Scholarlink

<p>Acid rain monitoring is crucial for evaluating the environmental impacts of air pollution on ecosystems. However, current manual measurement methods are limited in several ways. For example, they rely on only a few parameters, lack real-time monitoring capability, and often fail to detect anomalies or account for measurement variability. These limitations result in incomplete datasets, which in turn reduce the accuracy and reliability of the information used for environmental decision. A new system for real-time information is proposed in this study, which employs the Expert-Fuzzy method within a Decision Support System (DSS) that enhances the precision and consistency of acid rain measurements. Such improvements include individual sensor range detection, outlier identification, dynamic windowing, and averaging, all of which are facilitated by integrating these advanced statistical techniques into the Raspberry Pi. These enhancements improve confidence intervals and precision in the real-time validation of data. From May 7 to June 7, 2023, field testing took place at two locations (−&#xa0;6.9729594, 107.6274528; −&#xa0;6.969282, 107.6255821), where key parameters, including pH, temperature, and conductivity, among others, were monitored to ensure a confidence level of approximately 95%. The minor discrepancies between the raw data and the validated results suggest that this system’s precision is compromised, as the pH readings were 5.99, the conductivity measured 14.47&#xa0;ms/cm, and the temperatures were 25.01&#xa0;°C. The more support for the stability of these measurements from statistical T-tests, ANOVA, and evaluation metrics, the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model, which traces the sources of possible neutralisation pollutants. This research demonstrates that acid rain classification and decision-making can be improved by integrating expert knowledge with fuzzy logic. Using the Expert-Fuzzy method, environmental monitoring measurements can be made more precise and reliable.</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

Decision support system using the expert-fuzzy method in validating real-time acid rain measurements

  • 期刊论文

  • 发表日期：

    2025年11月4日

查看全文
  • Ardiansyah Ramadhan,
  • Indra Chandra,
  • Asri Indrawati,
  • Dyah Aries Tanti,
  • Israel Mendonça,
  • Masayoshi Aritsugi

摘要

Acid rain monitoring is crucial for evaluating the environmental impacts of air pollution on ecosystems. However, current manual measurement methods are limited in several ways. For example, they rely on only a few parameters, lack real-time monitoring capability, and often fail to detect anomalies or account for measurement variability. These limitations result in incomplete datasets, which in turn reduce the accuracy and reliability of the information used for environmental decision. A new system for real-time information is proposed in this study, which employs the Expert-Fuzzy method within a Decision Support System (DSS) that enhances the precision and consistency of acid rain measurements. Such improvements include individual sensor range detection, outlier identification, dynamic windowing, and averaging, all of which are facilitated by integrating these advanced statistical techniques into the Raspberry Pi. These enhancements improve confidence intervals and precision in the real-time validation of data. From May 7 to June 7, 2023, field testing took place at two locations (− 6.9729594, 107.6274528; − 6.969282, 107.6255821), where key parameters, including pH, temperature, and conductivity, among others, were monitored to ensure a confidence level of approximately 95%. The minor discrepancies between the raw data and the validated results suggest that this system’s precision is compromised, as the pH readings were 5.99, the conductivity measured 14.47 ms/cm, and the temperatures were 25.01 °C. The more support for the stability of these measurements from statistical T-tests, ANOVA, and evaluation metrics, the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model, which traces the sources of possible neutralisation pollutants. This research demonstrates that acid rain classification and decision-making can be improved by integrating expert knowledge with fuzzy logic. Using the Expert-Fuzzy method, environmental monitoring measurements can be made more precise and reliable.