| dc.contributor.author |
Parmar, RS |
en |
| dc.contributor.author |
McClendon, RW |
en |
| dc.contributor.author |
Hoogenboom, G |
en |
| dc.contributor.author |
Blankenship, PD |
en |
| dc.contributor.author |
Cole, RJ |
en |
| dc.contributor.author |
Dorner, JW |
en |
| dc.date.accessioned |
2014-06-06T06:43:14Z |
|
| dc.date.available |
2014-06-06T06:43:14Z |
|
| dc.date.issued |
1997 |
en |
| dc.identifier.issn |
00012351 |
en |
| dc.identifier.uri |
http://62.217.125.90/xmlui/handle/123456789/1118 |
|
| dc.relation.uri |
http://www.scopus.com/inward/record.url?eid=2-s2.0-0031147928&partnerID=40&md5=f1681e3364b2d8a38a7a27766d35ebb6 |
en |
| dc.subject |
Aflatoxin |
en |
| dc.subject |
Neural network |
en |
| dc.subject |
Peanuts |
en |
| dc.subject.other |
Accumulated heat units |
en |
| dc.subject.other |
Crop age |
en |
| dc.subject.other |
Drought duration |
en |
| dc.subject.other |
Preharvest peanuts |
en |
| dc.subject.other |
Soil temperature |
en |
| dc.subject.other |
Aflatoxins |
en |
| dc.subject.other |
Backpropagation |
en |
| dc.subject.other |
Contamination |
en |
| dc.subject.other |
Grain (agricultural product) |
en |
| dc.subject.other |
Mathematical models |
en |
| dc.subject.other |
Regression analysis |
en |
| dc.subject.other |
Temperature |
en |
| dc.subject.other |
Neural networks |
en |
| dc.subject.other |
Arachis hypogaea |
en |
| dc.title |
Estimation of aflatoxin contamination in preharvest peanuts using neural networks |
en |
| heal.type |
journalArticle |
en |
| heal.publicationDate |
1997 |
en |
| heal.abstract |
The prevention and elimination of aflatoxin contamination of preharvest peanuts requires the identification of the factors involved in the contamination process and the evaluation of the effects of those factors on contamination levels. The objectives of our study were to examine the variables that affect the contamination process and to develop a model to estimate contamination levels. Artificial neural networks and linear regression models were identified as appropriate techniques to model the contamination levels. Seven years of preharvest peanut aflatoxin data were used to develop and evaluate the models. The data were randomly divided into a training set and a test set for the artificial neural network model. Artificial neural networks were developed using various network architectures and combinations of variables as network inputs. The inputs considered were: soil temperature, drought duration, crop age, and accumulated heat units. The accumulated heat units were computed based on threshold soil temperatures ranging from 23 to 29°C. The backpropagation algorithm with a logistic activation function for hidden and output nodes and three layers of nodes were selected as the internal neural network parameters. The most accurate results with the artificial neural network were achieved when the threshold soil temperature to compute accumulated heat units was set to 25°C and all four variables were included as inputs in a network with eight hidden nodes. The R2-values for the training and the test sets were 0.9250 and 0.9522, respectively. Stepwise linear regression was also applied to develop a regression model for estimating aflatoxin values. The regression model was developed and evaluated for the same data sets used for the development and evaluation of the neural network model. The highest R2-values of 0.822 and 0.809 for the training and test sets, respectively, were achieved with the regression model when all four variables were selected as input factors and accumulated heat units were computed using a threshold temperature of 29°C. This study showed that artificial neural networks can be used to estimate aflatoxin contamination in peanuts. The artificial neural networks also performed better than traditional stepwise linear regression techniques.The prevention and elimination of aflatoxin contamination of preharvest peanuts requires the identification of the factors involved in the contamination process and the evaluation of the effects of those factors on contamination levels. This paper examines the variables that affect the contamination process and develops a model to estimate contamination levels. Artificial neural networks and linear regression model are identified as appropriate methods to model the contamination levels. Seven years of preharvest peanut aflatoxin data are used to developed and evaluate the models. Results show that artificial neural networks can be used to estimate aflatoxin contamination in peanuts. The artificial neural networks also performed better than traditional stepwise linear regression techniques. |
en |
| heal.journalName |
Transactions of the American Society of Agricultural Engineers |
en |
| dc.identifier.issue |
3 |
en |
| dc.identifier.volume |
40 |
en |
| dc.identifier.spage |
809 |
en |
| dc.identifier.epage |
813 |
en |