{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T11:06:14Z","timestamp":1784718374886,"version":"3.55.0"},"reference-count":39,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Movement-based and physical activity programs are central tools in autism intervention, so recognizing the activities a child performs during therapy is valuable for objective progress tracking. Manual monitoring of these sessions is time-consuming and subjective, and raw videos raise privacy concerns because it shows identifiable children. We address autism therapeutic activity recognition from privacy-preserving 2D skeletons, and we focus on the practical difficulty of how several therapeutic activities differ only in subtle motion details. As a backbone, we adopt ProtoGCN, a graph convolutional network that represents each action as a combination of learnable motion prototypes. However, this contrastive backbone organizes all classes at once, so it does not enforce a margin between the few pairs that remain entangled after training. We therefore introduce a Refine\u2013Confusable (RC) module, a training-only regularizer that pushes apart the empirically most-confused class pairs using a hinge-margin loss over momentum-updated class centroids. The module changes neither the backbone nor the inference cost. On the MMASD dataset, restricted to the ten-class 2D-skeleton configuration, the RC module improves the base model across random, session-independent, and subject-independent evaluation. The gain is largest on the strictest subject-independent split and a clip-level analysis confirms that this improvement is statistically significant. Under the protocol-matched holdout, the method reaches 96.30% accuracy with 0.959 macro-F1, surpassing recent 2D-skeleton baselines while keeping a lightweight and privacy-preserving modality. The improvements are modest, as expected on a small clinical dataset, and t-SNE and prototype visualizations show that the learned representation is discriminative and interpretable.<\/jats:p>","DOI":"10.3390\/s26144638","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:48:28Z","timestamp":1784717308000},"page":"4638","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Skeleton-Based Activity Recognition for Children with Autism Using Graph Convolutional Networks"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3060-0432","authenticated-orcid":false,"given":"Bet\u00fcl","family":"Ay","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Faculty of Engineering, F\u0131rat University, 23119 Elaz\u0131\u011f, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet Ata","family":"\u00d6zt\u00fcrk","sequence":"additional","affiliation":[{"name":"Department of Physical Education and Sports, Middle East Technical University, 06800 Ankara, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Galip","family":"Ayd\u0131n","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Faculty of Engineering, F\u0131rat University, 23119 Elaz\u0131\u011f, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"ref_1","unstructured":"Sun, G., Wu, W., Guo, Z., Wang, Z., Khosravi, P., and Chen, C. (2026). Unlocking Multi-Site Clinical Data: A Federated Learning Approach to Privacy-First Child Autism Behavior Analysis. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, IEEE."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1021","DOI":"10.1109\/TNSRE.2026.3657614","article-title":"Modeling the Heterogeneous Movements of ASD via Fine-Grained Skeleton Representation Learning","volume":"34","author":"Wang","year":"2026","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1001\/jama.2022.23661","article-title":"Autism Spectrum Disorder: A Review","volume":"329","author":"Hirota","year":"2023","journal-title":"JAMA"},{"key":"ref_4","first-page":"e43226","article-title":"Early Diagnosis of Autism Spectrum Disorder: A Review and Analysis of the Risks and Benefits","volume":"15","author":"Okoye","year":"2023","journal-title":"Cureus"},{"key":"ref_5","first-page":"A56","article-title":"Impact of a Commercial Exergamer on Reducing Stereotypical Hand Movements of Children with Autism Spectrum Disorders","volume":"90","year":"2019","journal-title":"Res. Q. Exerc. Sport"},{"key":"ref_6","first-page":"1","article-title":"Improving Physical Fitness in Individuals with Autism Spectrum with Game Console Physical Activity Program","volume":"11","year":"2019","journal-title":"J. Phys. Educ. Sports Stud."