Design of a Decision Support System for Functional Beverage Flavoring

Main Article Content

Ariya Ounsri
Pornthip Tabkosai
Athakorn Kengpol
Sopida Tuammee


The objective of research is to design and develop a Decision Support System (DSS) software to assess customer satisfaction on functional beverage flavor notes. Questionnaire is launched to gather data of costumer preference. The taste, color and odor are the subjects of questionnaire. Data is acquired from 400 customers in six groups from North, North Eastern, Central, Southern, and Bangkok of Thailand that have different gender and age. The survey shows that there are 5 well known tastes of functional drinks which are mango, passion fruit, Thai blueberry, linhzhi and mangosteen in both level of concentration (100% and mixed). The DSS is analyzed by using ANN in comparison with hybrid Artificial Neural Network and Particle Swarm Optimization (ANN-PSO). Both models give the same results shown in structure (6-18-30). The minimum MSE is 0.0054784 at 6 epochs. As a result of comparison between two models, the result shows that minimum speed time of ANN-PSO faster than ANNs. Hence, ANN-PSO is an appropriate system for using in the DSS software.

Article Details

How to Cite
Ounsri, A., Tabkosai, P., Kengpol, A., & Tuammee, S. (2020). Design of a Decision Support System for Functional Beverage Flavoring. Applied Science and Engineering Progress, 13(2), 112–117. Retrieved from
Research Articles


[1] M. Ceballos, “Characterisation of tequila according to their major volatile composition using multilayer perceptron neural networks,” Food Chemistry, vol. 136, pp. 1309–1315, Feb. 2013.

[2] S. Leung, Y. Tang, and W. Wong, “A hybrid particle swarm optimization and its application in neural networks,” Expert Systems with Applications, vol. 39, pp. 395–405, Jan. 2012.

[3] T. C. Union Global Public Company Limited. (2009, Jan.). The functional drink of marketing versus demand. T. C. Union Global Public Company Limited. Bangkok, Thailand [Online]. Available: (in Thai)

[4] A. Kengpol and W. Wangkananon, “An assessment of customer contentment for ready-to-drink tea flavour notes using artificial neural networks,” Toward Sustainable Operations of Supply Chain and Logistics Systems. Part of the Series EcoProduction, vol. 1, pp. 421–434, Jan. 2015.

[5] A. Kengpol, S. Tuamee, and W. Meethom “Design of a decision support system on selection of multimodal transportation with environmental consideration between Thailand and Vietnam,” KMUTNB International Journal of Applied Science and Technology, vol. 5, pp. 55–63, Feb. 2012.

[6] A. Kengpol and W. Wangkananon, “The expert system for assessing customer satisfaction on fragrance notes: Using artificial neural networks,” Computers & Industrial Engineering, vol. 51, pp. 567–584, Jan. 2006.

[7] A. J. Danial, “Developing a hybrid PSO–ANN model for estimating the ultimate bearing capacity of rock-socketed piles,” Neural Computing and Applications, vol. 28, pp. 391–405, Feb. 2017.

[8] P. Tabkosai and A. Kengpol, “The development of a database management for product development: A case study in a wire harness manufacturer”, presented at the IE Network, Khonkan, Thailand, Jul. 7–8, 2016.