A Convolutional Neural Network Algorithm for Pest Detection Using GoogleNet

• Published in: AgriEngineering Vol. 5; no. 4; pp. 2366 - 2380
• Main Authors: Yulita, Intan Nurma, Rambe, Muhamad Farid Ridho, Sholahuddin, Asep, Prabuwono, Anton Satria
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2023
• Subjects: Accuracy; Agriculture; Algorithms; Applications programs; Artificial intelligence; Artificial neural networks; Automation; Convolutional Neural Network; Corn; Crop yield; Crops; Deep learning; Experimental methods; Farmers; Farms; GoogLeNet; Identification; Language; Machine learning; mobile application; Mobile communications networks; Mobile computing; mobile telephones; Neural networks; Pest control; pest detection; pest identification; pest management; Pesticides; Pests; Smartphones; Software; Taiwan; Indonesia
• ISSN: 2624-7402; 2624-7402
• DOI: 10.3390/agriengineering5040145

The primary strategy for mitigating lost productivity entails promptly, accurately, and efficiently detecting plant pests. Although detection by humans can be useful in detecting certain pests, it is often slower compared to automated methods, such as machine learning. Hence, this study employs a Convolutional Neural Network (CNN) model, specifically GoogleNet, to detect pests within mobile applications. The technique of detection involves the input of images depicting plant pests, which are subsequently subjected to further processing. This study employed many experimental methods to determine the most effective model. The model exhibiting a 93.78% accuracy stands out as the most superior model within the scope of this investigation. The aforementioned model has been included in a smartphone application with the purpose of facilitating Indonesian farmers in the identification of pests affecting their crops. The implementation of an Indonesian language application is a contribution to this research. Using this local language makes it easier for Indonesian farmers to use it. The potential impact of this application on Indonesian farmers is anticipated to be significant. By enhancing pest identification capabilities, farmers may employ more suitable pest management strategies, leading to improved crop yields in the long run.