The bias in reversing the Box-Cox transformation in time series forecasting: An empirical study based on neural networks

The Box-Cox transformation is a technique mostly utilized to turn the probabilistic distribution of a time series data into approximately normal. And this helps statistical and neural models to perform more accurate forecastings. However, it introduces a bias when the reversion of the transformation is conducted with the predicted data. The statistical methods to perform a bias-free reversion require, necessarily, the assumption of Gaussianity of the transformed data distribution, which is a rare event in real-world time series. So, the aim of this study was to provide an effective method of removing the bias when the reversion of the Box-Cox transformation is executed. Thus, the developed method is based on a focused time lagged feedforward neural network, which does not require any assumption about the transformed data distribution. Therefore, to evaluate the performance of the proposed method, numerical simulations were conducted and the Mean Absolute Percentage Error, the Theil Inequality Index and the Signal-to-Noise ratio of 20-step-ahead forecasts of 40 time series were compared, and the results obtained indicate that the proposed reversion method is valid and justifies new studies. (C) 2014 Elsevier B.V. All rights reserved.

Bacterial and chemical leaching of chalcopyrite concentrates as affected by the redox potential and ferric/ferrous iron ratio at 22 degrees C

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Analysis of the intestinal bacterial microbiota in maize- or sorghum-fed broiler chickens using real-time PCR

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Impact of the temperament of Nellore cows on the quality of handling and pregnancy rates in fixed-time artificial insemination

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

The "chemical oxygen demand/total volatile acids" ratio as an anaerobic treatability indicator for landfill leachates

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

The mechanism of 234U 238U activity ratio enhancement in karstic limestone groundwater

Experimental etch/leach of Carboniferous Limestone gravels on a laboratory time-scale has demonstrated that 234U 238U activity ratios (AR's) greater than the radiochemical equilibrium value may be generated on short time-scales. The molar U/Ca and Mg/Ca ratios show that both U and Mg are leached preferentially relative to Ca whereas the molar U/Mg ratio is only slightly greater than that of the rock matrix. The generation of enhanced AR's is attributed to a two-stage process in which the limestone surface is dissolved by zero-order etch and silicate minerals so released are subjected to first-order chemical leach of U and Mg. The implications of these results for the production of enhanced AR's in Carboniferous Limestone groundwater are discussed. It is suggested that chemical leaching or exchange of U between groundwater and its particulate load or at the aquifer fluid-solid interface is an important mechanism controlling AR changes as groundwater migrates beyond a redox boundary. AR's for dissolved U in groundwater are more probably related to chemical equilibria than to groundwater age. © 1993.

The chemical oxygen demand / total volatile acids ratio as an anaerobic treatability indicator for landfill leachates

In some operational circumstances a fast evaluation of landfill leachate anaerobic treatability is necessary, and neither Biochemical Methane Potential nor BOD/COD ratio are fast enough. Looking for a fast indicator, this work evaluated the anaerobic treatability of landfill leachate from São Carlos-SP (Brazil) in a pilot scale Anaerobic Sequence Batch Biofilm Reactor (AnSBBR). The experiment was conducted at ambient temperature in the landfill area. After the acclimation, at a second stage of operation, the AnSBBR presented efficiency above 70%, in terms of COD removal, utilizing landfill leachate without water dilution, with an inlet COD of about 11,000 mg.L-1, a TVA/COD ratio of approximately 0.6 and reaction time equal to 7 days. To evaluate the landfill leachate biodegradability variation over time, temporal profiles of concentration were performed in the AnSBBR. The landfill leachate anaerobic biodegradability was verified to have a direct and strong relationship to the TVA/COD ratio. For a TVA/CODTotal ratio lower than 0.20, the biodegradability was considered low, for ratios between 0.20 and 0.40 it was considered medium, and above 0.40 it was considered high.