• Journal of the Korea Society of Computer and Information
• /
• v.29 no.11
• /
• pp.113-118
• /
• 2024

This paper proposes an optimized fruit set prediction model for cucumbers using an AI-based automatic growth control system. Based on data collected from experimental farms at Sunchon National University and Suncheon Bay cucumber farms, we constructed and compared the performance of models using three machine learning algorithms: Random Forest, XGBoost, and LightGBM. The models were trained using 19 environmental and growth-related variables, including temperature, humidity, and CO2 concentration. The LightGBM model showed the best performance (RMSE: 1.9803, R-squared: 0.5891). However, all models had R-squared values below 0.6, indicating limitations in capturing data nonlinearity and temporal dependencies. The study identified key factors influencing cucumber fruit set prediction through feature importance analysis. Future research should focus on collecting additional data, applying complex feature engineering, introducing time series analysis techniques, and considering data augmentation and normalization to improve model performance. This study contributes to the practical application of smart farm technology and the development of data-driven agricultural decision support systems.