The investigation of mercury presence in human blood: an extrapolation from animal data using neural networks

In this research effort, a neural network approach was used as a method of extrapolating the presence of mercury in human blood from animal data. We also investigated the effect of different data representations (as-is, category, simple binary, thermometer and flag) on the model performance. In addition, we used the rough sets methodology to identify the redundant independent variables and then examined the proposed extrapolation model´s performance for a reduced set of independent variables. Moreover, a quality measure was introduced that revealed that the proposed extrapolation model performed extremely well for the thermometer data representation.