<![CDATA[This article discusses the comparative analysis of activation functions in Convolutional Neural Network (CNN) for clustering rice types based on rice quality. Two activation functions tested are LogSoftmax and Softmax. Through data collection and CNN architecture implementation, we trained and evaluated the models using evaluation metrics such as accuracy, precision, recall, and F1 score. The results show significant differences in model performance based on the activation function used. These findings provide practical guidance for the food industry in selecting the optimal activation function for clustering rice types. The test results also indicate that the highest accuracy of 0.9787 or 97.87% was achieved with the LogSoftmax activation function architecture model, with the highest precision, recall, and F1 score. On the other hand, the Softmax activation function achieved an accuracy of 0.9286 or 92.86%.]]>
Copyrights © 2023
