Detection and impact of stochastic anomalies in investigations of urban pollution

Natrayan Lakshmaiya

doi:10.1117/12.3030839

26 June 2024 Detection and impact of stochastic anomalies in investigations of urban pollution

Natrayan Lakshmaiya

Proceedings Volume 13188, International Conference on Medical Imaging, Electronic Imaging, Information Technologies, and Sensors (MIEITS 2024); 131880V (2024) https://doi.org/10.1117/12.3030839
Event: International Conference on Medical Imaging, Electronic Imaging, Information Technologies, and Sensors (MIEITS 2024), 2024, Kuala Lumpur, Malaysia

Abstract

Four separate techniques—box graphs, variogram skies, differential diagrams, and the local version of Moran's equation I statistic—were used to find 48 probable anomalies in data on air quality made concurrently in Detroit, Michigan, the United States, and Windsor, Canada's province of Ontario, in the years 2008 and 2009. Following that, an additional set of 12 anomalies for nitrogen oxides, organic volatile chemicals, overall benzene, toluene, methyl, a chemical called xylene, as well as particulates separated into two sized divisions, were reduced and chosen using either one of these approaches. The determined outlier has been employed to update the air contamination algorithms after being removed from the data collection dataset. Furthermore, employing time series information from the neighbourhood’s air quality sensors, both with and without the chosen anomalies, a set of dynamically adjusted atmospheric pollution models was created. In both municipalities, relationships with flare-up incidences have been combined at a postal sector production, and the impact of outlier elimination on the relationships was measured.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Natrayan Lakshmaiya "Detection and impact of stochastic anomalies in investigations of urban pollution", Proc. SPIE 13188, International Conference on Medical Imaging, Electronic Imaging, Information Technologies, and Sensors (MIEITS 2024), 131880V (26 June 2024); https://doi.org/10.1117/12.3030839

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available