},{"key":"ref_7","first-page":"259","article-title":"TEACCH Otizm Program\u0131 Unsurlar\u0131n\u0131n Beden E\u011fitimi ve Sporda Kullan\u0131m\u0131","volume":"19","year":"2012","journal-title":"Dicle \u00dcniv. Ziya G\u00f6kalp E\u011fit. Fak. Derg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2903","DOI":"10.1109\/ACCESS.2024.3523872","article-title":"Early Diagnosis of Autism: A Review of Video-Based Motion Analysis and Deep Learning Techniques","volume":"13","author":"Yang","year":"2025","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Kanwal, A., Hanzala, A., Javed, K., and Ahmed, T. (2024). ARAIS\u2014Activity Recognition of Autism Children During Intervention Sessions. Proceedings of the 7th International Conference on Machine Learning and Natural Language Processing (MLNLP), IEEE.","DOI":"10.1109\/MLNLP63328.2024.10800500"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, J., Chheang, V., Kullu, P., Brignac, E., Guo, Z., Barner, K.E., Bhat, A., and Barmaki, R.L. (2023). MMASD: A Multimodal Dataset for Autism Intervention Analysis. Proceedings of the 25th International Conference on Multimodal Interaction (ICMI), Paris, France, 9\u201313 October 2023, Association for Computing Machinery.","DOI":"10.1145\/3577190.3614117"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2831","DOI":"10.25130\/tjes.sp1.2025.31","article-title":"A Systematic Survey of Vision Transformer-Based Autism Detection Using Full-Body Movement Data from Augmented Reality Gameplay","volume":"32","author":"Qaddara","year":"2025","journal-title":"Tikrit J. Eng. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kassir, M., Mahfouz, S., Mourad-Chehade, F., and Samrouth, K. (2025). A BiLSTM with Attention Approach Using 2D Skeletons for Autism Activity Recognition. Proceedings of the 2025 International Conference on Computer and Applications (ICCA), IEEE.","DOI":"10.1109\/ICCA66035.2025.11431081"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, H., Liu, Y., Ren, M., Wang, H., Wang, Y., and Sun, Z. (2025). Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-Based Action Recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52734.2025.02723"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rajagopalan, S., Dhall, A., and Goecke, R. (2013). Self-Stimulatory Behaviours in the Wild for Autism Diagnosis. Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), IEEE.","DOI":"10.1109\/ICCVW.2013.103"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Billing, E., Belpaeme, T., Cai, H., Cao, H.-L., Ciocan, A., Costescu, C., David, D., Homewood, R., Hernandez Garcia, D., and G\u00f3mez Esteban, P. (2020). The DREAM Dataset: Supporting a Data-Driven Study of Autism Spectrum Disorder and Robot Enhanced Therapy. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0236939"},{"key":"ref_16","unstructured":"Ravva, P.U., Kiafar, B., Kullu, P., Li, J., Bhat, A., and Barmaki, R.L. (2024). MMASD+: A Novel Dataset for Privacy-Preserving Behavior Analysis of Children with Autism Spectrum Disorder. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e16763","DOI":"10.1016\/j.heliyon.2023.e16763","article-title":"Vision-Based Activity Recognition in Children with Autism-Related Behaviors","volume":"9","author":"Wei","year":"2023","journal-title":"Heliyon"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"100444","DOI":"10.1016\/j.smhl.2023.100444","article-title":"Language-Assisted Deep Learning for Autistic Behaviors Recognition","volume":"32","author":"Deng","year":"2024","journal-title":"Smart Health"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shin, J., Miah, A.S.M., Kakizaki, M., Hassan, N., and Tomioka, Y. (2025). Autism Spectrum Disorder Detection Using Skeleton-Based Body Movement Analysis via Dual-Stream Deep Learning. Electronics, 14.","DOI":"10.3390\/electronics14112231"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"39981","DOI":"10.1109\/JSEN.2024.3477751","article-title":"Physics Augmented Tuple Transformer for Autism Severity-Level Detection","volume":"24","author":"Ranasingha","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ay, B., and Karakose, M. (2013). Motion Classification Approach Based on Biomechanical Analysis of Human Activities. Proceedings of the 2013 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), IEEE.","DOI":"10.1109\/ICCIC.2013.6724198"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., and Lin, D. (2018). Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. Proceedings of the 32nd AAAI Conference on Artificial Intelligence, AAAI Press.