Augmented reality device operator cognitive strain determination and prediction

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Augmented reality (AR) solutions are in the process of entering a broad variety of industries to modify the capabilities of workers through (close to) real-time display of context-dependent information. An example for real-time training is the display of instructional materials, such as manuals, for operation and maintenance. Especially in industrial settings, this will allow for the enhancement of workforce capabilities in real-time. However, little is known with respect to the cognitive load that is incurred as a result of this process, which might hinder the realization of desired outcomes. In this paper, we evaluate visual tasks with respect to the cognitive load based on electroencephalography (EEG) employing existing and new metrics utilizing a publicly available data set. In turn, we provide an initial quantified and directly measured approach. We find that overall results are highly subjective, but already available commercial equipment can readily be employed to determine the cognitive load with R2 scores around 0.5 when utilizing k-nearest-neighbor (KNN) approaches directly. More intricate metrics at different measurement points could thus help detect and alleviate undesired stressors in industrial augmented reality settings.

Original languageEnglish
Pages (from-to)100-110
Number of pages11
JournalAIMS Electronics and Electrical Engineering
Issue number1
StatePublished - Dec 13 2017


  • Augmented reality
  • Cognitive load
  • Electroencephalography
  • K-nearest-neighbor
  • Multimedia systems


Dive into the research topics of 'Augmented reality device operator cognitive strain determination and prediction'. Together they form a unique fingerprint.

Cite this