Facial Image-Based Autism Detection: A Comparative Study Among Machine Learning, Deep Learning and Transfer Learning
DOI:
https://doi.org/10.64296/vijir.v1i1.02Keywords:
Autism detection, Facial autism, Deep learning, Transfer learning, EfficientNetAbstract
For prompt intervention and better results, early autism screening is essential. This work investigates the use of face image databases for autism classification in a non-invasive, cost-effective manner. Support Vector Machine (SVM), Convolutional Neural Network (CNN), and EfficientNet were the three classification models used. With the greatest accuracy of 85.67% and superior performance across important performance parameters including precision, recall, and F1-score, EfficientNet surpassed the competition. The work demonstrates how EfficientNet may be used to detect minute face traits associated with autism, providing a good substitute for more traditional techniques including brain signal, imaging, and video analysis. This study highlights the potential of cutting-edge machine learning models for autism identification and promotes more investigation into bigger datasets to improve diagnostic accessibility and accuracy.
References
[1] Ahammed, M. S., Niu, S., Ahmed, M. R., Dong, J., Gao, X., and Chen, Y. Bag-of-features model for ASD fMRI classification using SVM. Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS), Shenyang, China: IEEE, Jan. 2021, pp. 52–57. doi: 10.1109/ACCTCS52002.2021.00019.Faras, H., Al Ateeqi, N., and Tidmarsh, L. Autism spectrum disorders, Annals of Saudi Medicine, 2010: 30(4), pp. 295–300, doi: 10.4103/0256-4947.65261
[2] Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L., and Lopez, A. A comprehensive survey on support vector machine classification: Applications, challenges and trends, Neurocomputing, 2020: 408, pp. 189–215, doi: 10.1016/j.neucom.2019.10.118.Karthik, M. D., Jeba Priya, S., and Mathu, T. Autism detection for toddlers using facial features with deep learning. In: 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India: IEEE, Jun. 2024, pp. 726–731. doi: 10.1109/ICAAIC60222.2024.10575487
[3] Charman, T. Variability in neuro-developmental disorders In: Evidence from Autism Spectrum Disorders, 2014, 25 pages.Li, B., Mehta, S., Aneja, D., Foster, C., Ventola, P., Shic, F., and Shapiro, L. A facial affect analysis system for autism spectrum disorder. In: IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan: IEEE, Sep. 2019, pp. 4549–4553. doi: 10.1109/ICIP.2019.8803604
[4] Faras, H., Al Ateeqi, N., and Tidmarsh, L. Autism spectrum disorders, Annals of Saudi Medicine, 2010: 30(4), pp. 295–300, doi: 10.4103/0256-4947.65261
[5] Hasan, M. M., Hossain, M. M., Sulaiman, N., Islam, M. N., and Khandaker, S. Automatic microsleep detection based on KNN classifier utilizing selected and effective EEG channels, J. Teknol., 2024: 86(6), pp. 165–177, doi: 10.11113/jurnalteknologi.v86.22154.Is it autism? Facial features that show disorder, CBS NEWS, Oct. 2011. [Online]. Available: https://www.cbsnews.com/pictures/is-it-autism-facial-features-that-show-disorder/10/
[6] Hasan, M. M., Islam, M. N., Khandaker, S., Sulaiman, N., Islam, A., and Hossain, M. M. Ensemble-based machine learning models for vehicle drivers’ fatigue state detection utilizing EEG signals, Electronics and Energetics - Facta Universitatis, 2024: 37, pp. 671–686.
doi: https://doi.org/10.2298/FUEE2404671H
[7] Hasan, M. M., Mirza, M. H., and Sulaiman, N. Fatigue state detection through multiple machine learning classifiers using EEG signal, Applications of Modelling and Simulation, 2023: 7, pp. 178–189.
