Modeling of a continuous food process with neural networks /

addition to constructing the models, a variety of techniques

Bibliographic Details
Main Author: Bullock, David Cole, 1969-
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1995.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:addition to constructing the models, a variety of techniques
basis function (RBF) network, and a time lagged recurrent
both next step prediction and multi-step prediction of a
constructed. The models were all designed to provide multi-
for evaluating neural applications is presented, and a
input/multi-output (MIMO) prediction. For next step
linear autoregressive model with exogenous inputs (ARX) was
methodolgy for applying neural networks for time series
modeling is proposed.
models were a feedforward sigmoidal network (FFN), a radial
multi-step prediction, the TLRNN model performed best. In
neural network (TLRNN). As a benchmark for comparison, a
prediction, the ARX model provided the best prediction. For
snack food continuous frying operation. The three neural
Three neural networks were constructed and trained to provide
Item Description:"Major subject: Agricultural Engineering".
Vita.
Physical Description:xii, 154 leaves : illustrations ; 28 cm.
Also available online.
Issued also on microfiche from Lange Micrographics.
Bibliography:Includes bibliographical references.