Body Posture Visualizer to Support Multimodal Learning Analytics

Roberto Munoz, Thiago Schumacher Barcelos, Rodolfo Villarroel, Rodolfo Guinez, Erick Merino

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Learning analytics consists of gathering and analyzing data from students in order to understand complex aspects of the learning process and promote its improvement. Currently, to the best of our knowledge, there is a lack of tools aimed at displaying multimodal data in an integrated way for general purpose analysis. In this paper, we present a free software tool based on the Microsoft Kinect sensor for automatic capture, identification, and visualization of ten body postures for posterior analysis. It is also possible to incorporate the identification of new postures if necessary. Learning and recognition is based on the AdaBoost algorithm. Posture recognition reached accuracy rates as high as 80% for 8 of the 10 identified postures. Concerning the software usability, a heuristic evaluation with three specialists was performed, as well as a usability test with five volunteer students. Results indicated that the software interface, based on the metaphor of a video editor, may allow its effective use by end users, though some adjustments are still necessary, such as the terminology used in some commands and the help system.

Original languageEnglish
Article number8795111
Pages (from-to)2706-2715
Number of pages10
JournalIEEE Latin America Transactions
Issue number11
StatePublished - Nov 2018


  • Kinect
  • Multimodal Learning Analytics
  • Visualizer


Dive into the research topics of 'Body Posture Visualizer to Support Multimodal Learning Analytics'. Together they form a unique fingerprint.

Cite this