Classification is a way to group certain things, for example primate animals, based on the similarities and differences that exist in animals. This classification intends to identify similarities or characteristics in these animals. Image classification is the process of grouping an object in the form of an image into certain categories using the CNN algorithm, but the resulting accuracy level is not satisfactory. Therefore, this research aims to produce the right optimizer to be used in the CNN model. In this study, the data was collected using the web scrapping method, and the data source is Google Images, so the total amount of data obtained is 1631 images. The framework for completing this research is the AI Project Cycle, which includes problem scoping, data acquisition, data exploration, modelling, and evaluation. Based on the research results, the optimizer with the highest accuracy value is Adadelta, which has an accuracy value of 75%. Therefore, Adadelta is the right optimizer for primate classification in the CNN algorithm model.
Copyrights © 2024