Deformation Energy Estimation of Cherry Tomato Based on Some Engineering Parameters Using Machine-Learning Algorithms

For the design and sizing of equipment and structures in agricultural operations concerning the cherry tomato industry, especially harvesting operations and postharvest operations of the crops, it is very important to determine their mechanical properties. In the study, mass, length, thickness, width, geometric diameter, sphericity, surface area, rupture force, firmness, Poisson's ratio, and modulus of elasticity were used as independent variables in the data set, and the dependent variable and deformation energy was estimated. Min-max normalization methods were used to increase the success and performance of the models. Three machine learning methods were utilized in the study, and statistical parameters, such as R-2, MAE, and MSE, were used to evaluate the performance of the methods. The R-2 of the artificial neural network (ANN), applied in the model as one of the machine learning methods, was found to be 96.8%, revealing the highest predictive power. Logistic regression with a 91.1% success rate, and decision tree regression with an 81.3% success rate, came second and third, respectively.

Automated summary

Determining the mechanical properties is crucial for the design and sizing of equipment and structures in agricultural operations, specifically in the cherry tomato industry regarding harvesting and postharvest operations. In this study, various independent variables such as mass, length, thickness, width, geometric diameter, sphericity, surface area, rupture force, firmness, Poisson's ratio, and modulus of elasticity were utilized, and their relationship with the dependent variable, deformation energy, was estimated. Min-max normalization methods were adopted to enhance the models' performance. Three machine learning methods were employed, and statistical parameters including R-2, MAE, and MSE were used to assess their performance. The artificial neural network (ANN) exhibited the highest predictive power with an R-2 of 96.8%. Logistic regression achieved a success rate of 91.1%, followed by decision tree regression with a success rate of 81.3%.