TY - CHAP

T1 - Using artificial neural networks for continuously decreasing time series data forecasting

T2 - A recent strategy for processing complex signals applications to chemistry

AU - Gutiérrez, Juan Manuel

AU - Muñoz, Roberto

AU - del Valle, Manel

N1 - Publisher Copyright:
© 2011 by Nova Science Publishers, Inc.
Grup de Sensors i Biosensors

PY - 2021/2/12

Y1 - 2021/2/12

N2 - Data preprocessing is an issue that is often recommended to create more uniform data to facilitate ANN learning, meet transfer function requirements, and avoid computation problems. In ANN typical transfer functions, such as the sigmoid logistic function, or the hyperbolic tangent function, cannot distinguish between two very large values, because both yield identical threshold output values of 1.0. It is then necessary to normalize (preprocess) the inputs and outputs of a network. Usually normalization is carried out using the minimum and maximum values obtained in the in-sample (calibration) data. Such a network will result in absurd output, if the out-of-sample (test) data contain values that are beyond the in-sample data range. This ultimately limits the application of ANN in forecasting continuously increasing or decreasing time series data. This study will present a novel and successful application of ANN, which is trained by the error backpropagation algorithm, in the context of forecasting beyond in-sample data range. The emphasis here is on continuously decreasing hydraulic pressure data forecasting that are observed at Mizunami underground research laboratory construction site, Japan. The ANN utilizes the sigmoid logistic function in its hidden and output layers.

AB - Data preprocessing is an issue that is often recommended to create more uniform data to facilitate ANN learning, meet transfer function requirements, and avoid computation problems. In ANN typical transfer functions, such as the sigmoid logistic function, or the hyperbolic tangent function, cannot distinguish between two very large values, because both yield identical threshold output values of 1.0. It is then necessary to normalize (preprocess) the inputs and outputs of a network. Usually normalization is carried out using the minimum and maximum values obtained in the in-sample (calibration) data. Such a network will result in absurd output, if the out-of-sample (test) data contain values that are beyond the in-sample data range. This ultimately limits the application of ANN in forecasting continuously increasing or decreasing time series data. This study will present a novel and successful application of ANN, which is trained by the error backpropagation algorithm, in the context of forecasting beyond in-sample data range. The emphasis here is on continuously decreasing hydraulic pressure data forecasting that are observed at Mizunami underground research laboratory construction site, Japan. The ANN utilizes the sigmoid logistic function in its hidden and output layers.

UR - http://www.scopus.com/inward/record.url?scp=85108920985&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/4a5fd5bf-3769-3f0b-8710-94ad45008bbb/

M3 - Chapter

AN - SCOPUS:85108920985

T3 - Focus on Artificial Neural Networks

SP - 323

EP - 340

BT - Focus on Artificial Neural Networks

A2 - Flores, John A.

ER -