A Study of Detection of Outliers for Working and Non-Working Days Air Quality in Kolkata, India: A Case Study  

作　　者：Mohammad Ahmad Weihu Cheng Zhao Xu Abdul Kalam Mohammad Ahmad;Weihu Cheng;Zhao Xu;Abdul Kalam(Faculty of Science, Beijing University of Technology, Beijing, China)

机构地区：[1]Faculty of Science, Beijing University of Technology, Beijing, China

出　　处：《Journal of Environmental Protection》2023年第8期685-709,共22页环境保护（英文）

摘　　要：A variety of factors affect air quality, making it a difficult issue. The level of clean air in a certain area is referred to as air quality. It is challenging for conventional approaches to correctly discover aberrant values or outliers due to the significant fluctuation of this sort of data, which is influenced by Climate change and the environment. With accelerating industrial expansion and rising population density in Kolkata City, air pollution is continuously rising. This study involves two phases, in the first phase imputation of missing values and second detection of outliers using Statistical Process Control (SPC), and Functional Data Analysis (FDA), studies to achieve the efficacy of the outlier identification methodology proposed with working days and Nonworking days of the variables NO₂, SO₂, and O₃, which were used for a year in a row in Kolkata, India. The results show how the functional data approach outshines traditional outlier detection methods. The outcomes show that functional data analysis vibrates more than the other two approaches after imputation, and the suggested outlier detector is absolutely appropriate for the precise detection of outliers in highly variable data.A variety of factors affect air quality, making it a difficult issue. The level of clean air in a certain area is referred to as air quality. It is challenging for conventional approaches to correctly discover aberrant values or outliers due to the significant fluctuation of this sort of data, which is influenced by Climate change and the environment. With accelerating industrial expansion and rising population density in Kolkata City, air pollution is continuously rising. This study involves two phases, in the first phase imputation of missing values and second detection of outliers using Statistical Process Control (SPC), and Functional Data Analysis (FDA), studies to achieve the efficacy of the outlier identification methodology proposed with working days and Nonworking days of the variables NO₂, SO₂, and O₃, which were used for a year in a row in Kolkata, India. The results show how the functional data approach outshines traditional outlier detection methods. The outcomes show that functional data analysis vibrates more than the other two approaches after imputation, and the suggested outlier detector is absolutely appropriate for the precise detection of outliers in highly variable data.

关 键 词：Statistical Process Control Functional Data Analysis Fuzzy C Means OUTLIERS Air Quality 

分 类 号：R73[医药卫生—肿瘤]