Please use this identifier to cite or link to this item: https://repository.isls.org/handle/1/9079
Title: Multimodal Data Fusion to Track Representational Flexibility of Adolescents With Autism Spectrum Disorder During Virtual Reality-Based Training
Authors: Moon, Jewoong
Ke, Fengfeng
Sokolikj, Zlatko
Chakraborty, Shayok
Keywords: Learning Sciences
Issue Date: 2022
Publisher: International Society of the Learning Sciences
Citation: Moon, J., Ke, F., Sokolikj, Z., & Chakraborty, S. (2022). Multimodal data fusion to track representational flexibility of adolescents with autism spectrum disorder during virtual reality-based training. In Chinn, C., Tan, E., Chan, C., & Kali, Y. (Eds.), Proceedings of the 16th International Conference of the Learning Sciences - ICLS 2022 (pp. 889-892). International Society of the Learning Sciences.
Abstract: We implemented multimodal data fusion to develop a prediction model tracking representational flexibility (RF) of adolescents with autism spectrum disorder (ASD) in virtual reality (VR)-based training. RF is a key competency related to individuals’ capability to select, coordinate, and create alternative representations inherent to STEM subjects. To promote ASD adolescents’ RF development, research has used VR-based 3D simulation design tasks. However, it remains a challenge to track ASD adolescents’ RF development during VR-based training. Using supervised machine learning, we implemented decision-level data fusion with RF evidence from multiple data sources. To train the model, we used a total of 178 audio- and screen-recorded VR training sessions of eight ASD adolescents. We compared model performance metrics of several candidate classifiers. Methodological details, findings, and implications of multimodal data fusion will be discussed. Keywords: Multimodal data fusion, virtual reality-based training, autism spectrum disorder, representational flexibility
Description: Short Paper
URI: https://dx.doi.org/10.22318/icls2022.889
https://repository.isls.org//handle/1/9079
Appears in Collections:ISLS Annual Meeting 2022

Files in This Item:
File SizeFormat 
ICLS2022_889-892.pdf335.39 kBAdobe PDFView/Open


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