Design of a Decision Support System for Functional Beverage Flavoring

Abstract

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.