Developing gesture recognition capabilities for interactive learning systems: Personalizing the learning experience with advanced algorithms

Michael Junokas, Nicholas Linares, Robb Lindgren

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We describe a novel approach to developing a gesture recognition system that accommodates the adaptability and low training requirements of interactive educational simulation environments. Hidden Markov Models allow us to make robust representations of learners' movement in real time, and adapt to their personal style of enacting simulation operations. The context is a project in which gesture-controlled simulations are being built to facilitate the use of crosscutting concepts (e.g., scale and magnitude) across science topics.

Original languageEnglish (US)
Title of host publication12th International Conference of the Learning Sciences, ICLS 2016
Subtitle of host publicationTransforming Learning, Empowering Learners, Proceedings
EditorsChee-Kit Looi, Joseph L. Polman, Peter Reimann, Ulrike Cress
PublisherInternational Society of the Learning Sciences (ISLS)
Pages1271-1272
Number of pages2
Volume2
ISBN (Electronic)9780990355083
StatePublished - 2016
Event12th International Conference of the Learning Sciences: Transforming Learning, Empowering Learners, ICLS 2016 - Singapore, Singapore
Duration: Jun 20 2016Jun 24 2016

Other

Other12th International Conference of the Learning Sciences: Transforming Learning, Empowering Learners, ICLS 2016
Country/TerritorySingapore
CitySingapore
Period6/20/166/24/16

Keywords

  • Embodied learning
  • Hierarchal hidden markov models
  • Learning gestures
  • Motion sensors
  • Quantitative reasoning
  • Scale
  • Simulation

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Education

Fingerprint

Dive into the research topics of 'Developing gesture recognition capabilities for interactive learning systems: Personalizing the learning experience with advanced algorithms'. Together they form a unique fingerprint.

Cite this