Synthetic Minority Oversampling Technique for Efforts to Improve Imbalanced Data in Classification of Lettuce Plant Diseases

Abstract

In this study we classified lettuce plant diseases. These plant diseases are available in the form of images that have been converted in .csv format to be classified. These plant diseases are available in the form of images that have been converted in .csv format to be classified. Image These plant diseases have been divided into several classes or categories. Then we determine the features of each row and column of the dataset.   Each line in the CSV file represents one image, and each column represents one feature Each line in the CSV file represents one image, and each column represents one feature. Then a label is made for each line in the CSV file, namely the class or category where the images are grouped. Thus, so that we get datasets that are ready to be processed with machine learning. However, in processing the dataset, we get imbalanced data. So we added the Synthetic Minority Over-sampling Technique (SMOTE) method to overcome the imbalance that occurs. So that the data can be classified using several algorithms to find the best accuracy.