Optimization of computational intelligence approach for the prediction of glutinous rice dehydration

BACKGROUND

Five computational intelligence approaches, namely Gaussian process regression (GPR), artificial neural network (ANN), decision tree (DT), ensemble of trees (EoT) and support vector machine (SVM), were used to describe the evolution of moisture during the dehydration process of glutinous rice. The hyperparameters of the models were optimized with three strategies: Bayesian optimization, grid search and random search. To understand the parameters that facilitate intelligence model adaptation to the dehydration process, global sensitivity analysis (GSA) was used to compute the impact of the input variables on the model output.

RESULT

The result shows that the optimum computational intelligence techniques include the 3-9-1 topology trained with Bayesian regulation function for ANN, Gaussian kernel function for SVM, Matérn covariance function combined with zero mean function for GPR, boosting method for EoT and 4 minimum leaf size for DT. GPR has the highest performance with R2 of 100% and 99.71% during calibration and testing of the model, respectively. GSA reveals that all the models significantly rely on the variation in time as the main factor that affects the model outputs.

CONCLUSION

Therefore, the computational intelligence models, especially GPR, can be applied for an effective description of moisture evolution during small-scale and industrial dehydration of glutinous rice. © 2024 Society of Chemical Industry.

Recent Advances in the Drying Process of Grains

Grain drying is a vital operation in preparing finished grain products such as flour, drinks, confectioneries and infant food. The grain drying kinetics is governed by the heat and mass transfer process between the grain and the environment. Incomplete, improper and over-drying are crucial to the grain quality and negatively influence the acceptance of the grain by the consumers. Dried grain moisture content is a critical factor for developing grain drying systems and selecting optimal performance by researchers and the grain processing industry. Many grain drying technologies such as fluidised bed dryers, fixed bed dryers, infrared dryers, microwave dryers, vacuum dryers and freeze dryers have been used in recent years. To improve the drying process of grain, researchers have combined some drying technologies such as microwave + hot air, infrared + hot air and microwave + a fluidised bed dryer. Also, they introduce some treatments such as ultrasound dielectric and dehumidification. These methods enhance the dryer performance, such as higher moisture removal, reduced processing time, higher energy efficiency and nutrient retention. Therefore, this review focused on the drying conditions, time, energy consumption, nutrient retention and cost associated with the reduction of moisture content in grain to a suitable safe level for further processing and storage.

Application of Artificial Neural Networks, Support Vector, Adaptive Neuro-Fuzzy Inference Systems for the Moisture Ratio of Parboiled Hulls

Drying as an effective method for preservation of crop products is affected by various conditions and to obtain optimum drying conditions it is needed to be evaluated using modeling techniques. In this study, an adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and support vector regression (SVR) was used for modeling the infrared-hot air (IR-HA) drying kinetics of parboiled hull. The ANFIS, ANN, and SVR were fed with 3 inputs of drying time (0–80 min), drying temperature (40, 50, and 60 °C), and two levels of IR power (0.32 and 0.49 W/cm2) for the prediction of moisture ratio (MR). After applying different models, several performance prediction indices, i.e., correlation coefficient (R2), mean square error index (MSE), and mean absolute error (MAE) were examined to select the best prediction and evaluation model. The results disclosed that higher inlet air temperature and IR power reduced the drying time. MSE values for the ANN, ANFIS tests, and SVR training were 0.0059, 0.0036, and 0.0004, respectively. These results indicate the high-performance capacity of machine learning methods and artificial intelligence to predict the MR in the drying process. According to the results obtained from the comparison of the three models, the SVR method showed better performance than the ANN and ANFIS methods due to its higher R2 and lower MSE.