발간년도 : [2023]
| 논문정보 |
|
| 논문명(한글) |
[Vol.18, No.6] A Study on the Comparison of Optimal Growth Models for Melon Harvest and Size Prediction |
|
| 논문투고자 |
Sang-Min Lim, Soo-Ho Jung, Meong-Hun Lee |
|
| 논문내용 |
Improving crop productivity and providing food security are currently emerging as important topicsaround the world. Among these, melon is a fruit loved by many consumers around the world, andpredictions of its production and quality have great significance in the agricultural field. In particular,accurately predicting melon growth is an important factor in increasing agricultural economics andproductivity. The purpose of this study is to utilize various machine learning techniques to accuratelypredict melon growth. The study was conducted based on melon growth and greenhouse environmentdata provided by the Jeollanam-do Agricultural Research and Extension Services. Initial data wascollected in minutes, which were preprocessed and converted to daily averages. Additionally, becausegrowth data were not measured at regular intervals, linear interpolation was used to fill in missingvalues. After completing data preprocessing and feature selection, learning was conducted using LinearRegression, Random Forest, XGBoost, LSTM, and GRU among several machine learning models. Theperformance of each model was evaluated by MSE and R² values. As a result, the random forest modelshowed the best performance. The brute-force method was used to select the optimal parameters for thismodel, and the MSE value of the random forest model using the optimal parameters derived throughthis was 2.33, showing high prediction accuracy. The results of this study are expected to significantlyimprove agricultural efficiency and productivity, and in the future, we plan to conduct research tofurther improve the accuracy of the prediction model by including more diverse variables and utilizingmore data. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
