PENERAPAN JARINGAN SARAF TIRUAN DENGAN ALGORITMA PERCEPTRON PADA DETEKSI PENYAKIT BAWANG MERAH

Abstract

This research focuses on advances in the onion (Allium ascalonicum) disease detection system using Artificial Neural Networks (ANN) with the Perceptron Algorithm. Onions are an important horticultural commodity with substantial economic importance in Indonesia. However, shallot production is often hampered by various diseases that can cause significant losses. Timely identification and effective management of the disease is essential to reduce its adverse effects. Expert systems that utilize artificial intelligence, especially ANN, have proven effective in plant disease detection. ANN imitates the way the human brain works in recognizing patterns and making decisions based on the data obtained. This study used data on onion disease symptoms which consisted of 13 symptoms and 7 types of disease. Each symptom and disease is connected in a knowledge base which is then analyzed using the Perceptron Algorithm. Perceptron is a supervised learning algorithm used for classification and pattern recognition. The training process involves initializing weights and biases, calculating output responses, and adjusting weights if errors occur. The final result of this system is the identification of the type of disease that attacks shallots based on the symptoms observed. The implementation of this system includes a home display, diagnostic display, and diagnostic results display. This system allows users to diagnose shallot diseases by answering questions related to the symptoms observed. The diagnosis results will display the type of disease and the recommended solution. This research shows that the Perceptron algorithm can be applied effectively in shallot disease detection systems, helping farmers identify and manage diseases more quickly and accurately.