Development of artificial intelligence based systems for prediction of hydration characteristics of wheat

• Published in: Computers and electronics in agriculture Vol. 128; pp. 34 - 45
• Main Authors: Shafaei, S.M., Nourmohamadi-Moghadami, A., Kamgar, S.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2016
• Subjects: Adaptive neuro-fuzzy inference system; Adaptive systems; Artificial neural network; Artificial neural networks; Computer simulation; Hydration; Hydration rate; Learning theory; Mathematical models; Moisture content; Moisture ratio; Neural networks; Artificial neural network; Adaptive neuro-fuzzy inference system; Moisture ratio; Moisture content; Hydration rate
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2016.08.014

[Display omitted] •Three ANFIS models were developed to simulate hydration characteristics of wheat.•The results of ANFIS models were compared with those of ANN model.•Both ANFIS and ANN were able to accurately predict hydration characteristics.•An ANN simulation framework was preferred to three ANFIS simulation frameworks. Hydration characteristics (moisture content, moisture ratio and hydration rate) of wheat kernel during soaking process were studied and simulated. Hydration procedure was performed at five different experimental water temperatures (30, 40, 50, 60 and 70 (°C)) with respect to hydration time changes. Hydration characteristics of samples were modeled using one of the most popular simulation frameworks of artificial intelligence, adaptive neuro-fuzzy inference system (ANFIS). A comparison was also made between results of the best developed ANFIS model and those of the another well-known artificial intelligence technique, artificial neural network (ANN). The hydration temperature and time were used as input parameters and moisture content, moisture ratio and hydration rate were taken as output parameters of the intelligent modeling frameworks. To attain the best model with the highest predictive ability, developed models were compared based on statistical parameters of coefficient of determination, root mean square error and mean relative deviation modulus. According to the results, although the best framework of both ANFIS and ANN were able to accurately predict hydration characteristics, the best ANN simulation framework with a simple structure (2–4–3) was easier to use than the ANFIS with three different structures. ANN surface plots also illustrated that increasing the hydration temperature and time increased moisture content and decreased moisture ratio. Moreover, ANN modeling results indicated that the hydration rate increased in the initial and decreased in the middle and final phase of hydration procedure.