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.
Other subject about saffron
mehdi Bashiri; Ali Maroosi; Amir Salari; Mohammad Ghodoosi
Abstract
Yield prediction for agricultural crops plays an important role in export-import planning, purchase guarantees, pricing, secure profits and increasing in agricultural productivity. Crop yield is affected by several parameters especially climate. In this study, the saffron yield in the Khorasan-Razavi ...
Read More
Yield prediction for agricultural crops plays an important role in export-import planning, purchase guarantees, pricing, secure profits and increasing in agricultural productivity. Crop yield is affected by several parameters especially climate. In this study, the saffron yield in the Khorasan-Razavi province was evaluated by different classification algorithms including artificial neural networks, regression models, local linear trees, decision trees, discriminant analysis, random forest, support vector machine and nearest neighbor analysis. These algorithms analyzed data for 20 years (1989-2009) including 11 climatological parameters. The results showed that a few numbers of climatological parameters affect the saffron yield. The minimum, mean and maximum of temperature, had the highest positive correlations and the relative humidity of 6.5h, sunny hours, relative humidity of 18.5h, evaporation, relative humidity of 12.5h and absolute humidity had the highest negative correlations with saffron cultivation areas, respectively. In addition, in classification of saffron cultivation areas, the discriminant analysis and support vector machine had higher accuracies. The correlation between saffron cultivation area and saffron yield values was relatively high (r=0.38). The nearest neighbor analysis had the best prediction accuracy for classification of cultivation areas. For this algorithm the coefficients of determination were 1 and 0.944 for training and testing stages, respectively. However, the algorithms accuracy for prediction of crop yield from climatological parameters was low (the average coefficients of determination equal to 0.48 and 0.05 for training and testing stages). The best algorithm i.e. nearest neighbor analysis had coefficients of determination equal to 1 and 0.177 for saffron yield prediction. Results showed that, using climatological parameters and data mining algorithms can classify cultivation areas. By this way it is possible to identify areas that have similar climate to prone areas and recognize suitable areas for cultivation.
