DETEKSI KEPITING MOLTING MENGGUNAKAN TEKNIK KLASIFIKASI MACHINE LEARNING

Abstract

Soft crab is an export product where foreign demand is much higher than production. In the production of soft crabs, it is done by keeping the crabs individually in a crab box which is placed in the pond until they molt. Molting is a natural process of molting, i.e. removing the old tough skin for growth purposes. Shortly after molting, the new crab shells are still very soft and will harden again after water absorption occurs. Therefore it is important to monitor molting crabs to help farmers in the cultivation of soft shell crabs. The number of crab datasets is 1060 which consists of 1000 training data and 60 testing data. There are several popular image classification algorithms, namely K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest Classifier (RFC). KNN, SVM, and RFC are classification algorithms from Machine Learning. This study aims to compare the performance of the three algorithms so that the performance of the three algorithms is known. Several parameters are used to configure the KNN, SVM, and RFC algorithms. From the results of the trials conducted, KNN has the best performance with 98.33% accuracy, 98.33% precision, 98.38% recall, and 98.38% F1 Score.