Optimization of EC Values of Nutrient Solution for Tomato Fruits Quality in Hydroponics System Using Artificial Neural Network and Genetic Algorithms
DOI:
https://doi.org/10.5614/itbj.sci.2009.41.1.3Abstract
Total soluble solids (TSS) and fruit fresh weight are two indicators to show the quality of tomato fruits. To gain high values of TSS and fruit fresh weight, it is important to consider the concentration of nutrient solution, which is commonly represented by Electrical Conductivity (EC) value. Generally, the increasing of EC value not only increases the number of TSS, but also decreases fruit fresh weight. Therefore, it is important to optimize the EC value for both indicators of quality of tomato fruits. The objective of this research is to optimize the EC value of nutrient solution on each generative stage using Artificial Neural Network (ANN) and Genetic Algorithms (GA). ANN was used to identify the relationship between different EC value treatments with TSS value and fruit fresh weight. GA was applied to determine the optimal EC value in generative growth, which is divided into three stages. Results showed that the optimal EC values in the flowering stage, the fruiting stage and the harvesting stage were 1.4 mS/cm, 10.2 mS/cm and 9.7 mS/cm, respectively.References
Adams, P. & Ho, L.C., Effect of constant and fluctuating salinity on yield, quality and calcium status of tomatoes, J. Hort. Sci., 64, pp. 725732, 1989.
Adams, P., Effect of increasing the salinity of the nutrient solution with major nutrients or sodium chloride on the yield, quality and composition of tomatoes grown in rockwool, J. Hort. Sci., 66, pp. 201 - 207, 1991.
Sanchez, A. R, RomeroAranda, R., Cuartero, J., Plant water uptake and water use efficiency of greenhouse tomato cultivars irrigated with saline water, Agric. Water Management, 78, pp. 5466, 2005.
Saito, T., Fukuda, Naoya & Nishimura, Shigeo, Effect of Salinity Treatment Duration and Planting Density on Size and Sugar Content of Hydroponically Grown Tomato Fruits. Journal Japan, Soc. Hort. Sci., 75 (5), pp. 392398, 2006.
Li, Y. L., Stanghellini, C. & Challa, H., Effect of electrical conductivity and transpiration on production of greenhouse tomato (Lycopersicum esculentum L.), Sci. Hort, 88, pp. 1129, 2001.
Whipker, B. E. & Cavins, Todd J., Electrical Conductivity (EC): Unit and Conversions, NCSU Floriculture Research Report 002. http://www.ces.ncsu.edu/depts/hort/floriculture/Florex/EC%20Conversion.pdf. December 2000.
Hashimoto, Y., Application artificial neural network and genetic algorithms to agricultural systems, Computer and Electronics in Agriculture, (18), pp. 7172, 1997.
Purwar, S.I.N. Kar & Jha, A.N., Online system identification of complex system using Chebyshev neural networks, Applied Soft Computing, (7), pp. 364372, 2007.
Nugroho, A. Satrio, Information Analysis Using Soft Computing - The Applications to Character Recognition, Meteorological Prediction and Bioinformatic Problems, PhD Dissertation, Nagoya Institute of Technology, Nagoya, Japan, pp. 12, 2003.
Goldberg, D.E., Genetic Algorithms in Search, Optimization, and Machine Learning, AddisonWesley, Reading, Massachusetts, pp. 412, 1989.
Morimoto, T., Purwanto, W., Suzuki, J. & Hashimoto, Y., Optimization of heat treatment for fruit during storage using neural network and genetic algorithms, Computers and electronics in agriculture, (19), pp. 87 - 101, 1997.
Linker, R, & Seginer, I. & Gutman, P.O., Optimal CO2 control in a greenhouse modeled with neural networks, Computers and electronics in agriculture, (19), pp. 289310, 1998.
Kondo, N., Ahmad, Usman, Monta, Mitsuji & Murase, Haruhiko, Machine vision based quality evaluation of Iyokan orange fruit using neural networks, Computers and electronics in agriculture, (29), 135147, 2000.
Qiao, J, Wang, N., Ngadi, M.O. & Kazemi, S., Predicting mechanical properties of fried chicken nuggets using image processing and neural network technique, Journal of Food Engineering, (79), pp. 1065 - 1070, 2007.
Kros, John F., Lin, Mike & L. Brown, Marvin, Effect of neural network sSigmoid function on KDD in the presence of imprecise data, Computer & Operation Research, (33), 31363149, 2006.
Morimoto, T. & Y. Hashimoto, AI approaches to identification and control of total plant production systems, Control Engineering Practice, (8), 555567, 2000.
Ehret, D. & Ho, L.C., Effects of osmotic potential in nutrient solution on diurnal growth of tomato fruit, Journal of Experimental Botany 37(182), pp. 12941302, 1986.
