Klasifikasi Kadar Kolesterol melalui Citra Iris Mata Menggunakan Convolutional Neural Network dengan Arsitektur InceptionV3

Abstract

The advancement of technology, there is an alternative to detecting cholesterol levels through pattern analysis of the iris, known as iridology. This method utilizes iris images processed using deep learning to detect patterns related to cholesterol levels. A popular algorithm in image classification today is the Convolutional Neural Network (CNN), with one of its commonly used architectures being Inception. This study evaluates the performance of InceptionV3 on iris data with and without the use of Contrast Limited Adaptive Histogram Equalization (CLAHE) technique, utilizing various epochs. The results show that the InceptionV3 architecture is capable of classification with the best accuracy reaching 94%, precision 94.3%, recall 93.9%, and F1-Score 94%. These results were obtained using 100 epochs, a batch size of 32, Adam optimizer, and a learning rate of 0.001 on data processed with CLAHE. Therefore, the use of CLAHE has been proven to improve the model's performance in classifying cholesterol levels through iris images.