Scholarlink

<p>This research focuses on utilizing data-driven machine learning techniques to study the impact of air pollution on the health of residents in industrial regions. The objective is to develop an efficient machine learning model that can accurately identify communities with a higher prevalence of health issues and diseases. A population-based survey was conducted in four geographical areas, collecting data on sociodemographic characteristics, health effects, perceived health status, and annoyance due to industries. The proposed model, XGBoost_BLR_GridCV, achieved high accuracy (ROC_AUC: 0.9215), precision of 92%, recall of 91% and f1-score of 91% in predicting the proximity of residents with chronic diseases. The results highlight the significant association between living in high proximity to industrial regions and increased rates of asthma, respiratory illness, and heart-related health problems. Comparative analysis with other tree-based models further demonstrates the effectiveness of the proposed model.</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

Application of XGBoost algorithm and grid search hyperparameter tuning to study health effects among individuals in the industrial area

  • 期刊论文

  • 发表日期：

    2025年1月21日

查看全文
  • Susymary Johnson,
  • Deepalakshmi Perumalsamy

摘要

This research focuses on utilizing data-driven machine learning techniques to study the impact of air pollution on the health of residents in industrial regions. The objective is to develop an efficient machine learning model that can accurately identify communities with a higher prevalence of health issues and diseases. A population-based survey was conducted in four geographical areas, collecting data on sociodemographic characteristics, health effects, perceived health status, and annoyance due to industries. The proposed model, XGBoost_BLR_GridCV, achieved high accuracy (ROC_AUC: 0.9215), precision of 92%, recall of 91% and f1-score of 91% in predicting the proximity of residents with chronic diseases. The results highlight the significant association between living in high proximity to industrial regions and increased rates of asthma, respiratory illness, and heart-related health problems. Comparative analysis with other tree-based models further demonstrates the effectiveness of the proposed model.