• Version
• Download 528
• File Size 514.29 KB
• Create Date December 29, 2020
• Download

Salvatore Rampone, Alessio Valente

Every day huge quantities of pollutants coming mainly from combustion processes continue to be poured into the atmosphere. Such emission products can interact with each other, favoured by physic-chemical conditions, resulting in new pollutants (ozone). An accumulation of pollutants in the lowest part of atmosphere can be dangerous for human health. Despite the fact that the quality of the air has recently improved in Italyand throughout Europe, to thisday pollution is still recognized as one of the main environmental risk factors. Administrations are obliged to prepare an air quality plan, when the levels of pollutants exceed the assigned limits, and this helps to activate recovery measures in the urban area. The aim of this research is to correlate trough soft computing techniques (Artificial Neural Networks - ANN and Genetic Programming - GP) the data of the tumours registered by the Local Health Authority (ASL) of the city of Benevento (Italy) with those of the concentrations of pollutants detected in the air quality monitoring stations. Such stations are equipped with instruments able to monitor the following components: NO2, CO, PM10, PM2.5, O3 and Benzene (C6H6). For this research, the data relating to pollutants are from the 2012-2014 period while, assuming possible effects on human health in the medium term, the tumour data, provided by local hospitals, refer to the years 2016-2018. The ANN result, confirmed by GP, shows a high correlation between the cases of lung tumours and the exceedance of atmospheric particulate matter and ozone.

Keywords: Air pollution; Tumour data; Soft computing techniques; Benevento; Italy

Proscience vol. 7

Pp 75-83

DOI: 10.14644/ghc2020.012