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., and Hu, W. (2021). Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_25","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., and Krishnan, D. (2020). Supervised Contrastive Learning. Advances in Neural Information Processing Systems (NeurIPS), Curran Associates Inc."},{"key":"ref_26","first-page":"45","article-title":"TriNet-HAR: A Trimodal Framework for Human Activity Recognition","volume":"18","author":"Patil","year":"2026","journal-title":"Int. J. Inf. Technol. Secur."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Lu, M., Poston, K., Pfefferbaum, A., Sullivan, E.V., Fei-Fei, L., Pohl, K.M., Niebles, J.C., and Adeli, E. (2020). Vision-Based Estimation of MDS-UPDRS Gait Scores for Assessing Parkinson\u2019s Disease Motor Severity. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), Lima, Peru, 4\u20138 October 2020, Springer.","DOI":"10.1007\/978-3-030-59716-0_61"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Endo, M., Poston, K.L., Sullivan, E.V., Fei-Fei, L., Pohl, K.M., and Adeli, E. (2022). GaitForeMer: Self-Supervised Pre-Training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), Singapore, 18\u201322 September 2022, Springer.","DOI":"10.1007\/978-3-031-16452-1_13"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, H., Ho, E.S.L., Zhang, F.X., and Shum, H.P.H. (2022). Pose-Based Tremor Classification for Parkinson\u2019s Disease Diagnosis from Video. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI), Singapore, 18\u201322 September 2022, Springer.","DOI":"10.1007\/978-3-031-16440-8_47"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, H., Shum, H.P.H., and Ho, E.S.L. (2022). Cerebral Palsy Prediction with Frequency Attention Informed Graph Convolutional Networks. Proceedings of the 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Glasgow, UK, 11\u201315 July 2022, IEEE.","DOI":"10.1109\/EMBC48229.2022.9871230"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","first-page":"188","article-title":"Improving Early Detection of Learning Disabilities Using Graph Convolutional Networks (GCN) and Multi-Modal Data","volume":"6","author":"Dhanalakshmi","year":"2026","journal-title":"Int. J. Artif. Intell. Mach. Learn."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chi, H.-g., Ha, M.H., Chi, S., Lee, S.W., Huang, Q., and Ramani, K. (2022). InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18\u201324 June 2022, IEEE.","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1002\/aur.1955","article-title":"The Effect of Physical Activity Interventions on Youth with Autism Spectrum Disorder: A Meta-Analysis","volume":"11","author":"Healy","year":"2018","journal-title":"Autism Res."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e20193447","DOI":"10.1542\/peds.2019-3447","article-title":"Council on Children with Disabilities, Section on Developmental and Behavioral Pediatrics. Identification, Evaluation, and Management of Children with Autism Spectrum Disorder","volume":"145","author":"Hyman","year":"2020","journal-title":"Pediatrics"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"15069","DOI":"10.1038\/s41598-021-94378-z","article-title":"Using 2D Video-Based Pose Estimation for Automated Prediction of Autism Spectrum Disorders in Young Children","volume":"11","author":"Kojovic","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41746-022-00598-6","article-title":"Evaluation of an Artificial Intelligence-Based Medical Device for Diagnosis of Autism Spectrum Disorder","volume":"5","author":"Megerian","year":"2022","journal-title":"npj Digit. Med."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M.J., and Mei, T. (2021). Monocular, One-Stage, Regression of Multiple 3D People. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), IEEE.","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., and Dai, B. (2022). Revisiting Skeleton-Based Action Recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52688.2022.00298"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4638\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T10:56:30Z","timestamp":1784717790000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/14\/4638"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":39,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26144638"],"URL":"https:\/\/doi.org\/10.3390\/s26144638","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]}}}