IMPLEMENTASI ALGORITMA CONVOLUTIONAL NEURAL NETWORK UNTUK DETEKSI PENYAKIT TANAMAN APEL BERDASARKAN CITRA DIGITAL

Apples are a fruit that is popular with many people. Apart from its taste, apples also contain lots of nutrients and can prevent the risk of chronic disease. Apples are a plant that develops in subtropical areas and have been cultivated since 1934. Apples can grow well and produce good fruit in highland areas. One of the apple production centers in Indonesia is Batu City and Poncokusumo, Kab. Poor. Convolutional Neural Network in this chapter will discuss the results and analysis of the Convolutional Neural Network (CNN) architecture or model and prediction results using the CNN algorithm. In architecture analysis or the CNN model consists of the weight and bias values used. The weight and bias values used are the last epoch values of the CNN model. After analyzing the weight and bias values, an analysis of the prediction results, accuracy graphs and losses graphs will be carried out. The program can work well and can detect apple plant diseases. The amount of data used is 1200 images of apple plants. Next, the data will be divided into 2, namely training data of 70% of the data or 840 and 30% of the validation data or 360. The test results show an accuracy level of 85.83% of the 360 validation data.