f EEG based Early Detection of Autism using Convolutional Neural Networks
FOREX Press I. J. of Electrical & Electronics Research
Support Open Access
  • Home/
  • IJEER-120406

Research Article |

EEG based Early Detection of Autism using Convolutional Neural Networks

Author(s): P. Poojitha* and M. Dharani

Published In : International Journal of Electrical and Electronics Research (IJEER)        Volume 12, Issue 4

Publisher : FOREX Publication

Published : 15 October 2024

e-ISSN : 2347-470X

Page(s) : 1163-1172

DOI: https://doi.org/10.37391/IJEER.120406

Abstract

This Timely intervention and improved management of autism spectrum disorder (ASD) are contingent upon early detection. In this paper a novel method for early autism identification using EEG signals and convolutional neural networks (CNNs) is proposed. Preprocessing, wavelet transform, Discrete Cosine Transform (DCT) , energy and entropy function feature extraction, and CNN classifier classification are some of the phases in the suggested approach. EEG signals are first pre-processed to get rid of artifacts and noise. Then, to extract pertinent characteristics from the EEG signals, wavelet transform and DCT are used. For feature extraction, energy and entropy calculations are used to identify unique patterns suggestive of ASD. After then, a CNN classifier receives these features and divides them into two categories: Autism identified or normal identified. The accuracy, specificity, sensitivity, and precision of the suggested approach are among the performance measures that are used to assess its effectiveness. With an accuracy of 92.34%, specificity of 92.95%, sensitivity of 92.65%, and precision of 92.65%, the experimental findings show encouraging performance. When compared to current systems, the suggested approach performs significantly better, outperforming the 91.78% accuracy of the current system.

Keywords: Convolutional Neural Networks (CNNs), Wavelet Transform, Discrete Cosine Transform (DCT), Feature Extraction, Energy and Entropy Functions Classification, Autism Spectrum Disorder (ASD), Performance Metrics.




P. Poojitha*, School of Engineering, Mohan Babu University, Sree Sainath Nagar, Tirupati, India; Email: p.poojitha543@gmail.com

M. Dharani, School of Engineering, Mohan Babu University, Sree Sainath Nagar, Tirupati, India

    [1] Institute of Medicine. (2001). Teaching kids with autism. The National Academy Press, Washington, DC.
    [2] Pelphrey, K. A., Rogers, S. J., Paul, R Volkmar, F. R (Eds.). (2014). Diagnostics, development, and brain mechanisms in the Handbook of Autism and Pervasive Developmental Disorders (Vol. I). New Jersey's Hoboken: John Wiley and Sons.
    [3] Harris, S. L., and Handleman, J (Eds.). (2008). Programs for preschool education The potential of Deep Convolutional Neural Networks (CNNs) for emotion classification from EEG signals was examined in this work. We suggested a brand-new strategy for kids with autism. PRO-ED, Austin, Texas.
    [4] Lord, C., Veenstra-VanderWeele, J., Elsabbagh, M., Baird, G (2018). Spectrum Disorder of Autism. 392 The Lancet, 508-520. 10.1016/S0140-6736 (18) 31129-2 is the DOI.
    [5] (2013) American Psychiatric Association. Publisher, Washington, DC; diagnostic and Statistical Manual of Mental Disorders, Fifth Edition: DSM-5.
    [6] S. Rajamand, M. Shafie-khah, J.P.S. Catalao, ˜ Energy storage systems implementation and photovoltaic output prediction for cost minimization of a Microgrid, Electr. Power Syst. Res. 202 (Jan. 2022), 107596.
    [7] "Feasibility and effectiveness of very early intervention for infants at-risk for autism spectrum disorder: a systematic review," by J. Bradshaw, A. M. Steiner, G. Gengoux, and L. K. Koegel 2015; journal of Developmental and Autism Disorders, 45 (3), 778–794.
    [8] "Autism and developmental disabilities monitoring network surveillance year 2010," Centers for Disease Control and Prevention. MMWR Surveillance Summary, vol. 63, no. SS 02, pp. 1–21, 2014. Occurrence of autism range disorders—Developmental and Autism Disabilities Monitoring Network, 11 locations, the United States, 2010.
    [9] The article "Autism spectrum disorder: screening, diagnosis, and medical evaluation" was published in Seminars in Pediatric Neurology in 2004. It was written by S. J. Spence, P. Sharifi and M. Wiznitzer.
    [10] D. L. Coury, "Information on the USPSTF screening recommendations for autism spectrum disorder: babies, bathwater, and screening for autism," Journal of Developmental and Behavioral Pediatrics, vol. 36, no. 9, pp. 661–663, 2015.
    [11] Early screening for autism spectrum disorder: suggestions for practice and research, L. Zwaigenbaum, M. L. Bauman, D. Fein, et al., Pediatrics, vol. 136, supplement 1, pp. S 41–S 59, 2015.
    [12] "Identification and evaluation of children with autism spectrum disorders," C. P. Johnson and S. M. Myers, Pediatrics, vol. 120, no. 5, pp. 1183–1215, 2007.
    [13] Review of autism screening tests: F. Soleimani, A. Khakshour, Z. Abasi, S. Khayat, S. Z. Ghaemi, and N. A. H. Golchin, International Journal of Pediatrics, vol. 2, no. 4, pp. 319–329, 2014.
    [14] "Screening for autism spectrum disorders: state of the art in Europe," P. García-Primo, A. Hellendoorn, T. Charman, et al., European Child and Adolescent Psychiatry, vol. 23, no. 11, pp. 1005–1021, 2014.

P. Poojitha and M. Dharani (2024), EEG based Early Detection of Autism using Convolutional Neural Networks. IJEER 12(4), 1163-1172. DOI: 10.37391/IJEER.120406.