首页|Exploring statistical and machine learning techniques to identify factors influencing indoor radon concentration
Exploring statistical and machine learning techniques to identify factors influencing indoor radon concentration
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Radon is a radioactive gas with a carcinogenic effect. The malign effect on human health is, however, mostlyinfluenced by the level of exposure. Dangerous exposure occurs predominantly indoors where the level of indoorradon concentration (IRC) is, in its turn, influenced by several factors. The current study aims to investigate thecombined effects of geology, pedology, and house characteristics on the IRC based on 3132 passive radonmeasurements conducted in Romania. Several techniques for evaluating the impact of predictors on thedependent variable were used, from univariate statistics to artificial neural network and random forest regressor(RFR). The RFR model outperformed the other investigated models in terms of R~2 (0.14) and RMSE (0.83) for theradon concentration, as a dependent continuous variable. Using IRC discretized into two classes, based on themedian (115 Bq/m~3), an AUC-ROC value of 0.61 was obtained for logistic regression and 0.62 for the randomforest classifier. The presence of cellar beneath the investigated room, the construction period, the height abovethe sea level or the floor type are the main predictors determined by the models used.
NETL
NSTL
Elsevier
