Abstract: The feasibility of photocatalytic degradation of X3B azo dye by TiO2/beads photocatalyst was studied. The effects of parameters such as the amount of TiO2/beads, airflow, as well as the concentrations of H2O2, Fe3+, Mg2+ and Na+ on the photocatalytic degradation of X3B azo dye were also studied. The results showed that 25 mg/dm3 X3B azo dye can be photocatalytically degraded completely by 30 min illumination with a 375W medium pressure mercury lamp. Adding a small amount of H2O2 or Fe3+, the efficiencies of photocatalytic degradation of X3B azo dye were increased rapidly. The mechanisms of the reaction and the role…of the additives were also investigated. After 120 hours TiO2/beads showed no significant loss of the photocatalytic activity.
Show more
Abstract: Neural network ensemble can significantly improve the generalization ability of neural network based systems. However, its comprehensibility is even worse than that of a single neural network because it comprises a collection of individual neural networks. In this paper, an approach named REFNE is proposed to improve the comprehensibility of trained neural network ensembles that perform classification tasks. REFNE utilizes the trained ensembles to generate instances and then extracts symbolic rules from those instances. It gracefully breaks the ties made by individual neural networks in prediction. It also employs specific discretization scheme, rule form, and fidelity evaluation mechanism. Experiments show…that with different configurations, REFNE can extract rules with good fidelity that well explain the function of trained neural network ensembles, or rules with strong generalization ability that are even better than the trained neural network ensembles in prediction.
Show more