Deep Learning-Based Autism Detection Using Facial Images and EfficientNet-B3

Muhaimin Hasanudin; Afiyati  Afiyati; Rahmat  Budiarto; Abdi  Wahab; Bambang  Jokonowo; Indrianto Indrianto; Efy  Yosrita; Nurul Afif  Hanifah

doi:10.52436/1.jutif.2026.7.1.4574

Authors

Muhaimin Hasanudin Faculty of Computer Science, Universitas Mercu Buana, Indonesia
Afiyati Afiyati Faculty of Computer Science, Universitas Mercu Buana, Indonesia
Rahmat Budiarto Faculty of Computer Science, Universitas Mercu Buana, Indonesia
Abdi Wahab Faculty of Computer Science, Universitas Mercu Buana, Indonesia
Bambang Jokonowo Faculty of Computer Science, Universitas Mercu Buana, Indonesia
Indrianto Faculty Of Energy Telematics, Institut Teknologi PLN, Indonesia
Efy Yosrita Faculty Of Energy Telematics, Institut Teknologi PLN, Indonesia
Nurul Afif Hanifah Faculty of Computer Science, Universitas Mercu Buana, Indonesia

DOI:

https://doi.org/10.52436/1.jutif.2026.7.1.4574

Keywords:

Autism, deep learning, Disability, Early detection, EfficientNet

Abstract

This study presents a novel deep learning approach for early detection of Autism Spectrum Disorder (ASD) using facial image analysis. Leveraging the EfficientNet-B3 model, the research addresses limitations in traditional diagnostic methods by autonomously extracting discriminative facial features associated with ASD. A balanced dataset of 2,940 facial images (1,470 autistic and 1,470 non-autistic children) from Kaggle was pre-processed to 200x200 pixels and evaluated under three dataset-splitting scenarios (80:10:10, 70:15:15, and 60:20:20) to assess generalisability. The model, trained with the Adam optimiser over 10 epochs, achieved optimal performance in the 80:10:10 scenario, with 84.67% precision, 84.35% recall, and 84.32% F1 score. Results demonstrate high confidence (>90% probability) in distinguishing autistic from non-autistic individuals on unseen data. The study underscores the potential of integrating deep learning into clinical decision-support systems for ASD detection, offering a robust, scalable, and efficient solution to improve diagnostic accuracy and reduce reliance on manual methods.

Downloads

Download data is not yet available.

References

P. Y. Pan, S. Bölte, P. Kaur, S. Jamil, and U. Jonsson, “Neurological disorders in autism: A systematic review and meta-analysis,” Autism, vol. 25, no. 3, pp. 812–830, 2021, doi: 10.1177/1362361320951370.

A. J. Harrison, M. M. Slane, L. Hoang, and J. M. Campbell, “An international review of autism knowledge assessment measures,” Autism, vol. 21, no. 3, pp. 262–275, 2017, doi: 10.1177/1362361316638786.

S. Fletcher-Watson et al., “Publishing standards for promoting excellence in autism research,” Autism, vol. 25, no. 6, pp. 1501–1504, 2021, doi: 10.1177/13623613211019830.

M. Hasanudin, A. H. Arribathi, Indrianto, K. Yuliana, and D. P. Kristiadi, “Increasing Independence of Cerebral Palsy Children using Virtual Reality based on Mlearning,” J. Phys. Conf. Ser., vol. 1764, no. 1, pp. 2–7, 2021, doi: 10.1088/1742-6596/1764/1/012119.

H. Kim, D. Baker, S. Kim, C. Liu, and K. Cook, “The impact of educational and medical systems on autistic children from multilingual American homes: A systematic review,” Autism, 2024, doi: 10.1177/13623613241242839.

P. Ritzmann de Lima, L. Leonardi Diman, L. Cristina Marques Moura, B. Jahn Henning, and M. Antônio Schueda, “Autism: Clinical impacts and late diagnosis in women - Literature review,” Int. Seven J. Heal. Res., vol. 3, no. 2, pp. 464–474, 2024, doi: 10.56238/isevjhv3n2-009.

M. Marcilla-Jorda, C. Grande, V. Coelho, C. Rubio-Belmonte, and M. Moro-Ipola, “Sensory Profile-2 in Autism Spectrum Disorder: An Analysis within the International Classification of Functioning, Disability and Health Framework,” J. Autism Dev. Disord., 2024, doi: 10.1007/s10803-024-06337-y.

M. B. Halvorsen, A. N. Kildahl, S. Kaiser, B. Axelsdottir, M. G. Aman, and S. B. Helverschou, “Applicability and Psychometric Properties of General Mental Health Assessment Tools in Autistic People: A Systematic Review,” J. Autism Dev. Disord., no. 0123456789, 2024, doi: 10.1007/s10803-024-06324-3.

A. Kumar and U. C. Jaiswal, “A Survey of Machine Learning Techniques Related to Understanding Autism Spectrum Disorder,” 2024 2nd Int. Conf. Disruptive Technol. ICDT 2024, pp. 717–725, 2024, doi: 10.1109/ICDT61202.2024.10489242.

H. Phillips et al., “Adapting and validating the Autism Diagnostic Observation Schedule Version 2 for use with deaf children and young people,” J. Autism Dev. Disord., vol. 52, no. 2, pp. 553–568, 2022, doi: 10.1007/s10803-021-04931-y.

