Detection of attention state in children with autism spectrum disorder based on neural network classification of electroencephalograms
DOI:
https://doi.org/10.21638/spbu10.2025.107Abstract
Autism spectrum disorder (ASD) is a neurological condition characterized by impairments in social interaction. This diagnosis carries economic and social implications due to its high prevalence and associated morbidity. Data from electroencephalogram (EEG) sensors is numerical and serves as the input for machine learning-based predictions. The input data in this research includes features extracted from EEG signals, such as theta/beta ratio, theta/alpha ratio, and other relative power metrics, which are closely linked to cognitive control and attentional dynamics. These data are organized into two balanced classes: “Attention” and “No Attention,” comprising a total of 33 936 samples. This paper proposes 12 weighted and weighted-average ensemble models to enhance the accuracy of predicting attentional cues in individuals with ASD. For ensembling three multilayer perceptron architectures were developed and trained using various optimizers. The accuracy of the employed ensemble model of three multilayer perceptrons reached 95.90 %. The findings of this research can contribute to the advancement of novel diagnostic approaches and educational initiatives and serve as a foundation for future research utilizing machine learning techniques and the creation of innovative technologies for attention monitoring and training.
Keywords:
electroencephalogram, autism spectrum disorder, neural network, EEG processing, ensembling, multilayer linear perceptron
Downloads
References
References
Hodges H., Fealko C., Soares N. Autism spectrum disorder: Definition, epidemiology, causes, and clinical evaluation. Translational Pediatrics, 2020, vol. 9, iss. 1, pp. 55–65.
Al-Mazidi S. The physiology of cognition in Autism Spectrum Disorder: Current and future challenges. Cureus, 2023, vol. 15, iss. 10, art. no. e46581.
Kasari C., Brady N., Lord C., Tager-Flusberg H. Assessing the minimally verbal school-aged child with Autism Spectrum Disorder. Autism Research, 2013, vol. 6, iss. 6, pp. 479–493.
Kangarani-Farahani M., Malik M. A., Zwicker J. G. Motor impairments in children with Autism Spectrum Disorder: A systematic review and meta-analysis. Journal of Autism and Developmental Disorders, 2024, vol. 54, iss. 5, pp. 1977–1997.
Morie K. P., Jackson S., Zhai Z. W., Potenza M. N., Dritschel B. Mood disorders in high-functioning autism: The importance of alexithymia and emotional regulation. Journal of Autism and Developmental Disorders, 2019, vol. 49, iss. 7, pp. 2935–2945.
Amaral C., Mouga S., Sim oes M., Pereira H. C., Bernardino I., Quental H., Playle R., McNamara R., Oliveira G., Castelo-Branco M. A feasibility clinical trial to improve social attention in Autistic Spectrum Disorder (ASD) using a brain computer interface. Frontiers in Neuroscience, 2018, vol. 12, p. 477. https://doi.org/10.3389/fnins.2018.00477
Falck-Ytter T., Kleberg J. L., Portugal A. M., Thorup E. Social attention: Developmental foundations and relevance for Autism Spectrum Disorder. Biological Psychiatry, 2023, vol. 94, iss. 1, pp. 8–17.
Johnson M. H., Jones E. J. H., Gliga T. Brain adaptation and alternative developmental trajectories. Development and Psychopathology, 2015, vol. 27, iss. 2, pp. 425–442.
Gliga T., Jones E. J., Bedford R., Charman T., Johnson M. H. From early markers to neuro-developmental mechanisms of autism. Developmental Review, 2014, vol. 34, iss. 3, pp. 189–207.
