The influence of ARIMA-GARCH parameters in feed forward neural networks prediction

The objective of this article is to find out the influence of the parameters of the ARIMA-GARCH models in the prediction of artificial neural networks (ANN) of the feed forward type, trained with the Levenberg-Marquardt algorithm, through Monte Carlo simulations. The paper presents a study of the relationship between ANN performance and ARIMA-GARCH model parameters, i.e. the fact that depending on the stationarity and other parameters of the time series, the ANN structure should be selected differently. Neural networks have been widely used to predict time series and their capacity for dealing with non-linearities is a normally outstanding advantage. However, the values of the parameters of the models of generalized autoregressive conditional heteroscedasticity have an influence on ANN prediction performance. The combination of the values of the GARCH parameters with the ARIMA autoregressive terms also implies in ANN performance variation. Combining the parameters of the ARIMA-GARCH models and changing the ANN`s topologies, we used the Theil inequality coefficient to measure the prediction of the feed forward ANN.

Synergistic acceleration of thyroid hormone degradation by phenobarbital and the PPAR alpha agonist WY14643 in rat hepatocytes

Energy balance is maintained by controlling both energy intake and energy expenditure. Thyroid hormones play a crucial role in regulating energy expenditure. Their levels are adjusted by a tight feed back-control led regulation of thyroid hormone production/incretion and by their hepatic metabolism. Thyroid hormone degradation has previously been shown to be enhanced by treatment with phenobarbital or other antiepileptic drugs due to a CAR-dependent induction of phase 11 enzymes of xenobiotic metabolism. We have recently shown, that PPAR alpha agonists synergize with phenobarbital to induce another prototypical CAR target gene, CYP2B1. Therefore, it was tested whether a PPAR alpha agonist could enhance the phenobarbital-dependent acceleration of thyroid hormone elimination. In primary cultures of rat hepatocytes the apparent half-life of T3 was reduced after induction with a combination of phenobarbital and the PPARa agonist WY14643 to a larger extent than after induction with either Compound alone. The synergistic reduction of the half-life could be attributed to a synergistic induction of CAR and the CAR target genes that code for enzymes and transporters involved in the hepatic elimination of T3, such as OATP1A1, OATP1A3, UGT1A3 and UCT1A10. The PPAR alpha-dependent CAR induction and the subsequent induction of T3-eliminating enzymes might be of physiological significance for the fasting-incluced reduction in energy expenditure by fatty acids as natural PPARa ligands. The synergism of the PPAR alpha agonist WY14643 and phenobarbital in inducing thyroid hormone breakdown might serve as a paradigm for the synergistic disruption of endocrine control by other combinations of xenobiotics. (C) 2009 Elsevier Inc. All rights reserved.