Seyaed Ehsan Yasrebi; Iman Zabbah; Behnaz Behzadiyan; Ali Maroosi; Roya Rezaie
Abstract
Saffron is an important commercial good in Iran and it is important to pay attention to its mechanization from production to packaging. Upon arrival of the saffron to the laboratory's qualitative process, an initial assessment is carried out by an expert on the basis of the apparent features. However, ...
Read More
Saffron is an important commercial good in Iran and it is important to pay attention to its mechanization from production to packaging. Upon arrival of the saffron to the laboratory's qualitative process, an initial assessment is carried out by an expert on the basis of the apparent features. However, human error in determining the quality of saffron based on its apparent features is inevitable; use of artificial intelligence techniques can be effective in reducing human errors while mechanizing the system. It was a diagnostic study and its database consisted of 113 samples of saffron with 7 features, which were collected by the researchers on October 2016 from the valid laboratory of Saffron and under the supervision of an expert. Sample qualitative analysis was performed with the help of features in 4 different classes including excellent, good, average and second grade average. Artificial neural networks have been used to classify saffron. After analyzing and comparing the generated models using multilayer perceptron neural networks and learning vector neural network, the highest accuracy of classification on the training and testing samples was obtained with 75.93 and 75.75%, respectively. The accuracy obtained indicated that the multi-layer perceptron neural network model can be used as a decision maker by an expert or independently in saffron lab centers.
Hossien Riahi Modavar; Abbas Khashei-Siuki; Akram Seifi
Abstract
Because of saffron yield sensitivity and the effects of climate on its performance, and also due to the nonlinear nature of crop yield functions, the Artificial Neural Network (ANN) model is employed in this study for prediction and uncertainty analysis of saffron yield in the South Khorasan province ...
Read More
Because of saffron yield sensitivity and the effects of climate on its performance, and also due to the nonlinear nature of crop yield functions, the Artificial Neural Network (ANN) model is employed in this study for prediction and uncertainty analysis of saffron yield in the South Khorasan province based on 20 years of data. The input vector of the ANN model was optimized from 37 parameters through correlation and variance inflation. The optimum architecture of the model was derived as 1-2-4-11 with a sigmoidal activation function based on the results at three stages of training, testing and verification. The root mean square error (RMSE) and mean absolute error (MAE) were equal to 0.3 and 0.5 in the training step and 0.7 and 1 in the test step, respectively. These results indicate that the ANN is a suitable model for predicting saffron yield. Uncertainty analysis based on R2, d-factor and 95%PPU showed that despite use of inadequate data, model prediction showed acceptable prediction bounds and predicted a satisfactorily saffron yield trend. The R2 values were equal to 0.92 and 0.58 in the training and test steps, respectively, which are statistically significant at the P