Obukhov A. D., Korobova I. L., Nazarova A. O., Zaytseva D. V. Primeneniye mashinnogo obucheniya pri analise EEG dlya vyavleniya phobicheskoy reaktsii v virtualnoy real'nosty [Application of machine learning in EEG analysis to identify phobic reactions in virtual reality]. Informatcianno-upravlyauschie sistemy [Information and Control Systems], 2023, vol. 4, pp. 56–70. (In Russian)
Dorovskih I. V., Senko O. V., Chuchupal V. Ya., Dokukin A. A., Kuznetsova A. V. Issledovaniye vozmozhnosti diagnostiki dementsii po signalam EEG s pomoshch'yu metodov mashinnogo obucheniya [Research of the possibility of diagnosing dementia using EEG signals using machine learning methods]. Matematicheskaya biologiya i bioinformatika [The Mathematical Biology and Bioinformatics], 2019, vol. 14, iss. 2, pp. 543–553. (In Russian)
Cohen I. L., Schutte C., Hewitson L. PDDBI and ADOS-2 autism severity scores are correlated but yield discrepant levels of severity across assessment sites. Research in Autism Spectrum Disorders, 2023, vol. 107, art. no. 102206.
Bosl W. J., Tager-Flusberg H., Nelson C. A. EEG analytics for early detection of Autism Spectrum Disorder: A data-driven approach. Science Report, 2018, vol. 8, art. no. 6828. https://doi.org/10.1038/s41598-018-24318-x
Torres J. M. M., Medina-DeVilliers S., Clarkson T., Lerner M. D., Riccardi G. Evaluation of interpretability for deep learning algorithms in EEG emotion recognition: A case study in autism. Artificial Intelligence in Medicine, 2023, vol. 143, art. no. 102545.
Tregubov V. P., Egorova N. K. Postroyeniye mekhanicheskoy modeli levogo zheludochka serdtsa cheloveka v protsesse yego sokrashcheniya [Construction of a mechanical model of the left ventricle of the human heart during its contraction]. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes, 2022, vol. 18, iss. 3, pp. 402–409. https:// doi.org/10.21638/11701/spbu10.2022.309 (In Russian)
Pantic J. P., Valjarevic S., Cumic J., Pantic I. AI-enhanced EEG signal interpretation: A novel approach using texture analysis with random forests. Medical Hypotheses, 2024, vol. 189, art. no. 111405.
Pyrzowski J., Kałas M., Mazurkiewicz-Beldzińska M., Siemiński M. EEG biomarkers for the prediction of post-traumatic epilepsy: A systematic review of an emerging field. Seizure: European Journal of Epilepsy, 2024, vol. 119, pp. 71–77.
Sarmukadam K., Bitsika V., Sharpley C. F., McMillan M. M., Agnew L. L. Comparing different EEG connectivity methods in young males with ASD. Behavioural Brain Research, 2020, vol. 383, art. no. 112482.
Esqueda-Elizondo J. J., Juárez-Ramírez R., López-Bonilla O. R., García-Guerrero E. E., Galindo-Aldana G. M, Jiménez-Beristáin L., Serrano-Trujillo A., Tlelo-Cuautle E., Inzunza-González E. Attention measurement of an Autism Spectrum Disorder user using EEG signals: A case study. Mathematical and Computational Applications, 2022, vol. 27, iss. 2, p. 21.
Patel M., Bhatt H., Munshi M., Pandya S., Jain S., Thakkar P., Yoon S. CNN-FEBAC: A framework for attention measurement of autistic individuals. Biomedical Signal Processing and Control, 2024, vol. 88, iss. C, art. no. 105018.
Nguyen V. H., Nguyen N. T. Combining dynamic and static host intrusion detection features using variational long short-term memory recurrent autoencoder. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes, 2024, vol. 20, iss. 1, pp. 34–51. https://doi.org/10.21638/11701/spbu10.2024.104
Xu Y., Yu Z., Li Y., Liu Y., Li Y., Wang Y. Autism spectrum disorder diagnosis with EEG signals using time series maps of brain functional connectivity and a combined CNN — LSTM model. Computer Methods and Programs in Biomedicine, 2024, vol. 250, art. no. 108196.
Aglinskas A., Hartshorne J. K., Anzellotti S. Contrastive machine learning reveals the structure of neuroanatomical variation within autism. Science, 2022, vol. 376, pp. 1070–1074.
