Deep CNN architecture for autism spectrum disorder detection

  • Unique Paper ID: 176059
  • Volume: 11
  • Issue: 11
  • PageNo: 4819-4824
  • Abstract:
  • Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social interaction, communication, and repetitive behaviours. Early and accurate detection of ASD is crucial for timely intervention and support. This paper explores the application of deep Convolutional Neural Networks (CNNs) for the detection of ASD, leveraging the power of TensorFlow, a widely-used deep learning framework. The proposed system utilizes a comprehensive dataset comprising neuroimaging data, behavioural assessments, and genetic information to train a CNN model capable of identifying ASD-related patterns with high accuracy. The model's architecture is designed to automatically extract and learn intricate features from the input data, enhancing its diagnostic precision. Preliminary results demonstrate that the deep CNN approach, implemented with TensorFlow, achieves significant improvements in the classification of ASD cases compared to traditional methods. This study underscores the potential of deep learning techniques in advancing the early diagnosis of ASD, offering a promising tool for healthcare professionals and researchers in the field.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 11
  • PageNo: 4819-4824

Deep CNN architecture for autism spectrum disorder detection

Related Articles