Prediction Model of Loan Support Limit of Plows and Rotavators Used in South Korea by Regression Analysis

• Published in: Journal of Biosystems Engineering, 47(3) Vol. 47; no. 3; pp. 409 - 416
• Main Authors: Hwang, Seok-Joon, Kim, Jeong-Hun, Jang, Moon-Kyeong, Nam, Ju-Seok
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.09.2022; 한국농업기계학회
• Subjects: Agriculture; Control; Engineering; Environmental Engineering/Biotechnology; Mechatronics; Original Article; Robotics; 농학; Loan support limit; Rotavator; Plow; Power required; Regression analysis
• ISSN: 1738-1266; 2234-1862
• DOI: 10.1007/s42853-022-00154-w

Purpose This study predicts the loan support limit using main variables of plows and rotavators by regression analysis. Methods The study collected and analyzed the data on loan support limit, rotary tilling width, the power required, and the number of rotary blades from 360 units of commercial rotavators in South Korea. Additionally, loan support limit, plowing width, the power required, and weight were investigated for 80 units of plows commercially available in South Korea. Simple and multiple linear regression analyses were conducted to examine the effect of variables on the loan support limit. Results Simple and multiple regression models for the prediction of the loan support limit of plows and rotavators were developed. The coefficient of determination ( R 2 ) and root mean square error (RMSE) were derived to evaluate the accuracy of each regression model. In the case of plows, the R 2 and RMSE of the weight-based simple regression model showed the highest performance of prediction for the loan support limit, followed by the models based on power required and plowing width variables. In the case of rotavators, R 2 and RMSE of a simple regression model based on rotary tilling width showed the highest prediction accuracy of loan support limit, followed by the models based on power required and the number of rotary blades variables. Conclusions For plows and rotavators, multiple regression models have a higher R 2 and a smaller RMSE compared to the simple regression models, demonstrating their adequacy for the prediction of the loan support limit. The developed prediction model can be helpful to save time and make a suitable decision for farmers to purchase tractor implements.