number of different perspectives in order to make the overall picture of what actually happened during the exercise clear to the trainees. It is therefore of utmost importance to be able to identify the most instructive moments, and compile the data to be used for the debriefing. This is a delicate and critical task that needs to be undertaken swiftly so that the debriefing activity can be conducted directly after the flight exercise. This paper presents a methodology and prototype system for identifying moments of inefficient radio communication as a means to obtaining additional data for improving many versus many air combat flight simulator training debriefings. The work fits into an overall systems perspective where off the shelf speech recognition technology is used to obtain textual representations of the radio communication call sentences, which are then fed to a tailor-made machine learning classifier that is capable of detecting incorrect terminology/phrasing, unnecessary repetitions, unnecessary stalling of the radio communication channel, etc. With this overall systems perspective in mind, radio communication recordings originating from ordinary exercises being held at the Swedish Air Force Combat Simulation Centre have been used to construct classifiers capable of capturing communication patterns that are interesting to look at from an efficiency point of view. To validate its usefulness, the developed classifiers have been used to create visualizations that help identifying additional exercise moments in terms of inefficient radio communication that ought to be highlighted alongside the ordinary 3D visualization of the air flight, the cockpit displays, etc.

Place, publisher, year, edition, pages
Arlington, Virginia: National Training and Simulation Association (NTSA) , 2016. 1-12 p., 16287
National Category
Computer Science
Research subject
Computer Science
URN: urn:nbn:se:kth:diva-198559OAI: diva2:1057518
2016 Interservice/Industry Training, Simulation, and Education Conference (I/ITSEC 2016)

QC 20160110

Available from: 2016-12-19 Created: 2016-12-18 Last updated: 2017-01-10Bibliographically approved

Open Access in DiVA

fulltext(590 kB)6 downloads
File information
File name FULLTEXT01.pdfFile size 590 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Search in DiVA

By author/editor
Brynielsson, Joel
By organisation
Theoretical Computer Science, TCS
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 6 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 36 hits
ReferencesLink to record
Permanent link

Direct link