Artificial Neural Network Approach for the Identification of Clove Buds Origin Based on Metabolites Composition

Abstract

This paper examines the use of an artificial neural network approach in identifying the origin of clove buds based on metabolites composition. Generally, large data sets are critical for an accurate identification. Machine learning with large data sets lead to a precise identification based on origins. However, clove buds uses small data sets due to the lack of metabolites composition and their high cost of extraction. The results show that backpropagation and resilient propagation with one and two hidden layers identifies the clove buds origin accurately. The backpropagation with one hidden layer offers 99.91% and 99.47% for training and testing data sets, respectively. The resilient propagation with two hidden layers offers 99.96% and 97.89% accuracy for training and testing data sets, respectively.

Modified Possibilistic Fuzzy C-Means Algorithm for Clustering Incomplete Data Sets

“…The evaluation is based on three aspects, the percentage accuracy, the number of iterations, and centroid errors. The formula used to calculate the percentage accuracy is as follows [19].…”

“…To obtain the optimal number of clusters in a complete data set, we use a cluster validity index. The cluster validity index used is the Xie-Beni index shown in Equation (12). A validity index is a measure used to determine the optimal number of clusters.…”

“…The performance of OCSPFCM and NPSPFCM algorithms in clustering incomplete data sets are evaluated in three ways: the percentage accuracy of each data point being on the correct cluster member, number of iterations to termination, and centroid errors. The formula used to calculate the percentage of accuracy is as follows [12].…”

“…In the artificial data sets II, evaluations related to the percentage of accuracy, the number of iterations, and the centroid errors of the OCSPFCM and NPSPFCM algorithms are respectively shown in Figures 11,12,and 13. Figure 11 shows the average of accuracy percentage in the OCSPFCM and NPSPFCM algorithms in the artificial data sets II. Both algorithms provide accuracy percentages above 95% for all missing values percentage levels, which is an accurate value.…”

Assessment of the effectiveness of lubrication of Ti-6Al-4V titanium alloy sheets using radial basis function neural networks

“…The mathematical models allow to explore mechanisms relating controllable input variables to observed outputs. ANNs are a tool enabling the building of linear and nonlinear models that solve complex classification and regression tasks [26,27]. One of the basic advantages of neural networks is the fact that as a result of the learning process, the network can acquire the ability to predict output signals based on the observation of the training set.…”