C. Walsh, P. O’Connor, E. Walsh, and S. Lydon, “A Systematic Review of Interventions to Improve Healthcare Experiences and Access in Autism,” Rev. J. Autism Dev. Disord., vol. 10, no. 2, pp. 185–202, 2023, doi: 10.1007/s40489-021-00279-2.

S. K. Jarraya, M. Masmoudi, and M. Hammami, “A comparative study of Autistic Children Emotion recognition based on Spatio-Temporal and Deep analysis of facial expressions features during a Meltdown Crisis,” Multimed. Tools Appl., vol. 80, no. 1, pp. 83–125, 2021, doi: 10.1007/s11042-020-09451-y.

N. P. Novani, D. R. Salsabila, R. Aisuwarya, L. Arief, and N. Afriyeni, “Sistem Pendeteksi Gejala Awal Tantrum Pada Anak Autisme Melalui Ekspresi Wajah Dengan Convolutional Neural Network,” JITCE (Journal Inf. Technol. Comput. Eng., vol. 5, no. 02, pp. 93–106, 2021, doi: 10.25077/jitce.5.02.93-106.2021.

E. Loth, L. Garrido, J. Ahmad, E. Watson, A. Duff, and B. Duchaine, “Facial expression recognition as a candidate marker for autism spectrum disorder: How frequent and severe are deficits?,” Mol. Autism, vol. 9, no. 1, pp. 1–11, 2018, doi: 10.1186/s13229-018-0187-7.

P. Rani, M. T. Student, and A. Kaur, “Emotion Detection of Autistic Children using Support Vector Machine: A Review,” Int. J. Innov. Sci. Res. Technol., vol. 4, no. 6, pp. 505–508, 2019, [Online]. Available: www.ijisrt.com505

H. Santoso, I. Hanif, H. Magdalena, and Afiyati, “A Hybrid Model for Dry Waste Classification using Transfer Learning and Dimensionality Reduction,” Int. J. Informatics Vis., vol. 8, no. 2, pp. 623–634, 2024, doi: 10.62527/joiv.8.2.1943.

M. S. V. S. K. Narala, S. Vemuri, and C. Kattula, “A Comparative Study for Autism spectrum disorder Using EfficientNet, ResNet50,” 2023 Int. Conf. Comput. Intell. Networks Secur. ICCINS 2023, pp. 1–6, 2023, doi: 10.1109/ICCINS58907.2023.10450124.

M. F. Nadhif and S. Dwiasnati, “Classification of Date Fruit Types Using CNN Algorithm Based on Type,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 3, no. 1, pp. 36–42, 2023, doi: 10.57152/malcom.v3i1.724.

Y. Jumaryadi, A. Muhammad Ihsan, and B. Priambodo, “KLIK: Kajian Ilmiah Informatika dan Komputer Klasifikasi Jenis Buah-Buahan Menggunakan Citra Digital Dengan Metode Convolutional Neural Networks,” Media Online, vol. 4, no. 3, pp. 1737–1746, 2023, doi: 10.30865/klik.v4i3.1421.

I. Ahmad, J. Rashid, M. Faheem, A. Akram, N. A. Khan, and R. ul Amin, “Autism spectrum disorder detection using facial images: A performance comparison of pretrained convolutional neural networks,” Healthc. Technol. Lett., vol. 11, no. 4, pp. 227–239, 2024, doi: 10.1049/htl2.12073.

F. W. Alsaade and M. S. Alzahrani, “Classification and Detection of Autism Spectrum Disorder Based on Deep Learning Algorithms,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/8709145.

A. Ridlan, M. Hasanudin, O. Cizela, and D. E. Latumaerissa, “Early Autism Disorder Prediction Using Machine Learning,” vol. 13, no. 1, 2025.

M. H. O. C. da C. T. D. E. L. Ahmad Ridlan, “early-autism-disorder-prediction-using-machine-learning,” Int. J. Open Inf. Technol., 2025.

A. M. Law, “How to Build Valid and Credible Simulation Models,” Proc. - Winter Simul. Conf., vol. 2022-Decem, pp. 1283–1295, 2022, doi: 10.1109/WSC57314.2022.10015411.

A. Mumuni and F. Mumuni, “Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods,” Knowl. Inf. Syst., 2024, doi: 10.1007/s10115-025-02349-x.

K. Bhavana Yadav, S. Vishwas, N. Anand, B. S. Rishab Kashyap, and R. Bangalore, “Automated Identification and Classification of Autism Spectrum Disorder using Behavioural and Visual Patterns in Children,” 2023 4th Int. Conf. Emerg. Technol. INCET 2023, pp. 1–5, 2023, doi: 10.1109/INCET57972.2023.10170707.

F. Akbar, J. Handani, E. Wijayanti, and R. Fiati, “Implementation Of Convolutional Neural Network Method In Penerapan Metode Convolutional Neural Network Dalam,” vol. 6, no. 1, pp. 211–219, 2025.

O. A. Montesinos López, A. Montesinos López, and J. Crossa, Multivariate Statistical Machine Learning Methods for Genomic Prediction. 2022. doi: 10.1007/978-3-030-89010-0.

R. Sulek et al., “Support Preferences and Clinical Decision Support Systems (CDSS) in the Clinical Care of Autistic Children: Stakeholder Perspectives,” Adv. Neurodev. Disord., no. 0123456789, 2024, doi: 10.1007/s41252-024-00410-4.