Application of Firefly Algorithm for Optimizing Backpropagation Method in Identifying Types of Rice Plant Diseases

Abstract

Rice is the main food source for Indonesians, with consumption continuing to increase in line with population growth. To meet this growing demand, the use of modern technology is important to increase rice production. However, rice plants are highly susceptible to various diseases that can reduce yields and lower the quality of rice crops. Diseases such as leaf blight, blast, leaf rot, brown spot, stripe spot, and tungro are threats to rice productivity, requiring rapid and accurate prevention. This study applies a classification system to detect diseases in rice plants using an artificial neural network (ANN) with the Backpropagation method. Backpropagation, although effective, has weaknesses, such as long convergence time and sensitivity to initial weight values, which often cause the model to get stuck at local minimum values, thereby reducing its overall performance. To overcome these weaknesses, the Firefly Algorithm (FA) is used as an optimization technique to improve the performance of Backpropagation. The results show that the use of the Backpropagation method produces an accuracy of 43%. However, when combined with the Firefly Algorithm (BPP-FA), the accuracy increases significantly, producing a value of 90%. This increase shows that BPP-FA improves accuracy in detecting diseases in rice plants. This combination of methods is expected to provide a reliable and efficient solution for detecting diseases in rice plants, thereby improving the quality and productivity of rice cultivation.

Plant phenotyping relevance

イネ病害を対象に、BackpropagationとFirefly Algorithmを組み合わせた分類手法を開発・比較し、病害検出精度を評価している。植物の病害状態を観測から推定する計算手法が研究の中心である。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.