Systemic Approach for Health Risk Assessment of Ambient Air Concentrations of Benzene in Petrochemical Environments: In-tegration of Fuzzy Logic, Artificial Neural Network, and IRIS Toxicity Method

摘要: Background: Reliable methods are crucial to cope with uncertainties in the risk analysis process. The aim of this study is develop an integrated approach assessing risks benzene petrochemical plant that produces benzene. We offer system contribute imprecise variables into health calculation. Methods: project was conducted Asaluyeh, southern Iran during years from 2013 2014. Integrated method includes fuzzy logic and artificial neural networks. Each technique had specific computational properties. Fuzzy used for estimation absorption rate. Artificial networks can decrease noise data so applied prediction concentration. First, actual exposure calculated then it combined Risk Information System (IRIS) toxicity factors assess real risks. Results: High correlation between measured predicted concentration achieved (R 2 = 0.941). As variable distribution, best a population implied 33% workers exposed less than 1×10 -5 67% inserted 1.0×10 9.8×10 levels. average estimated entire work zones equal 2.4×10 , ranging 1.5×10 -6 6.9×10 . Conclusion: model highly flexible as well rules possibly will be changed according necessities user different circumstance. exposures duplicated through proposed realistic assessment produced.