Artificial Neural Network (ANN) Implementation with Conjugate Gradient Algorithm to Predict Sumatran Melinjo Plant Production

Abstract

Melinjo is an annual plant with open seeds. Tree-shaped and has two houses called dioecious or there are males and females. Melinjo is often found in dry and tropical areas. Indonesia can be one that produces melinjo as a trade product in large quantities. Melinjo is collected and shipped natural products after 5-6 long time after sowing of seeds. In West Sumatra, it is detailed that each year produces 20,000 to 25,000 natural melinjo products and the seed generation reaches 80 to 100 kg per tree per year. Therefore, it is important to know every need for melinjo by anticipating the number of generations of Melinjo using a Manufacturing Artificial Neural System with Backpropagation strategy. With the neural structure made, it will be easier to carry out this investigation. Where the machine learning method can help to find the best performance value and value from the simple data studied. The Matlab2011b application has a feature that helps to calculate the best performance and value with the help of the Conjugate Gradient algorithm. After testing using 5 samples, namely: 4-10-1, 4-15-1, 4-20-1,4-25-1, 4-30-1. Of the five tests, the best results are on data 4-15-1 with the MSE/Performance value of 0.011154591. 4-15-1, 4-20-1,4-25-1, 4-30-1. Of the five tests, the best results are on data 4-15-1 with the MSE/Performance value of 0.011154591. 4-15-1, 4-20-1,4-25-1, 4-30-1. Of the five tests, the best results are on data 4- 15-1 with the MSE/Performance value of 0.011154591.