Optimisation of neural network topology for predicting moisture content of spray dried coconut milk powder
DOI:
https://doi.org/10.24191/mjcet.v5i2.15444Keywords:
Moisture content, Neural network, Spray drying process, Coconut milk, Network topologyAbstract
Moisture content is an important parameter to be controlled in an agricultural product to prevent rapid degradation and promote stabilisation of product and longer shelf life. There are various techniques on predicting the moisture content of spray dried powder that had been used by past researchers. In this study artificial neural network (ANN) is proposed to be used for its well-known benefits of simplicity and accuracy. The aim of this research is to evaluate the effect of hidden layer and hidden neuron in ANN in predicting moisture content of spray dried coconut milk. The effect of training algorithm, e.g., Gradient Descent (GD) back propagation and Levenberg-Marquart (LM) back propagation, and activation functions, e.g., hyperbolic tangent sigmoid [tansig] and log sigmoid (logsig) functions are also studied. Based on the result of correlation coefficient of determination (R2) value of 0.9951 and root mean square error (RMSE) value of 0.0145 that was used to evaluate the ANN performance, it can be concluded that the best ANN topology is 2-10-1 with Levenberg-Marquart for learning algorithm, and tangent sigmoid as activation function.
References
Abdullah, Z., Taip, F. S., Mustapa Kamal, S. M., & Abdul Rahman, R. Z. (2018). Effect of sodium caseinate concentration and sonication amplitude on the stability and physical characteristics of homogenized coconut milk. Journal of Food Processing and Preservation, 42(11), e13773. https://doi.org/10.1111/jfpp.13773
Abdullah, Z., Taip, F. S., Kamal, S. M. M., & Rahman, R. Z. A. (2020). Nonlinear model-based inferential control of moisture content of spray dried coconut milk. Foods, 9(9), 1177. https://doi.org/ 10.3390/foods9091177
Bhat, R., Alias, A. K., & Paliyath, G. (Eds.). (2012). Progress in food preservation. John Wiley & Sons. https://doi.org/ 10.1002/9781119962045
Brownlee, J. (2019). (2021, January 18). How to choose an activation function for deep learning. https://machinelearningmastery.com/choose-an-activation-function-for-deep-learning/
Doshi, S. (2019). (2019, January 13). Various optimization algorithms for training neural network. https://towardsdatascience.com/optimizers-for-training-neural-network-59450d71caf6
Kızrak, A. (2020). Comparison of activation functions for deep neural networks. https://towardsdatascience.com/comparison-of-activation-functions-for-deep-neural-networks-706ac4284c8a
Ming, J. L. K., Taip, F. S., Anuar, M. S., Noor, S. B. M., & Abdullah, Z. (2020). Artificial neural network topology optimization using k-fold cross validation for spray drying of coconut milk. IOP Conference Series: Materials Science and Engineering, 778, 012094. https://doi.org/ 10.1088/1757-899X/778/1/012094
Nazghelichi, T., Kianmehr, M. H., & Aghbashlo, M. (2011). Prediction of carrot cubes drying kinetics during fluidized bed drying by artificial neural network. Journal of Food Science and Technology, 48(5), 542–550. https://doi.org/10.1007/s13197-010-0166-2
Onu, C. E., Igbokwe, P. K., Nwabanne, J. T., Nwajinka, C. O., & Ohale, P. E. (2020). Evaluation of optimization techniques in predicting optimum moisture content reduction in drying potato slices. Artificial Intelligence in Agriculture, 4, 39–47. https://doi.org/ 10.1016/j.aiia.2020.04.001
Perazzini, H., Perazzini, M. T. B., Meili, L., Freire, F. B., & Freire, J. T. (2020). Artificial neural networks to model kinetics and energy efficiency in fixed, fluidized and vibro-fluidized bed dryers towards process optimization. Chemical Engineering and Processing-Process Intensification, 156, 108089. https://doi.org/10.1016/j.cep.2020.108089
Seow, C. C., & Gwee, C. N. (2003). Coconut milk: chemistry and technology. International Journal of Food Science & Technology, 32(3), 189–201. https://doi.org/ 10.1046/J.1365-2621.1997.00400.X
Sodeifian, G., Sajadian, S. A., & Ardestani, N. S. (2016). Evaluation of the response surface and hybrid artificial neural network-genetic algorithm methodologies to determine extraction yield of Ferulago angulata through supercritical fluid. Journal of the Taiwan Institute of Chemical Engineers, 60, 165–173. https://doi.org/10.1016/j.jtice.2015.11.003
Taylan, O., & Haydar, A. (2004). Artificial neural network models in prediction of the moisture content of a spray drying process. Journal of the Korean Ceramic Society, 41(5), 353–358. https://doi.org/ 10.4191/KCERS.2004.41.5.353
Tümer, A. E., & Edebali, S. (2019). Modeling of trivalent chromium sorption onto commercial resins by artificial neural network. Applied Artificial Intelligence, 33(4), 349–360. https://doi.org/10.1080/08839514.2019.1577015
Torrecilla, J. S., Aragón, J. M., & Palancar, M. C. (2005). Modeling the drying of a high-moisture solid with an artificial neural network. Industrial & Engineering Chemistry Research, 44(21), 8057–8066. https://doi.org/10.1021/ie0490435
Torrecilla, J. S., Aragón, J. M., & Palancar, M. C. (2008). Optimization of an artificial neural network by selecting the training function. Application to olive oil mills waste. Industrial & Engineering Chemistry Research, 47(18), 7072–7080. https:/doi.org/10.1021/ie8001205
Uzair, M., & Jamil, N. (2020, November). Effects of hidden layers on the efficiency of neural networks. IEEE 23rd International Multitopic Conference (INMIC) 2020, 1–6. https://doi.org/10.1109/INMIC50486.2020.9318195.
Ukaoha, K. C., & Igodan, E. C. (2019). Architecture optimization model for the deep neural network. International Journal of Intelligent Computing and Information Sciences, 19(2), 1–16. https://doi.org/ 10.21608/ijicis.2019.96101
Wilamowski, B. M. (2013, June). Comparison of training algorithms and network architectures. IEEE 17th International Conference on Intelligent Engineering Systems (INES) 2013, 11–11. IEEE. https:/doi.org/10.1109/INES.2013.6632792.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.