Prediction of supercritical extraction recovery of EGCG using hybrid of Adaptive Neuro-Fuzzy Inference System and mathematical model

Modeling of lime production process using artificial neural network

Lime is a significant material in many industrial processes, including steelmaking by blast furnace. Lime production through rotary kilns is a standard method in industries, yet it has depreciation, high energy consumption, and environmental pollution. A model of the lime production process can help to not only increase our knowledge and awareness but also can help reduce its disadvantages. This paper presents a black-box model by Artificial Neural Network (ANN) for the lime production process considering pre-heater, rotary kiln, and cooler parameters. To this end, actual data are collected from Zobahan Isfahan Steel Company, Iran, which consists of 746 data obtained in a duration of one year. The proposed model considers 23 input variables, predicting the amount of produced lime as an output variable. The ANN parameters such as number of hidden layers, number of neurons in each layer, activation functions, and training algorithm are optimized. Then, the sensitivity of the optimum model to the input variables is investigated. Top-three input variables are selected on the basis of one-group sensitivity analysis and their interactions are studied. Finally, an ANN model is developed considering the top-three most effective input variables. The mean square error of the proposed models with 23 and 3 inputs are equal to 0.000693 and 0.004061, respectively, which shows a high prediction capability of the two proposed models.

Supercritical Fluid Extraction Kinetics of Cherry Seed Oil: Kinetics Modeling and ANN Optimization

This study was primarily focused on the supercritical fluid extraction (SFE) of cherry seed oil and the optimization of the process using sequential extraction kinetics modeling and artificial neural networks (ANN). The SFE study was organized according to Box-Behnken design of experiment, with additional runs. Pressure, temperature and flow rate were chosen as independent variables. Five well known empirical kinetic models and three mass-transfer kinetics models based on the Sovová’s solution of SFE equations were successfully applied for kinetics modeling. The developed mass-transfer models exhibited better fit of experimental data, according to the calculated statistical tests (R², SSE and AARD). The initial slope of the SFE curve was evaluated as an output variable in the ANN optimization. The obtained results suggested that it is advisable to lead SFE process at an increased pressure and CO₂ flow rate with lower temperature and particle size values to reach a maximal initial slope.

Appraisal of adaptive neuro-fuzzy computing technique for estimating anti-obesity properties of a medicinal plant

This research examines the precision of an adaptive neuro-fuzzy computing technique in estimating the anti-obesity property of a potent medicinal plant in a clinical dietary intervention. Even though a number of mathematical functions such as SPSS analysis have been proposed for modeling the anti-obesity properties estimation in terms of reduction in body mass index (BMI), body fat percentage, and body weight loss, there are still disadvantages of the models like very demanding in terms of calculation time. Since it is a very crucial problem, in this paper a process was constructed which simulates the anti-obesity activities of caraway (Carum carvi) a traditional medicine on obese women with adaptive neuro-fuzzy inference (ANFIS) method. The ANFIS results are compared with the support vector regression (SVR) results using root-mean-square error (RMSE) and coefficient of determination (R(2)). The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ANFIS approach. The following statistical characteristics are obtained for BMI loss estimation: RMSE=0.032118 and R(2)=0.9964 in ANFIS testing and RMSE=0.47287 and R(2)=0.361 in SVR testing. For fat loss estimation: RMSE=0.23787 and R(2)=0.8599 in ANFIS testing and RMSE=0.32822 and R(2)=0.7814 in SVR testing. For weight loss estimation: RMSE=0.00000035601 and R(2)=1 in ANFIS testing and RMSE=0.17192 and R(2)=0.6607 in SVR testing. Because of that, it can be applied for practical purposes.