Identification of Children with Autism Spectrum Disorder via Multi-Modal HyperdimensionalComputing with EEG and Eye-Tracking Data
Wang Sha1, Jiang Guoqian1,2*#, Han Junxia3, Xie Ping1,2, Li Xiaoli4
1(School of Electrical Engineering, Yanshan University, Qinhuangdao 066000, Hebei, China) 2(Key Laboratory of Intelligent Control and Neural Information Processing, Ministry of Education, Yanshan University, Qinhuangdao 066000, Hebei, China) 3(School of Psychology, Capital Normal University, Beijing 100048, China) 4(State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing 100875, China)
Abstract：Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by core deficits in social communication and the presence of restricted, repetitive behaviors. Its high heterogeneity poses substantial challenges for early identification and diagnosis. Traditional approaches often rely on single-modality data and are constrained by small sample sizes and poor generalization, limiting their utility in clinical decision support. To address these issues, this study proposed a multimodal fusion recognition framework based on hyperdimensional computing (MMHDC). The framework encoded electroencephalography (EEG) and eye-tracking data from 40 children with ASD and 50 typically developing children into hyperdimensional vectors, leveraging the complementary information between neurophysiological and behavioral signals through fusion modeling to enhance recognition accuracy and model robustness. Experimental results showed that the MMHDC model achieved an accuracy of 86.82% using only 5% of the training data, significantly outperforming mainstream methods such as support vector machines, naive Bayes,extreme gradient boosting, and multimodal stacked denoising autoencoders. Further ablation studies demonstrated that combining EEG and eye-tracking features effectively improved discriminative power, highlighting the advantages of a multimodal strategy. By integrating small-sample learning with hyperdimensional encoding theory, this work provided a lightweight and efficient new approach for the early identification of children with ASD, with strong potential for practical deployment and clinical application.
王莎, 江国乾, 韩俊霞, 谢平, 李小俚. 融合脑电与眼动数据的多模态超维计算模型用于孤独症谱系障碍儿童识别[J]. 中国生物医学工程学报, 2026, 45(1): 1-10.
Wang Sha, Jiang Guoqian, Han Junxia, Xie Ping, Li Xiaoli. Identification of Children with Autism Spectrum Disorder via Multi-Modal HyperdimensionalComputing with EEG and Eye-Tracking Data. Chinese Journal of Biomedical Engineering, 2026, 45(1): 1-10.
[1] Sarmiento Catalina, Lau Chloe. Diagnostic and statistical manual of mental disorders, 5th Ed.: DSM-5[M]. John Wiley & Sons Ltd, 2020. [2] Xu Guifeng, Strathearn Lane, Liu Buyun, et al. Prevalence of autism spectrum disorder among US children and adolescents, 2014-2016 [J]. JAMA, 2018, 319(1): 81-82. [3] Huang Zhian, Zhu Zexuan, Yau Chuen Heung, et al. Identifying autism spectrum disorder from resting-state fmri using deep belief network [J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(7): 2847-2861. [4] Nie Wei, Zhou Bingrui, Wang Zhiyong, et al. Computational interpersonal communication model for screening autistic toddlers: A case study of response-to-name [J]. IEEE Journal of Biomedical and Health Informatics, 2024, 28(6): 3683-3694. [5] Wang Zhiyong, Qin Haibo, Liu Jingjing, et al. Early screening of autism in toddlers via express-needs-with-pointing protocol [J]. IEEE Journal of Biomedical and Health Informatics, 2025, 29(4): 2911-2921. [6] Goin-Kochel RP, Mackintosh VH, Myers BJ. How many doctors does it take to make an autism spectrum diagnosis? [J]. Autism, 2006, 10(5): 439-451. [7] Wang Zhiyong, Liu Jingjing, Zhang Wanqi, et al. Diagnosis and intervention for children with autism spectrum disorder: a survey [J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(3): 819-832. [8] Hazlett H, Gu H, Munsell B, et al. Early brain development in infants at high risk for autism spectrum disorder [J]. Nature, 2017, 542(7641): 348-351. [9] Zhang Han, Li Rui, Wen Xiaotong, et al. Altered time-frequency feature in default mode network of autism based on improved hilbert-huang transform [J]. IEEE Journal of Biomedical and Health Informatics, 2021, 25(2): 485-492. [10] Kikuchi M, Yoshimura Y, Mutou K, et al. Magnetoencephalography in the study of children with autism spectrum disorder [J]. Psychiatry and clinical neurosciences, 2016, 70(2): 74-88. [11] Han Junxia, Zeng Ke, Kang Jiannan, et al. Development of brain network in children with autism from early childhood to late childhood [J]. Neuroscience, 2017, 367: 134-146. [12] Heunis TM, Aldrich CA, de Vries PJ. Recent advances in resting-state electroencephalography biomarkers for autism spectrum disorder-a review of methodological and clinical challenges [J]. Pediatric Neurology, 2016, 61: 28-37. [13] Takahashi T, Yoshimura Y, Hiraishi H, et al. Enhanced brain signal variability in children with autism spectrum disorder during early childhood [J]. Human Brain Mapping, 2016, 37(3): 1038-1050. [14] Li Jing, Kong Xiaoli, Sun Linlin, et al. Identification of autism spectrum disorder based on electroencephalography: a systematic review [J]. Computers in Biology and Medicine, 2024, 170: 108075. [15] 赵杰, 靳亚娟, 张志明, 等. 