Unsupervised and Supervised Learning based Classification Models for Air Pollution Data

As far as, air quality index (AQI) is concerned, the long duration lockdown that was applied in India in year 2020 due to Covid-19 pandemic was very fruitful. The reason being, due to complete ban on the movement of people and automobiles, the air became so pure and clean, and AQI value went much down. The secondary air pollution data of the lockdown duration, for Uttarakhand, is the base of this research work. This work attempts to design unsupervised and supervised classification models to classify the provided data into two classes i.e class 1 ('clean') and class 2 ('hazardous') using MATLAB. The techniques used are FCM clustering and Probabilistic neural network (PNN). Eventually, a comparative study of the performance of both models is performed. © 2021 IEEE.

LVQ Based Classification of Air Quality Using Data for Lockdown Period of COVID-19

The lockdown duration of COVID-19 gave rise to a significant betterment in AQI (Air Quality Index) worldwide. In the present research paper, binary classification problem of the air pollutants data of Uttarakhand, India, for year 2019 and 2020 (lockdown period), has been addressed. This problem is challenging to solve as it is non-linearly separable. Using this data, a neural network has been trained, to perform classification, using competitive learning technique (unsupervised learning). Then, for achieving better classification results, a supervised learning technique, learning vector quantization algorithm (LVQ), is used. Finally, the performance of both the networks is compared. All results are obtained in MATLAB. © 2021 IEEE.

K-Means Clustering of Ambient Air Quality Data of Uttarakhand, India during Lockdown Period of Covid-19 Pandemic

The analysis of the lockdown effect during covid-19 pandemic on ambient quality of air of Uttarakhand state of India, has been performed. The combination of SO2, NO2, and particulate matter (P.M.10) indicates ambient air quality characteristics. The clustering capability of the K-means clustering technique is investigated with two different approaches of measuring distance using MATLAB. The first approach is termed Euclidean distance and the second one is cosine distance. The data, which is clustered, is the air uualitv data containing three major components of air pollution such as P.M.10, SO2, and NO2 of different major cities of Uttarakhand. © 2021 IEEE.