Matrix profile based analysis of repeated patterns of pollutants

Abstract

Air pollution is one of the most pressing challenges nowadays. Almost every country has been contaminated by the environment. The majority of air pollution in the environment is caused by the consumption of energy for certain purposes. There is a significant risk of toxic gas production. Air pollution has a variety of negative effects on people’s health. In humans, it causes a wide range of cutaneous and respiratory issues. Air pollution causes asthma, bronchitis, and a range of other illnesses. Furthermore, it hastens the ageing of the lungs, lowers lung function, and destroys the cells of the respiratory system. In this work, we are trying to find the pollution level and behaviour of pollutants in different stations in Delhi by finding repeated patterns on a daily, weekly, and monthly basis using a matrix profile. Several pollutants are used to discover repeated patterns such as PM2.5, BP, Ozone, RH, etc. and for each pollutant, there are thirty-two stations. The z-normalize method and without the z-normalize method are used to collect results after finding patterns from stations and then cluster them based on euclidean distance between them.