[8] Hortal, E., Ianez, E., Ubeda, A., Planelles, D., Costa, A., and Azorin, J. M. Selection of the best mental tasks for a SVM-based BCI system. In: IEEE International Conference on Systems, Man, and Cybernetics (SMC), San Diego, CA, USA: IEEE, Oct. 2014, pp. 1483–1488. doi: 10.1109/SMC.2014.6974125
[9] Is it autism? Facial features that show disorder, CBS NEWS, Oct. 2011. [Online]. Available: https://www.cbsnews.com/pictures/is-it-autism-facial-features-that-show-disorder/10/
[10] Islam, M. N., Sulaiman, N., Rashid, M., Mustafa, M., and Hasan, M. J. Auditory evoked potentials (AEPs) response classification: A fast Fourier transform (FFT) and support vector machine (SVM) approach. In: K. Isa, Z. Md. Zain, R. Mohd-Mokhtar, M. Mat Noh, Z. H. Ismail, A. A. Yusof, A. F. Mohamad Ayob, S. S. Azhar Ali, and H. Abdul Kadir, (Eds.), Lecture Notes in Electrical Engineering, 2022: 770, Singapore: Springer, pp. 539–549. doi: 10.1007/978-981-16-2406-3_41.Spectrum Boston children’s hospital testing & diagnosis for autism disorder in children. [Online]. Available: https://on.bchil.org/38N6bRR
[11] Itani, S., and Thanou, D. Combining anatomical and functional networks for neuropathology identification: A case study on autism spectrum disorder, Medical Image Analysis, 2021: 69, p. 101986, doi: 10.1016/j.media.2021.101986.Khosla, Y., Ramachandra, P., and Chaitra, N. Detection of autistic individuals using facial images and deep learning. IEEE International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), Bangalore, India: IEEE, Dec. 2021, pp. 1–5. doi: 10.1109/CSITSS54238.2021.9683205
[12] Karthik, M. D., Jeba Priya, S., and Mathu, T. Autism detection for toddlers using facial features with deep learning. In: 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India: IEEE, Jun. 2024, pp. 726–731.
doi: 10.1109/ICAAIC60222.2024.10575487
[13] Khan, I. Autistic children facial dataset [Online].
Available: https://www.kaggle.com/datasets/imrankhan77/autistic-children-facial-data-set.
[14] Khosla, Y., Ramachandra, P., and Chaitra, N. Detection of autistic individuals using facial images and deep learning. IEEE International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), Bangalore, India: IEEE, Dec. 2021, pp. 1–5. doi: 10.1109/CSITSS54238.2021.9683205
[15] Lee, T., Na, Y., Kim, B. G., Lee, S., and Choi, Y. Identification of individual Hanwoo cattle by muzzle pattern images through deep learning, Animals, 2023: 13(18), p. 2856, doi: 10.3390/ani13182856
[16] Li, B., Mehta, S., Aneja, D., Foster, C., Ventola, P., Shic, F., and Shapiro, L. A facial affect analysis system for autism spectrum disorder. In: IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan: IEEE, Sep. 2019, pp. 4549–4553.
doi: 10.1109/ICIP.2019.8803604
[17] Mhiri, I., and Rekik, I. Joint functional brain network atlas estimation and feature selection for neurological disorder diagnosis with application to autism, Medical Image Analysis, 2020: 60, p. 101596, doi: 10.1016/j.media.2019.101596
[18] Sadiq, S., Castellanos, M., Moffitt, J., Shyu, M.-L., Perry, L. and Messinger, D. Deep learning based multimedia data mining for autism spectrum disorder (ASD) diagnosis. International Conference on Data Mining Workshops (ICDMW), Beijing, China: IEEE, Nov. 2019, pp. 847–854. doi: 10.1109/ICDMW.2019.00124
[19] Sherkatghanad, Z., Akhondzadeh, M. S., Salari, S., Moghadam, M. Z., Abdar, M., Acharya, U. R., Khosrowabadi, R., and Salari, V. Automated detection of autism spectrum disorder using a convolutional neural network, Front. Neurosci., 2020: 13, p. 1325, doi: 10.3389/fnins.2019.01325
[20] Spectrum Boston children’s hospital testing & diagnosis for autism disorder in children. [Online]. Available: https://on.bchil.org/38N6bRR
[21] Tamilarasi, F. C., Vatti, R., and Shanmugam, J. Child autism detection based on facial feature classification, International Journal of Advanced Research in Engineering and Technology (IJARET), 2020: 11(10), pp. 468–475.
[22] Thabtah, F., and Peebles, D. A new machine learning model based on induction of rules for autism detection, Health Informatics J, 2020: 26(1), pp. 264–286, doi: 10.1177/1460458218824711
[23] Vakadkar, K., Purkayastha, D., and Krishnan, D. Detection of autism spectrum disorder in children using machine learning techniques, SN Comput. Sci., 2021: 2(5), p. 386, doi: 10.1007/s42979-021-00776-5
[24] Zhan, Y., Wei, J., Liang, J., Xu, X., He, R., Robbins, T. W., and Wang, Z. Diagnostic classification for human autism and obsessive-compulsive disorder based on machine learning from a primate genetic model, AJP, 2021: 178(1), pp. 65–76, doi: 10.1176/appi.ajp.2020.19101091