Kabir M. S., Kurkin S., Portnova G., Martynova O., Wang Z., Hramov A. Contrastive machine learning reveals in EEG resting-state network salient features specific to Autism Spectrum Disorder. Chaos, Solitons & Fractals, 2024, vol. 185, art. no. 115123.
Fouad I. A. A robust and reliable online P300-based BCI system using Emotiv EPOC+headset. Journal of Medical Engineering & Technology, 2021, vol. 45, iss. 2, pp. 94–114.
Fahimi F., Guan C., Goh W. B., Ang K. K., Lim C. G., Lee T. S. Personalized features for attention detection in children with Attention Deficit Hyperactivity Disorder. 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2017, pp. 414–417.
Wang T-S., Wang S-S., Wang C-L., Wong S-B. Theta/beta ratio in EEG correlated with attentional capacity assessed by Conners Continuous Performance Test in children with ADHD. Frontiers in Psychiatry, 2024, vol. 14, art. no. 1305397.
Angelidis A., Hagenaars M., van Son D., van der Does W., Putman P. Do not look away! Spontaneous frontal EEG theta/beta ratio as a marker for cognitive control over attention to mild and high threat. Biological Psychology, 2018, vol. 135, pp. 8–17.
Wang Y., Sokhadze E. M., El-Baz A. S., Li X., Sears L., Casanova M. F., Tasman A. Relative power of specific EEG bands and their ratios during neurofeedback training in children with Autism Spectrum Disorder. Frontiers in Human Neuroscience, 2016, vol. 9, iss. 723, art. no. 723. https://doi.org/10.3389/fnhum.2015.00723
Chen J., Xiao Y., Xu B., Zhang D. The developmental trajectory of task-related frontal EEG theta/beta ratio in childhood. Developmental Cognitive Neuroscience, 2023, vol. 60, art. no. 101233.
Sabry F. Feedforward neural networks: Fundamentals and applications for the architecture of thinking machines and neural webs. Artificial Intelligence. Vol. 3. Belmont, One Billion Knowledgeable Publ., 2023, 130 p.
Naitzat G., Zhitnikov A., Lim L.-H. Topology of deep neural networks. Journal of Machine Learning Research, 2020, vol. 21, pp. 1–40.
Kingma D. P., Ba J. L. Adam: A method for stochastic optimization. 3th International Conference on Learning Representations Proceedings, 2014, pp. 1–15.
Zaheer M., Reddi S. J., Sachan D., Kale S., Research G., Kumar S. Adaptive methods for nonconvex optimization. Advances in Neural Information Processing Systems, 2018, vol. 31, pp. 1–11.
Dubey S. R., Chakraborty S., Roy S. K., Mukherjee S., Singh S. K., Chaudhuri B. B. DiffGrad: An optimization method for convolutional neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2020, vol. 31, iss. 11, pp. 4500–4511.
Khng K. H., Mane R. Beyond BCI — Validating a wireless, consumer-grade EEG headset against a medical-grade system for evaluating EEG effects of a test anxiety intervention in school. Advanced Engineering Informatics, 2020, vol. 45, art. no. 101106.
Sussner P., Campiotti I. Hyperconnectivity of social brain networks in autism during action-intention judgment. Extreme Learning Machine for a New Hybrid Morphological/Linear Perceptron, 2020, vol. 123, pp. 288–298.
Curteanu S., Cartwright H. Neural networks applied in chemistry. I. Determination of the optimal topology of multilayer perceptron neural networks. Journal of Chemometrics, 2011, vol. 25, iss. 10, pp. 527–549.
Chicco D., Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 2020, vol. 21, iss. 6, pp. 1–13.
Downloads
Published
How to Cite
Issue
Section
License
Articles of "Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes" are open access distributed under the terms of the License Agreement with Saint Petersburg State University, which permits to the authors unrestricted distribution and self-archiving free of charge.
