Statistical approach for modelling exposure to background air pollution
By: Gupta, Naina et al
.
Material type: 
BookPublisher: Urban India: A Journal of the National Institute of Urban Affairs Description: 40(3), Jul-Dec, 2020: p.51-60.Subject(s): Background pollution, Finite mixture model, Hidden markov model, K-mean
In:
Urban India: A Journal of the National Institute of Urban AffairsSummary: Background air pollution is a long term resident and low-level concentration pollution difficult to quantify and to which the population chronically exposed. In this study, hourly time series data of air pollutants CO, NO2 , PM10 were analyzed using the four statistical methods k-means clustering, Finite mixture model, Hidden Markov model and Hierarchical clustering to estimate the exposure to background pollution in Lucknow in two monitoring sites Lalbagh and central school from 2009 to 2019 using 47 data sets. The data sets represents the lowest cluster corresponds to background concentration and hmm clustering technique outperforms compared to the remaining showing estimates of exposure related to background pollution in the form of its percentage cluster size, mean and standard deviation in the ambient air for all the air pollutants and sites studied. – Reproduced
| Item type | Current location | Call number | Vol info | Status | Date due | Barcode |
|---|---|---|---|---|---|---|
Articles
|
Indian Institute of Public Administration | 40(3), Jul-Dec, 2020: p.51-60 | Available | AR125395 |
Background air pollution is a long term resident and low-level concentration pollution difficult to quantify and to which the population chronically exposed. In this study, hourly time series data of air pollutants CO, NO2 , PM10 were analyzed using the four statistical methods k-means clustering, Finite mixture model, Hidden Markov model and Hierarchical clustering to estimate the exposure to background pollution in Lucknow in two monitoring sites Lalbagh and central school from 2009 to 2019 using 47 data sets. The data sets represents the lowest cluster corresponds to background concentration and hmm clustering technique outperforms compared to the remaining showing estimates of exposure related to background pollution in the form of its percentage cluster size, mean and standard deviation in the ambient air for all the air pollutants and sites studied. – Reproduced
There are no comments for this item.