Artificial Neural Network Topology Optimization using K-Fold Cross Validation for Spray Drying of Coconut Milk

Abstract

In this study, the development of an optimized topology neural network model for spray drying coconut milk is investigated using K-fold cross validation technique. Performance between standalone ANN and ANN with K-fold cross validation is compared, as K-fold cross validation method is integrated into neural network to overcome the limitations of restricted dataset. With inlet temperature (140 °C-180 °C), concentration of maltodextrin and sodium caseinate (0 w/w %- 10w/w %) are established as the input parameters, while moisture content (3.64%-5.1%), outlet temperature (76.5 °C-104.5 °C) and surface free fat percentage (0.35%-34.51%) are the output parameters for the neural network. Experimental data from the spray drying process is used to develop the neural network. Selection from the best training algorithm (gradient descent backpropagation, gradient descent with momentum, resilience backpropagation, conjugate gradient backpropagation with Polak-Riebre restarts, conjugate gradient backpropagation with Fletcher-Reeves, scaled conjugate gradient, Broyden-Flectcher-Goldfard-Shanno backpropagation algorithm and Levenberg-Marquardt backpropagation), transfer function (tansig, logsig, purelin and satlin), number of training runs (1000-5000), number of hidden layers (1-3) and nodes (5-15) have significant effect on the performance of the ANN models based on the lowest MSE values and R2 values. Overall, the optimum topology ANN model with k-fold cross validation outperformed the recorded lowest MSE value of 0.064 and highest R2 value of 0.855 compared to the optimum standalone ANN model with MSE value of 0.082 and R2 value of 0.832. The optimum ANN with K-fold cross validation implements the Levenberg-Marquart training algorithm with hyperbolic tangent sigmoid transfer function using 4500 times training runs with optimal topology configuration of 3-8-2-3. Result concludes that the developed neural network using K-fold cross validation represents the spray drying process as a highly reliable model with high degree of accuracy.

Mathematical Modeling Using ANN Based on k-fold Cross Validation Approach and MOAHA Multi-Objective Optimization Algorithm During Turning of Polyoxymethylene POM-C

“…Therefore, in case of limited input data, it constitutes one of the best approaches. According to Ming et al [48], the ANN model with K-fold crossvalidation gives a better prediction result compared to the stand-alone ANN model.…”

An assisted decision-making tool for synchrotron beamline alignment based on neural networks

“…We split the original dataset into a test dataset and a training dataset at a ratio of 3/10 and 7/10. To make the best use of the data, we choose the K-fold cross-validation method [14,15] to train the ANN [16].…”

“…To take full advantage of the limited dataset, the K-fold cross-validation technique was chosen when training the neural network (see figure 5). When training a network with K-fold crossvalidation [14,15], the test set is each k fold of the dataset, and the training set is the remaining (k-1) folds. Therefore, in the process of training the network, k times of training and verification…”

Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk

“…PSO optimization techniques were integrated into the ANN to determine the optimum weights in the neural network design using MATLAB version 2019a. Lastly, the developed PSO-ANN was compared with external ANN [27] and GA-ANN [28] based on MSE and R 2 evaluation and supported with sensitivity analysis.…”

“…The ANN used is a multilayer perceptron (MLP) neural network with optimum configuration with a topology of 3-2-8-3, transfer function of logsig, and a Levenberg-Marquardt algorithm using K-Fold cross validation, which was established from research conducted by the previous authors [27]. Using normalized data, the optimal ANN design is determined using a selected network topology design, such as number of neurons (5)(6)(7)(8)(9)(10)(11)(12)(13)(14)(15), hidden neural layers (1-3), four different transfer functions, and seven training algorithms.…”