Scholarlink

The goal of the study is to use deep learning and machine learning models to enhance early identification and diagnosis of Autism Spectrum Disorder (ASD). The ABIDE preprocessed dataset is used in this study, along with other classification approaches such as Decision Trees, Random Forest, Support Vector Machines, K-Nearest Neighbors, and Feedforward Neural Networks. A stacked ensemble model was designed to combine the capabilities of separate classifiers achieving an accuracy of 99.77%. The study discovered that deep learning captures complex patterns in neuroimaging data, implying that hybrid models can make a major contribution to early detection and prompt therapies. Future research should look at larger datasets and more advanced neural networks.

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

Machine Learning and Neural Networks for Enhanced Autism Spectrum Detection ASD Detection with ABIDE Preprocessed Dataset

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Gaytri Mohapatra,
  • Ritu Rani,
  • Rajiv Sharma,
  • Garima Jaiswal,
  • Arun Sharma

摘要

The goal of the study is to use deep learning and machine learning models to enhance early identification and diagnosis of Autism Spectrum Disorder (ASD). The ABIDE preprocessed dataset is used in this study, along with other classification approaches such as Decision Trees, Random Forest, Support Vector Machines, K-Nearest Neighbors, and Feedforward Neural Networks. A stacked ensemble model was designed to combine the capabilities of separate classifiers achieving an accuracy of 99.77%. The study discovered that deep learning captures complex patterns in neuroimaging data, implying that hybrid models can make a major contribution to early detection and prompt therapies. Future research should look at larger datasets and more advanced neural networks.