Scholarlink

This study addresses the significant challenge of accurately detecting Hand, Foot, and Mouth Disease (HFMD) in infants and children. The research leverages deep neural networks, specifically an ensemble learning approach, to enhance robustness and accuracy in HFMD identification. The meta-model combines predictions from pre-trained neural network architectures, aiming to overcome limitations posed by sparse data and diverse symptom presentations. Our goals include improving HFMD detection precision and comprehensiveness. Methods involve ensemble training with models such as GoogLeNet, ResNet18, MobileNetV2, DenseNet121, and EfficientNet. Results demonstrate the approach’s effectiveness, achieving a notable 94% accuracy on a dedicated test set.

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

Ensemble Deep Learning for Enhanced Detection and Classification of Hand, Foot, and Mouth Disease: A Comprehensive Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Md. Asif Hasan,
  • Mohammad Hasan Azhar,
  • Md. Abid Sarkar,
  • Afsana Hossain Esha,
  • Md. Adnan Morshed,
  • Ahmed Wasif Reza

摘要

This study addresses the significant challenge of accurately detecting Hand, Foot, and Mouth Disease (HFMD) in infants and children. The research leverages deep neural networks, specifically an ensemble learning approach, to enhance robustness and accuracy in HFMD identification. The meta-model combines predictions from pre-trained neural network architectures, aiming to overcome limitations posed by sparse data and diverse symptom presentations. Our goals include improving HFMD detection precision and comprehensiveness. Methods involve ensemble training with models such as GoogLeNet, ResNet18, MobileNetV2, DenseNet121, and EfficientNet. Results demonstrate the approach’s effectiveness, achieving a notable 94% accuracy on a dedicated test set.