融合多特征脑电评估孤独症儿童 [J]. 中国生物医学工程学报, 2021, 40(5): 550-558. [16] Baygin M, Dogan S, Tuncer T, et al. Automated ASD detection using hybrid deep lightweight features extracted from EEG signals [J]. Computers in Biology and Medicine, 2021, 134: 104548. [17] Zhang Hanlin, Hu Chunchun, Wang Zhiyong, et al. Exploring eye-tracking based biomarkers to assess cognitive abilities in autistic children: a feasibility study [J]. IEEE Journal of Biomedical and Health Informatics, 2025, 29(6): 4401-4414. [18] Nakano T, Tanaka K, Endo Y, et al. Atypical gaze patterns in children and adults with autism spectrum disorders dissociated from developmental changes in gaze behaviour [J]. Proceedings of the Royal Society B: Biological Sciences, 2010, 277(1696): 2935-2943. [19] 林栋, 齐诗仪, 袁丁, 等. 基于近似熵对自闭症患儿眼电数据的 模块化处理与分析 [J]. 中国生物医学工程学报, 2024, 43(6): 759-763. [20] Liu Wenbo, Li Ming, Yi Li. Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework [J]. Autism Research, 2016, 9(8): 888-898. [21] Wan Guobin, Kong Xuejun, Sun Binbin, et al. Applying eye tracking to identify autism spectrum disorder in children [J]. Journal of Autism and Developmental Disorders, 2019, 49(1): 209-215. [22] Cociu BA, Das S, Billeci L, et al. Multimodal functional and structural brain connectivity analysis in autism: a preliminary integrated approach with EEG, fMRI, and DTI [J]. IEEE Transactions on Cognitive and Developmental Systems, 2018, 10(2): 213-226. [23] Vsquez-Correa JC, Arias-Vergara T, Orozco-Arroyave JR, et al. Multimodal assessment of Parkinson's disease: a deep learning approach [J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(4): 1618-1630. [24] Liu Siqi, Liu Sidong, Cai Weidong, et al. Multimodal neuroimaging feature learning for multiclass diagnosis of alzheimer's disease [J]. IEEE Transactions on Biomedical Engineering, 2015, 62(4): 1132-1140. [25] Tan Gansheng, Xu Kai, Liu Jinbiao, et al. A trend on autism spectrum disorder research: eye tracking-eeg correlative analytics [J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(3): 1232-1244. [26] Delorme A, Makeig S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis [J]. Journal of Neuroscience Methods, 2004, 134(1): 9-21. [27] Durka PJ, Klekowicz H, Blinowska KJ, et al. A simple system for detection of EEG artifacts in polysomnographic recordings [J]. IEEE Transactions on Biomedical Engineering, 2003, 50(4): 526-528. [28] 韩俊霞, 康健楠, 欧阳高翔, 等. 孤独症儿童脑电与眼动追踪研究 [J]. 科学通报, 2018, 63(15): 1464-1473. [29] Ana C, Owen C, Simon BC, et al. Atypical EEG complexity in autism spectrum conditions: a multiscale entropy analysis [J]. Clinical Neurophysiology, 2011, 122(12): 2375-2383. [30] Rahimi A, Benatti S, Kanerva P, et al. Hyperdimensional biosignal processing: A case study for EMG-based hand gesture recognition [C] //IEEE International Conference on Rebooting Computing. San Diego:IEEE, 2016: 1-8. [31] Chang CC, Lin CJ. LIBSVM: a library for support vector machines [J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3): 1-27. [32] Castillo G, Gama J. Adaptive Bayesian network classifiers [J]. Intelligent Data Analysis, 2009, 13(1): 39-59. [33] Chen Tianqi, Guestrin C, Machinery AC. XGBoost: A scalable tree boosting system [C] //Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). San Francisco:IEEE, 2016; 785-794. [34] Han Junxia, Jiang Guoqian, Ouyang Gaoxiang, et al. A multimodal approach for identifying autism spectrum disorders in children [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2003-2011. [35] Kanerva P. Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors [J]. Cognitive Computation, 2009, 1(2):139-159. [36] Rahimi A, Kanerva P, Benini L, et al. Efficient biosignal processing using hyperdimensional computing: network templates for combined learning and classification of exg signals [J]. Proceedings of the IEEE, 2019, 107(1): 123-143. [37] Chang E, Rahimi A, Benini L, et al. Hyperdimensional computing-based multimodality emotion recognition with physiological signals [C] //Proceedings of the 1st IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS). Hsinchu: IEEE, 2019: 137-141. [38] Du Yipeng, Ren Yuan, Wong N, et al. Hyperdimensional computing with multiscale local binary patterns for scalp eeg-based epileptic seizure detection [J]. IEEE Internet of Things Journal, 2024, 11(15):26046-26061.
