Scholarlink

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopmental condition impacting academic performance and social interactions. Traditional diagnostic methods rely heavily on subjective behavioral assessments. This study introduces an EEG-based classification approach using 1D Convolutional Neural Networks (CNNs). EEG signals from 121 participants (61 ADHD, 60 controls) were pre-processed and segmented into overlapping epochs. A CNN architecture employing small kernels, Leaky ReLU activation, dropout, and the Adam optimizer was trained for binary classification. The model achieved 94% accuracy, 94.44% specificity, and 92.94% sensitivity. These results highlight the promise of deep learning-enhanced EEG analysis as an objective diagnostic tool for ADHD.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

EEG-Based ADHD Classification Using 1D CNN

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Venkat Avinash Kollu,
  • Radhika R,
  • Kabir Gupta,
  • Shoumik Behera

摘要

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurodevelopmental condition impacting academic performance and social interactions. Traditional diagnostic methods rely heavily on subjective behavioral assessments. This study introduces an EEG-based classification approach using 1D Convolutional Neural Networks (CNNs). EEG signals from 121 participants (61 ADHD, 60 controls) were pre-processed and segmented into overlapping epochs. A CNN architecture employing small kernels, Leaky ReLU activation, dropout, and the Adam optimizer was trained for binary classification. The model achieved 94% accuracy, 94.44% specificity, and 92.94% sensitivity. These results highlight the promise of deep learning-enhanced EEG analysis as an objective diagnostic tool for ADHD.