Klasifikasi Kecambah Mangrove Menggunakan Multi Layer Perceptron

Abstract

Data processing in the field of machine learning and its application to environment is still an interesting field until now. It is because there have been a lot of research related to computer science and agriculture especially mangroves, so there are still many research gaps that can be executed in the future. The long-term goal of this research is to apply machine learning techniques to the data and problem domains of mangrove plants. This study aims to obtain a classification of three classes of mangrove sprouts, namely: Avicennia Marina, Sonneratia Caseolaris and Ceriops Tagal, using the Multi Layer Perceptron (MLP) method, where MLP is one of the methods in the field of Machine Learning and Artificial Intelligence. The results of this study are using the number of neurons in the hidden layer more than the number of neurons in the input layer resulting in an optimal accuracy value at the 1000th epoch with an accuracy value of 97.7% for data testing, and an accuracy value of 99% for testing data. 

Keywords: Machine Learning, Classification, Mangrove Sprouts, Multi-Layer Perceptron.