Quantitative Assessment of Brix in Grafted Melon Cultivars: A Machine Learning and Regression-Based Approach

被引:0
作者
Ercan, Ugur [1 ]
Sonmez, Ilker [2 ]
Kabas, Aylin [3 ]
Kabas, Onder [4 ]
Zyambo, Busra Calik [2 ]
Golukcu, Muharrem [5 ]
Paraschiv, Gigel [6 ]
机构
[1] Akdeniz Univ, Dept Informat, TR-07070 Antalya, Turkiye
[2] Univ Akdeniz, Fac Agr, Dept Soil Sci & Plant Nutr, TR-07070 Antalya, Turkiye
[3] Akdeniz Univ, Manavgat Vocat Sch, Dept Organ Farming, TR-07070 Antalya, Turkiye
[4] Akdeniz Univ, Tech Sci Vocat Sch, Dept Machine, TR-07070 Antalya, Turkiye
[5] Bati Akdeniz Agr Res Inst, TR-07100 Antalya, Turkiye
[6] Natl Univ Sci & Technol POLITEHN Bucharest, Fac Biotech Engn, Dept Biotech Engn, Bucharest 060042, Romania
关键词
SVR; grafting; melon; Brix; FRUIT-QUALITY; SOLUBLE SOLIDS; PREDICTION; MUSKMELON; IMPACT; YIELD;
D O I
10.3390/foods13233858
中图分类号
TS2 [食品工业];
学科分类号
0832 ;
摘要
The article demonstrates the Brix content of melon fruits grafted with different varieties of rootstock using Support Vector Regression (SVR) and Multiple Linear Regression (MLR) model approaches. The analysis yielded primary fruit biochemical measurements on the following rootstocks, Sphinx, Albatros, and Dinero: nitrogen, phosphorus, potassium, calcium, and magnesium. Established models were evaluated with Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2) metrics. In the test section, the results of the MLR model were calculated as MAE: 0.0728, MAPE: 0.0117, MSE: 0.0088, RMSE: 0.0936, and R2: 0.9472, while the results of the SVR model were calculated as MAE: 0.0334, MAPE: 0.0054, MSE: 0.0016, RMSE: 0.0398, and R2: 0.9904. Despite both models performing well, the SVR model showed superior accuracy, outperforming MLR by 54% to 82% in terms of predictions. The relationships between Brix levels and various nutrients, such as sucrose, glucose, and fructose, were found to be strong, while titratable acidity had a minimal effect. SVR was found to be a more reliable, non-destructive method for melon quality assessment. These findings revealed the relationship between Brix and sugar levels on melon quality. The study highlights the potential of these machine learning models in optimizing the rootstock effect and managing melon cultivation to improve fruit quality.
引用
收藏
页数:16
相关论文
共 66 条
[1]  
Amaro A.L., 2015, Processing and Impact on Active Components in Food
[2]  
atalba Erdoan E.B., 2019, Masters Thesis
[3]  
Awad M., 2015, DIMACS Ser. Discrete. Math. Theor. Comput. Sci, P39, DOI [10.1007/978-1-4302-5990-9_4, DOI 10.1007/978-1-4302-5990-9]
[4]  
Bhimappa B.B., 2017, Veg. Sci, V44, P113, DOI [10.61180/4cf1s676, DOI 10.61180/4CF1S676]
[5]  
Bremner J. M., 1965, Monographs of the American Society of Agronomists, V9, P1149
[6]  
Brito L.T.L., 2000, Rev. Bras. Eng. Agrcola Ambient, V4, P19, DOI [10.1590/S1415-43662000000100004, DOI 10.1590/S1415-43662000000100004]
[7]   Machine Learning Regression Model for Predicting Honey Harvests [J].
Campbell, Tristan ;
Dixon, Kingsley W. ;
Dods, Kenneth ;
Fearns, Peter ;
Handcock, Rebecca .
AGRICULTURE-BASEL, 2020, 10 (04)
[8]  
Cemerolu B., 2010, Gda Analizleri, VVolume 34
[9]  
Chikh-Rouhou H., 2021, International Journal of Vegetable Science, V27, P3, DOI 10.1080/19315260.2019.1692268
[10]   Developing numerical equality to regional intensity-duration-frequency curves using evolutionary algorithms and multi-gene genetic programming [J].
Citakoglu, Hatice ;
Demir, Vahdettin .
ACTA GEOPHYSICA, 2023, 71 (01) :469-488