Alphanumeric Journal (Jun 2022)

Classification of Autism Spectrum Disorder for Adolescents Using Artificial Neural Networks

  • Sümeyye Çelik,
  • Melike Şişeci Çeşmeli,
  • İhsan Pençe,
  • Özlem Çetinkaya Bozkurt

DOI
https://doi.org/10.17093/alphanumeric.1031513
Journal volume & issue
Vol. 10, no. 1
pp. 15 – 24

Abstract

Read online

Artificial neural networks, is one of the most preferred artificial intelligence techniques in the modeling of complex systems today and the models are based on the working structure of the nerve cells in the human brain. Autism spectrum disorder is a complex neuro-developmental disorder that is congenital or occurs at an early age. Since early diagnosis has a very important role in the treatment, there are many studies on this subject. In this study, a subset of current autism spectrum disorder data obtained from UCI machine learning repository for adolescents has used. In order to test the success of the model, after the necessary preprocesses have performed on the data set, the data has separated into training and test set and classified with the trained network. As a result, 100% accuracy rate in the training set and 96.77% accuracy rate in the test set are achieved. Sensitivity, Specificity and F-measure values obtained in the test set are 0.94, 1.0 and 0.97, respectively and reveals the model success.

Keywords