Scholarlink

<p>Pneumonia diagnosis based on X-ray imaging can be costly and inaccessible in resource-limited settings. We propose a machine learning framework that classifies respiratory sounds to detect pneumonia and further distinguish wheeze and crackle, which reflect different pathologies. To improve reliability under class imbalance, we apply a hybrid resampling strategy that combines ADASYN and Tomek Link, and incorporate acoustically plausible augmentations through noise injection and volume control to enhance robustness while preserving signal characteristics. Experiments on the ICBHI 2017 dataset show that XGBoost consistently outperforms Random Forest, achieving higher predictive performance and more confident classifications. These results suggest that the proposed approach enables reliable sound-based respiratory disease screening, even with small and imbalanced datasets.</p>

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

Reliable pneumonia detection and wheeze–crackle classification via data balancing and augmentation

  • 期刊论文

  • 发表日期：

    2026年3月31日

查看全文
  • Jaewon Seong,
  • Soo Min Oh,
  • Bengie L. Ortiz,
  • Jo Woon Chong

摘要

Pneumonia diagnosis based on X-ray imaging can be costly and inaccessible in resource-limited settings. We propose a machine learning framework that classifies respiratory sounds to detect pneumonia and further distinguish wheeze and crackle, which reflect different pathologies. To improve reliability under class imbalance, we apply a hybrid resampling strategy that combines ADASYN and Tomek Link, and incorporate acoustically plausible augmentations through noise injection and volume control to enhance robustness while preserving signal characteristics. Experiments on the ICBHI 2017 dataset show that XGBoost consistently outperforms Random Forest, achieving higher predictive performance and more confident classifications. These results suggest that the proposed approach enables reliable sound-based respiratory disease screening, even with small and imbalanced datasets.