Cross-subject workload classification using pupil-related measures

Tobias Appel, Christian Scharinger, Peter Gerjets, Enkelejda Kasneci

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

41 Scopus citations


Real-time evaluation of a person’s cognitive load can be desirable in many situations. It can be employed to automatically assess or adjust the difficulty of a task, as a safety measure, or in psychological research. Eye-related measures, such as the pupil diameter or blink rate, provide a non-intrusive way to assess the cognitive load of a subject and have therefore been used in a variety of applications. Usually, workload classifiers trained on these measures are highly subject-dependent and transfer poorly to other subjects. We present a novel method to generalize from a set of trained classifiers to new and unknown subjects. We use normalized features and a similarity function to match a new subject with similar subjects, for which classifiers have been previously trained. These classifiers are then used in a weighted voting system to detect workload for an unknown subject. For real-time workload classification, our methods performs at 70.4% accuracy. Higher accuracy of 76.8% can be achieved in an offline classification setting.

Original languageEnglish
Title of host publicationProceedings - ETRA 2018
Subtitle of host publication2018 ACM Symposium on Eye Tracking Research and Applications
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450357067
StatePublished - 14 Jun 2018
Externally publishedYes
Event10th ACM Symposium on Eye Tracking Research and Applications, ETRA 2018 - Warsaw, Poland
Duration: 14 Jun 201817 Jun 2018

Publication series

NameEye Tracking Research and Applications Symposium (ETRA)


Conference10th ACM Symposium on Eye Tracking Research and Applications, ETRA 2018


  • Blinks
  • Classification
  • Cross-subject
  • Eye tracking
  • Pupillometry
  • Workload


Dive into the research topics of 'Cross-subject workload classification using pupil-related measures'. Together they form a unique fingerprint.

Cite this