Scholarlink

<p>The continuation of human civilization is dependent on the purity of the air, but tremendous improvements in modern life have resulted in severe environmental damage. Industrial, transportation, and home activities emit dangerous pollutants into the atmosphere, reducing air quality. Monitoring the Air Quality Index (AQI) is critical for evaluating environmental health and mitigating the negative consequences of pollution. This research presents a novel framework for dynamic AQI assessment that blends intuitionistic fuzzy credibility numbers (IFCNs) with the Hamacher aggregation operators (HAO) for information integration. The Logic-Oriented Pairwise COmparison Weighted (LOPCOW) methodology, which is combined with the Compromise RAnking via Distance to the Ideal Solution (CRADIS) method.The IFCNs model the uncertainties in AQI measurements, while the HAO ensures reliable aggregation of various pollutant data. LOPCOW prioritizes critical air quality factors, while CRADIS rates pollution sources and mitigation strategies effectively. Furthermore, random forest and principal component analysis are used for feature selection of AQI criterion, resulting in a robust decision analytics for AQI prediction. The suggested approach improves AQI computation accuracy and dependability, allowing for better informed environmental management decisions. Experimental validation using real-world datasets proves the method’s capacity to identify significant pollution causes and optimize resource allocation for air quality improvement. The findings offer policymakers useful insights into establishing focused AQI improvement measures.</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

Integrating machine learning and LOPCOW-CRADIS framework for optimizing air quality index and urban clean environment using intuitionistic fuzzy credibility numbers

  • 期刊论文

  • 发表日期：

    2026年8月4日

查看全文
  • Iqra Zareef,
  • Muhammad Riaz

摘要

The continuation of human civilization is dependent on the purity of the air, but tremendous improvements in modern life have resulted in severe environmental damage. Industrial, transportation, and home activities emit dangerous pollutants into the atmosphere, reducing air quality. Monitoring the Air Quality Index (AQI) is critical for evaluating environmental health and mitigating the negative consequences of pollution. This research presents a novel framework for dynamic AQI assessment that blends intuitionistic fuzzy credibility numbers (IFCNs) with the Hamacher aggregation operators (HAO) for information integration. The Logic-Oriented Pairwise COmparison Weighted (LOPCOW) methodology, which is combined with the Compromise RAnking via Distance to the Ideal Solution (CRADIS) method.The IFCNs model the uncertainties in AQI measurements, while the HAO ensures reliable aggregation of various pollutant data. LOPCOW prioritizes critical air quality factors, while CRADIS rates pollution sources and mitigation strategies effectively. Furthermore, random forest and principal component analysis are used for feature selection of AQI criterion, resulting in a robust decision analytics for AQI prediction. The suggested approach improves AQI computation accuracy and dependability, allowing for better informed environmental management decisions. Experimental validation using real-world datasets proves the method’s capacity to identify significant pollution causes and optimize resource allocation for air quality improvement. The findings offer policymakers useful insights into establishing focused AQI improvement measures.