Docstoc

Radial basis artificial neural network models for

Document Sample
Radial basis artificial neural network models for Powered By Docstoc
					Radial basis artificial neural network
models for predicting solubility index of
roller dried goat whole milk powder




                                   Sumit Goyal
                                   G. K. Goyal
               WSC17 10-21 Dec.2012




INTRODUCTION
                                             WSC17 10-21 Dec.2012




                Introduction

A study was planned for predicting the solubility
 index of roller dried goat whole milk powder by
 developing radial basis function models.

In today’s tough competition, a key issue that
 defines the success of a manufacturing
 organization is its ability to adapt easily to the
 changes of its business environment.
                                               WSC17 10-21 Dec.2012




                 Introduction

It is very useful for a modern company to have a
 good estimate of how key indicators are going to
 behave in the future, a task that is fulfilled by
 forecasting.

A competent predictive method can improve
 machine utilization, reduce inventories, achieve
 greater flexibility to changes and increase profits.
                                            WSC17 10-21 Dec.2012




                Introduction

The contribution of goat milk to the economic and
 nutritional well being of humanity is undeniable
 in many developing countries, especially in the
 Mediterranean, Middle East, Eastern Europe
 and South American countries.

Goat milk has played a very important role in
 health and nutrition of young and elderly people.
                                            WSC17 10-21 Dec.2012




                Introduction



In present era, the consumers are extremely
 conscious about quality of the foods they buy.

 Regulatory agencies are also very vigilant about
 quality and safety issues and insist on the
 manufacturers adhering to the label claims about
 quality and shelf life.
                                             WSC17 10-21 Dec.2012




                Introduction

Such discerning consumers, therefore, pose a far
 greater challenge in product development and
 marketing.

The development of RBF-ANN models for
 predicting the solubility index of useful dairy
 product, viz., roller dried goat whole milk powder
 would be extremely beneficial to the
 manufactures, retailers, consumers and
 regulatory agencies from the quality, health and
 safety points of view.
             WSC17 10-21 Dec.2012




  REVIEW
    OF
LITERATURE
                                                    WSC17
                                       WSC17 10-21 Dec.2012



        Review of Literature

ANNs have been used as a predictive modelling
tool for several foods, such as :

Butter                Cakes
Cheese                Apple juice
Processed Cheese      Chicken nuggets
Milk                  Iranian flat bread
Burfi                 Potato chips
Cherries              Pistachio nuts
                                            WSC17 10-21 Dec.2012




          Review of Literature



The published literature shows that no study has
 been conducted using ANN modelling for
 predictive analysis on goat milk powder.

 The present study would be of great significance
 to the dairy industry, academicians and
 researchers.
           WSC17 10-21 Dec.2012




METHOD
MATERIAL
                                               WSC17 10-21 Dec.2012




           METHOD MATERIAL

For developing Radial Basis (Exact Fit) and
 Radial Basis (Fewer Neurons) models for
 predicting the solubility index of roller dried goat
 whole milk powder, several combinations were
 tried and tested to train the RBF-ANN models
 with spread constant ranging from 10 to 200.

The dataset was randomly divided into two
 disjoint subsets namely, training set (having 78%
 of the total observations) and testing set (22% of
 the total observations).
                                           WSC17 10-21 Dec.2012




           METHOD MATERIAL
The input variables for RBF-ANN models were
 the data of the product pertaining to loose bulk
 density, packed bulk density, wettability and
 dispersibility, while solubility index was the
 output variable.
                                                    WSC17 10-21 Dec.2012




          METHOD MATERIAL
MSE, RMSE, R2 and E2 were used with the aim to compare the
prediction ability of the developed models.



                             (1)



                             (2)



                             (3)



                             (4)
                                                               WSC17 10-21 Dec.2012




           METHOD MATERIAL
Training pattern of ANN models is illustrated:


                  Training ANN
                     models




                                     Selecting minimum error




                 Calculating error
                   and making
                  adjustment to
                     weights
             WSC17 10-21 Dec.2012




 RESULTS
    &
DISCUSSION
                                             WSC17 10-21 Dec.2012




        RESULTS & DISCUSSION


The Radial Basis (Exact Fit) and Radial Basis
 (Fewer Neurons) models got simulated very well,
 and gave high R2 and E2 values.

 The best results for radial basis model were with
 the spread constant 20MSE 6.18519E-05;
 RMSE: 0.007864599; R2: 0.992135401; E2:
 0.999938148.
                                             WSC17 10-21 Dec.2012




        RESULTS & DISCUSSION

Our results are similar to the earlier findings of
 Sutrisno et al.(2009), who developed ANN models
 with backpropagation algorithm to predict
 mangosteen quality during storage at the most
 appropriate pre-storage conditions which
 performed the longest storage period.

In their experiments R2 was found close to 1
 (more than 0.99) for each parameter, indicating
 that the model was good to memorize data.
                                              WSC17 10-21 Dec.2012




        RESULTS & DISCUSSION

Fernandez et al.(2006) studied the weekly milk
 production in goat flocks and clustering of goat
 flocks by using self organizing maps for prediction,
 establishing the effectiveness of ANN modelling
 in animal science applications.

Another study showed that ANN modelling is a
 successful alternative to statistical regression
 analysis for predicting amino acid levels in feed
 ingredients (Cravener et al.,1999).
             WSC17 10-21 Dec.2012




CONCLUSION
                                            WSC17 10-21 Dec.2012




               CONCLUSION

The RBF-ANN models predicted the solubility
 index of roller dried goat whole milk powder with
 excellent    accuracy    with    coefficient of
 determination and Nash - Sutcliffe coefficient
 close to 1.

From the study, it is concluded that RBF-ANN
 models are a promising tool for predicting the
 solubility index of roller dried goat whole milk
 powder.
ThankYou

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:1
posted:6/24/2014
language:Unknown
pages:22