Abstract
Today the need for fruit consumption is increasing along with the increasing human population and awareness of the consumption of nutritious foods, apples are one of the most consumed fruits by humans worldwide. According to data quoted from the Indonesian National Statistics Center in 2021, apple production in 2021 decreased from the previous year from 519,531 tons to 509,544 tons. One of the causes of the decline in apple production is the presence of pests on the apple plant. At least there are several types of pests that can be identified on apple leaves, namely Apple Scrub (Venturia inaequalis), Apple Black Root (Botryosphaeria) and Apple Cedar/Rust (Gymnosporangium juniperi virginianae). The research stage begins with conducting several literature studies regarding related research, then formulating and validating the problem and starting to collect data from the Kaggle public dataset. Then in the experimental stage, the author divides the dataset into three parts with a percentage of 80% training data, 10% validation data and 10% testing data. The image classification method used is the Convolutional Neural Network (CNN) algorithm to create a model that can classify image data, the process of implementing the author uses the python programming language to build the model. The author conducted several experiments by making changes to several model parameters that affect the accuracy of the model. To evaluate the performance and accuracy of the model using a confusion matrix. The results of the study indicate that image size, data augmentation and the number of epochs greatly affect the accuracy of the model, from the test results the CNN model with the best accuracy is the model with the image size parameter 256x256, horizontal flip, vertical flip and random rotation data augmentation and the number of the 60th epoch has the highest accuracy rate of 99.66%. The results of this study are expected to be implemented in an application that can be used directly by farmers in detecting pests on apple plants quickly and accurately.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.