Virtual Reality Based Adaptive Game for Enhancing Joint Attention in Children With Autism

Virtual Reality Based Adaptive Game for Enhancing Joint Attention in Children With Autism P. Valarmathi Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai Tamilnadu India https://orcid.org/0009-0000-8587-0774 A. Packialatha Department of Computer Science and Engineering Vels Institute of Science & Technology & Advanced Studies Chennai Tamilnadu India ABSTRACT

Atypical brain development is a characteristic of autism spectrum disorder (ASD), a neurodevelopmental disorder that frequently shows up as deficits in joint attention, a crucial social‐communication ability including gaze sharing and gaze following. Children with ASD frequently exhibit atypical gaze behaviours that hinder effective coordination of attention with others. Although recent studies have explored virtual reality (VR) to address these aspects, the existing systems rely primarily on performance‐based learning and offer limited adaptability to individual behavioural patterns. To overcome these limitations, this study proposes a novel virtual reality and adaptive game‐based system (VRAGS) designed to assess and enhance attention in children with ASD, thereby supporting improved learning capacity. The proposed framework begins with data acquisition through the 3D game environment. The collected data are preprocessed using an improved tanh normalization, which effectively suppresses noise while preserving informative variations for learning. Then, the feature extraction process takes place, in which the raw data features, statistical features and improved entropy features are derived. The improved entropy is computed using information gain, prioritizing features that maximally reduce uncertainty with respect to attention states, thereby enhancing discriminative power. Finally, the attention prediction is done via the hybrid classification (HC) model that integrates an Adam‐optimized deep convolutional neural network (AODCNN) and a bidirectional long short‐term memory (Bi‐LSTM) network. This architecture collectively captures hierarchical spatial patterns and temporal dependencies within the data. The integration of the improved tanh activation and Adam optimization in the AODCNN model ensures stable convergence and robust feature learning. Moreover, the experimental evaluation demonstrates that the proposed model significantly outperforms existing methods, achieving an accuracy of 0.933, an F‐measure of 0.925 and a negative predictive value (NPV) of 0.936. These findings demonstrate the potential of the suggested framework as a customized, adaptable tool for therapeutic intervention and support its efficacy in precisely predicting attention levels in children with ASD.
04 14 2026 04 2026 e70122 10.1002/jdn.70122 2 10.1002/crossmark_policy onlinelibrary.wiley.com true 2025-03-15 2026-02-28 2026-04-14 http://onlinelibrary.wiley.com/termsAndConditions#vor http://doi.wiley.com/10.1002/tdm_license_1.1 10.1002/jdn.70122 https://onlinelibrary.wiley.com/doi/10.1002/jdn.70122 https://onlinelibrary.wiley.com/doi/pdf/10.1002/jdn.70122 https://onlinelibrary.wiley.com/doi/pdf/10.1002/jdn.70122 https://onlinelibrary.wiley.com/doi/full-xml/10.1002/jdn.70122 10.3390/jcm9051260 Computational Intelligence and Neuroscience Alsaade F. W. 8709145 2022 1 2022 Classification and Detection of Autism Spectrum Disorder Based on Deep Learning Algorithms 10.1109/TNSRE.2021.3108351 10.1007/s41666-021-00101-y 10.1007/s10803-019-04253-0 10.1109/TNSRE.2013.2240700 10.1186/s11689-018-9246-9 10.1038/s41598-025-24243-w 10.1016/j.entcom.2021.100409 10.1016/j.ijporl.2019.109850 10.1109/ACCESS.2020.3012532 10.1177/1362361313500382 10.3390/children9020181 10.1007/s10209-021-00818-y 10.1111/j.1460-9568.2010.07102.x 10.1002/aur.1877 10.1016/j.tics.2008.11.006 10.1076/chin.6.3.235.3152 10.1016/j.ridd.2020.103678 10.1016/j.phycom.2020.101115 10.1016/j.patcog.2017.10.013 10.1016/j.smhl.2022.100371 10.1007/s10639-019-10050-0 10.1016/j.newideapsych.2011.11.001 10.3390/app10092996 10.1016/j.rasd.2020.101616 10.1109/TLT.2019.2912371 10.1177/0162643420945603 10.1016/j.rasd.2015.04.005 10.1016/j.jksuci.2022.11.001 10.1016/j.eclinm.2020.100588 10.1177/1941406414523981 International Journal of Computer Applications Latha L. 57 32 10 2011 Efficient Approach to Normalization of Multimodal Biometric Scores 10.1016/j.bbadis.2020.165767 10.1016/j.dscb.2022.100032 Maechler M. P.Rousseeuw C.Croux et al.2021. “Robustbase: Basic Robust Statistics.”http://robustbase.r‐forge.r‐project.org/. 10.1109/EMBC48229.2022.9871173 10.1016/j.image.2021.116184 10.1007/s10633-019-09685-8 10.1016/j.sbspro.2017.02.038 10.1016/j.mex.2025.103278 10.1109/TBME.2019.2919273 10.1016/j.nicl.2020.102181 10.1109/ACCESS.2020.3006004 10.1007/s10803-019-03913-5 Statistics Canada. n.d. “Median.”https://www150.statcan.gc.ca/n1/edu/power‐pouvoir/ch11/median‐mediane/5214872‐eng.htm. 10.1007/s42979-021-00776-5 Wikimedia Foundation. n.d.‐a. “Conditional Entropy.”https://en.wikipedia.org/wiki/Conditional_entropy#Definition. Wikimedia Foundation. n.d.‐b. “Standard Deviation.”https://en.wikipedia.org/wiki/Standard_deviation. Wikimedia Foundation. n.d.‐c. “Statistic.”https://en.wikipedia.org/wiki/Statistic. 10.1016/j.future.2020.03.022 10.1109/TNSRE.2020.2991675 10.1109/THMS.2018.2791562 10.1109/TNSRE.2016.2598727 10.1016/j.neucom.2019.04.099