Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/10721
Full metadata record
DC FieldValueLanguage
dc.contributor.authorSokolikj, Zlatko
dc.contributor.authorKe, Fengfeng
dc.contributor.authorChakraborty, Shayok
dc.contributor.authorMoon, Jewoong
dc.date.accessioned2024-06-10T05:49:23Z-
dc.date.available2024-06-10T01:44:11Z
dc.date.available2024-06-10T05:49:23Z-
dc.date.issued2024
dc.identifier.citationSokolikj, Z., Ke, F., Chakraborty, S., & Moon, J. (2024). A Comparison of Deep Learning and Supervised Machine Learning Methods in RF tracking for Neurodivergent Learners. In Lindgren, R., Asino, T. I., Kyza, E. A., Looi, C. K., Keifert, D. T., & Suárez, E. (Eds.), Proceedings of the 18th International Conference of the Learning Sciences - ICLS 2024 (pp. 1446-1449). International Society of the Learning Sciences.en
dc.identifier.urihttps://doi.org/10.22318/icls2024.784207
dc.identifier.urihttps://repository.isls.org//handle/1/10721-
dc.descriptionShort Paperen
dc.description.abstractRepresentational Flexibility (RF) is an individual's cognitive ability to select, coordinate and create alternative representations during information processing. Students with autism spectrum disorder (ASD) typically lack representational flexibility and therefore are underrepresented in the fields of STEM. Research has used virtual reality-based (VR) 3D simulations to promote RF development of ASD adolescent learners. However, to promote RF development, the need to be able to track RF throughout the intervention is critical. In this paper we report RF tracking in a VR-based learning program intended for RF development. We studied the performance of state-of-the-art deep neural network models to track RF subsets throughout the intervention. We trained these models, along with multiple classical machine-learning classifiers, using multimodal data collected from 209 sessions with ten ASD adolescents. Our empirical analysis shows promising evidence that deep learning can be used to track the cognitive-affective states of learners with ASD in real time.en
dc.publisherInternational Society of the Learning Sciences
dc.relation.ispartofurn:ISBN:979-8-9906980-0-0
dc.relation.ispartofProceedings of the 18th International Conference of the Learning Sciences - ICLS 2024, pp. 1446-1449
dc.subjectLearning Sciencesen
dc.titleA Comparison of Deep Learning and Supervised Machine Learning Methods in RF tracking for Neurodivergent Learnersen
dc.typeconferencePaper
dc.identifier.doi10.22318/icls2024.784207
Appears in Collections:ISLS Annual Meeting 2024

Files in This Item:
File SizeFormat 
ICLS2024_1446-1449.pdf446.46 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.