| 摘 要: 常用的空气质量等级分析方法由于没有考虑大气污染物之间的关联性,导致在治理空气质量时可能存在单一性和片面性。文章提出了基于Apriori算法(关联规则算法)对各项大气污染物之间的关联性进行分析研究。该方法对获取的原始样本集进行了属性规约、数据离散化等预处理,将处理后的样本数据集输入模型,设置并调整了模型的最小支持度和最小置信度,直至输出符合现实意义的关联规则集合。根据实验得出的关联规则,证明空气污染问题通常是多种污染物共同作用的结果。 |
| 关键词: Apriori;大气污染物;支持度;置信度 |
|
中图分类号: TP181
文献标识码: A
|
| 基金项目: 山西省软科学研究计划(2019041023-5) |
|
| Research on Correlation Analysis of Air Pollutants Based on Apriori Algorithm |
|
GUO Yanping, GAO Yun, JING Wen
|
(School of Computer and Network Engineering, Shanxi Datong University, Datong 037009, China)
38922343@qq.com; 63378161@qq.com; 29708916@qq.com
|
| Abstract: Commonly used air quality grade analysis methods do not take into account the correlation between atmospheric pollutants, resulting in a potentially one-dimensional and one-sided approach to air quality control. The paper proposes to analyze and study the correlation analysis between various air pollutants based on Apriori algorithm (association rules algorithm). With the proposed method, the obtained original sample set is preprocessed by attribute specification and data discretization, and then, the processed sample data set is input into the model. The minimum support degree and minimum confidence degree of the model are set and adjusted until the output conforms to the association rule set of practical significance. The association rules obtained from experiments prove that air pollution problems are usually the result of a combination of pollutants. |
| Keywords: Apriori; air pollutants; support degree; confidence degree |
